DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This is a Final Action on the merits. Claims 1, 4-8, 10-12, 14-18, and 20-21 are currently pending and are addressed below.
Response to Amendments
The amendment filed on December 1st, 2025 has been considered and entered. Accordingly, claims 1, 8, 11, 18, and 21 have been amended.
Response to Arguments
The applicant’s arguments with respect to claims 1, 4-8, 10-12, 14, 17-18, and 20-21 have been considered but are moot in view of the newly formulated grounds of rejections necessitated by the applicant’s amendments,
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 5, 7-8, 11-12, 17-18, and 21 are rejected under 35 U.S.C. 103 as being unpatentable over Levinson (JP 2018538647 A) (“Levinson”) (Translation Attached) in view of Fok (US 20210356277 A1) (“Fok”) in view of Tebbens (US 20220187837 A1) (“Tebbens”) in view of Hou (US 20200209002 A1) (“Hou”) in view of Miwa (US 10533859 B2) (“Miwa”) in view of Bonanni (US 20210207968 A1) (“Bonanni”).
With respect to claim 1, Levinson teaches detecting a trigger event comprising an object detection by a vehicle while in use; responsive to said detecting, triggering performance of a vehicle simulation by at least one computing device onboard the vehicle while the vehicle is still in use performing the vehicle simulation as part of a map validation process by the onboard computing device to validate a road or terrain map for possibly facilitating control of the vehicle currently in use, the map validation process (See at least Levinson FIG. 2 and Paragraphs 18-19 “FIG. 2 is an example of a flow diagram for monitoring a group of autonomous vehicles according to some embodiments. At 202, flow 200 begins when a group of autonomous vehicles is monitored. At least one autonomous vehicle includes an autonomous vehicle controller configured to autonomously move the vehicle from a first geographic region to a second geographic region. At 204, data representative of an event associated with the calculated confidence level of the vehicle is detected. An event may be a condition or situation that affects the operation of an autonomous vehicle or may affect its operation. The event may be inside or outside the autonomous vehicle. For example, an obstruction blocking a road and a reduction or loss of communication can be seen as an event. An event may include an unexpected or abnormal number or type of external object (or track) perceived by traffic conditions or congestion and the perception engine. The event may be based on weather conditions, such as weather-related conditions (eg loss of friction due to ice or rain) or low angles to the horizon making sunlight bright in the eyes of a human driver of another vehicle (For example, at sunset). These and other conditions can be seen as events that cause a remote operator service call or cause the vehicle to perform a safe stop trajectory. At 206, data representing a subset of candidate trajectories may be received from the autonomous vehicle in response to the detection of the event. For example, a planner of an autonomous vehicle controller can calculate and evaluate multiple trajectories (eg, thousands or more) per unit time such as 1 second. In some embodiments, the candidate trajectory may be a relatively higher confidence level at which the autonomous vehicle can safely be advanced in consideration of the event (eg, using an alternative route provided by the remote operator) Which is a subset of the trajectory. It should be noted that some candidate trajectories may be ranked higher than other candidate trajectories or may be associated with higher confidence than other candidate trajectories. According to some examples, a subset of candidate trajectories may be generated by any number of planners, such as a planner, a remote operator computing device (eg, a remote operator can determine and provide an approximate path) It can be derived from the source or can be combined as a subset of candidate trajectories. At 208, route guidance data may be identified at one or more processors. The route guidance data may be configured to aid the remote operator in selecting a trajectory to be guided from one or more of the candidate trajectories. In some instances, the route guidance data indicates a confidence level or probability indicating a certainty that a particular candidate trajectory can reduce or ignore the likelihood that the event may affect the operation of the autonomous vehicle Specify a value. The guided trajectory as a candidate trajectory to be chosen may be input at 210 at the input from the remote operator (eg, the remote operator may select at least one candidate trajectory from a group of differently ranked candidate trajectories, Which can be selected as the guided trajectory). Selection may be made via an operator interface listing several candidate trajectories, for example in order from highest confidence level to lowest confidence level. At 212 the selection of a candidate trajectory as a guided trajectory may be sent to the vehicle which is guided to resolve the condition by causing the vehicle to perform the operation specified by the remote operator Perform orbit. As such, autonomous vehicles can transition from non-canonical operating states.” | Paragraph 54 “The simulator interface controller 1414 is configured to provide an interface between the simulator 1440 and the remote operator computing device 1404. For example, sensor data from a group of autonomous vehicles is applied to reference data updater 1438 via autonomous ("AV") group data 1470, whereby reference data updater 1438 generates an updated map and route data 1439 I think that it is configured to do. In some embodiments, the updated map and route data 1439 may be released beforehand as updates to data in the map data repositories 1420 and 1422 or as updates to data in the route data repository 1424 it can. In this case, such data may include, for example, a lower threshold for requesting remote operator service may be implemented when a map tile containing pre-updated information is used by an autonomous vehicle Beta version "as shown in FIG. Further, the updated map and route data 1439 may be introduced to the simulator 1440 to verify the updated map data. Upon receiving the full release (eg, at the end of the beta test), the previously lowered threshold for requesting remote operator service is canceled. The user interface graphics controller 1410 provides rich graphics to the remote operator 1408 so that a group of autonomous vehicles can be simulated within the simulator 1440 and the simulated autonomous vehicle Can be accessed via the remote operator computing device 1404 as if the groups are real”).
Levinson, however, fails to explicitly disclose obtaining, by the at least one computing device onboard the vehicle, the road or terrain map which has been updated to create a new version of the road or terrain map, wherein the road or terrain map comprises data about physical details of a geographic area in a real world environment; selecting, by the at least one computing device, a portion of the new version of the road or terrain map to be quality tested based on a current location of the vehicle, wherein a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane; generating, by the at least one computing device, a plurality of simulation routes for a simulated vehicle using the selected portion of the new version of the road or terrain map, wherein the simulation routes have different start locations for the simulated vehicle and different end locations for the simulated vehicle; selecting, by the at least one computing device, a simulation route from the plurality of simulation routes based on a result produced by an algorithm seeded with a map identifier, a map portion identifier, and lane identifiers; performing operations, by the at least one computing device, to simulate vehicle operations along the entire selected simulation route in the new version of the road or terrain map during a single simulation scenario, wherein the selected simulation route comprises a start location, an end location and two or more test lanes of interest, the start and end locations both reside outside of the two or more test lanes of interest, and the two or more test lanes of interest are tested in the single simulation scenario; analyzing, by the at least one computing device, results from the simulating to determine whether a quality of the new version of the road or terrain map is validated or invalidated; selecting, by the at least one computing device, a prior version of the road or terrain map based on a result of said analyzing indicating that the quality of the new version of the road or terrain map is invalidated; and controlling, by the at least one computing device, autonomous or semi-autonomous operations of the vehicle using the prior version of the road or terrain map which was selected.
Fok teaches obtaining, by the at least one computing device, a road or terrain map which has been updated to create a new version of the road or terrain map, wherein the road or terrain map comprises data about physical details of a geographic area in a real world environment (See at least Fok FIG. 3 “304”)
generating, by the at least one computing device, a plurality of simulation routes for a simulated vehicle using the selected portion of the new version of the road or terrain map, wherein the simulation routes have different start locations for the simulated vehicle and different end locations for the simulated vehicle (Generating multiple simulation routes: See at least Fok Fig. 3 “308” and Paragraph 47 “test route”; ¶ 1 “validation tests . . . tests may be generated based on a simulated autonomous vehicle traversing the one or more road features” | Paragraph 52).
performing operations, by the at least one computing device, to simulate vehicle operations along the entire selected simulation route in the new version of the road or terrain map during a single simulation scenario, wherein the selected simulation route comprises a start location, an end location and two or more test lanes of interest, the start and end locations both reside outside of the two or more test lanes of interest, and the two or more test lanes of interest are tested in the single simulation scenario (Simulate vehicle traveling on each route: See at least Fok Fig. 3 ”312” and “314” and Paragraphs 48 and 49 “The one or more validation tests may be executed over the different ones of the multiple test route subsections at 314. Executing the one or more validation tests may include simulating an autonomous vehicle to transverse the test route subsections”) (Fok Fig 4 shows starting point 402 and 404 are outside of lanes that the vehicle will travel during simulation: See also at least Paragraph 52).
analyzing, by the at least one computing device, results from the simulating to determine whether a quality of the new version of the road or terrain map is validated or invalidated (Analyzing results to determine validity of map: See at least Fok Fig. 3 “316” and Paragraphs 50-51 i.e., “process 300 may include determining whether the one or more validation tests pass or fail, and outputting the results”).
selecting a version of the map based on said results of said analyzing (See at least Fok FIG. 3).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Levinson to include obtaining, by the at least one computing device, a road or terrain map which has been updated to create a new version of the road or terrain map, wherein the road or terrain map comprises data about physical details of a geographic area in a real world environment; generating, by the at least one computing device, a plurality of simulation routes for a simulated vehicle using the selected portion of the new version of the road or terrain map, wherein the simulation routes have different start locations for the simulated vehicle and different end locations for the simulated vehicle; performing operations, by the at least one computing device, to simulate vehicle operations along the entire selected simulation route in the new version of the road or terrain map during a single simulation scenario, wherein the selected simulation route comprises a start location, an end location and two or more test lanes of interest, the start and end locations both reside outside of the two or more test lanes of interest, and the two or more test lanes of interest are tested in the single simulation scenario; analyzing, by the at least one computing device, results from the simulating to determine whether a quality of the new version of the road or terrain map is validated or invalidated; and selecting a version of the map based on said results of said analyzing, as taught by Fok as disclosed above, in order to ensure an accurate and efficient validation process of a vehicle map (Fok Paragraph 1 “The present disclosure relates generally to validating maps, and in particular, some embodiments relate to automatically generating map validation tests corresponding to multiple test route subsections.”).
Levinson in view of Fok, however, fails to explicitly disclose that the computing device is onboard the vehicle; selecting, by the at least one computing device, a portion of the new version of the road or terrain map to be quality tested based on a current location of the vehicle, wherein a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane, selecting, by the at least one computing device, a simulation route from the plurality of simulation routes based on a result produced by an algorithm seeded with a map identifier, a map portion identifier, and lane identifiers; and controlling, by the at least one computing device, autonomous or semi-autonomous operations of the vehicle using the prior version of the map which was selected.
Tebbens teaches selecting, by the at least one computing device, a simulation route from the plurality of simulation routes based on a result produced by an algorithm seeded with a map identifier, a map portion identifier, and lane identifiers (See at least Tebbens Paragraph 107 “Scenario database 505 stores various driving scenarios. Examples of driving scenarios include any situation or circumstance that a vehicle may encounter in the real-world. An example scenario can include a scenario that is associated with (e.g., involves, concentrates on, and/or the like) an avoidance maneuver at a particular map location performed with one or more agents (e.g., other vehicles, pedestrians) present in the vicinity, in a variety of different road geometries (e.g., near or at junctions and intersections, lane splittings and lane reductions, turns and filtering lanes, etc.). Each scenario can be designed to emphasize certain aspects of a behavior to be tested. Each of the scenarios can define limits of acceptable behavior, determine common anomalies, which include both behavioral patterns of human drivers to be avoided, and unreasonable decisions made by the vehicle. Scenarios include checks to validate the full complexity of potential behaviors in the scenario. FIGS. 6A-6D illustrate example scenarios.” | Paragraph 156 “FIG. 18 illustrates using the rule-based trajectory evaluation system to compare two candidate trajectories and select one of the trajectories based on a number of rulebook violations, in accordance with one or more embodiments. Trajectories 1804 a, 1804 b generated for a particular scenario configuration 1801 are evaluated 1805 for violations of rules in rulebook(s) 1803. In an embodiment, the results of the evaluations (e.g., violation score of the most important violated rule, or a weighted sum of violations) are scores that can be compared to determine which trajectory has the least violation of the rulebook 1803, and the trajectory with the least violation is selected as the best trajectory for the ego vehicle to take for scenario 1803.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Levinson in view of Fok to include selecting, by the at least one computing device, a simulation route from the plurality of simulation routes based on a result produced by an algorithm seeded with a map identifier, a map portion identifier, and lane identifiers, as taught by Tebbens as disclosed above, in order to ensure efficient simulation route selection (Tebbens Paragraph 1 “The description that follows relates generally to tools for validating the behavior of an autonomous vehicle under different driving scenarios”).
Levinson in view of Fok in view of Tebbens, however, fails to explicitly disclose that the computing device is onboard the vehicle; selecting a portion of the new version of the road or terrain map to be quality tested based on a current location of the vehicle, wherein a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane; and controlling, by the at least one computing device, autonomous or semi-autonomous operations of the vehicle using the prior version of the map which was selected.
Hou, however, teaches that the computing device is onboard the vehicle (See at least Hou Paragraph 61 “While FIG. 1B describes certain operations as being performed by the vehicle 120 or the server 130, this is not meant to be limiting. The operations performed by the vehicle 120 and the server 130 as described herein can be performed by either entity.”)
selecting a portion of the new version of the road or terrain map to be quality tested based on a current location of the vehicle (Vehicle location is used to determines area of the map to be validated: See at least Hou FIG. 7 “710” and “712” and Paragraphs 180-181 “At block 710, the telemetry analysis system identifies particular telemetry data of interest. For example, the telemetry data of interest may be identified by vehicle position data, vehicle orientation data, time stamp data, and/or the like. At block 712, the telemetry data of interest may be used to validate the route, to validate the map used to generate the map”).
controlling, by the at least one computing device, autonomous or semi-autonomous operations of the vehicle using the version of the road or terrain map which was selected (Vehicle follows map when map and its route when determined it is validated: See at least Hou Paragraph 154-155 “ The vehicle may also determine that it cannot determine whether or not there is an exception event or the likelihood of an exception event. If the likelihood does not exceed the corresponding threshold, at block 514, the vehicle continues using the current route for navigation” and Fig. 5 “514”).
It would have been obvious to one of ordinary skill in the art to have modified the method of Levinson in view of Fok in view of Tebbens to include that the computing device is onboard the vehicle and selecting a portion of the new version of the road or terrain map to be quality tested based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane, as taught by Hou as disclosed above, such that the map which has been updated to create a new version of the map is obtained by the vehicle’s onboard computing device, and controlling, by the at least one computing device, autonomous or semi-autonomous operations of the vehicle using the version of the map which was selected, as taught by Hou as disclosed above, in order to ensure safe travel of the autonomous vehicle (Hou Paragraph 6 “In response to detecting that the environment is such that it is impossible or disadvantageous to continue using the initial route at a given route node, the corresponding alternative route may be identified and selected”) and because Fok suggests using validated maps for autonomous vehicle control (¶ 22 “vehicles may utilize validated maps to enable autonomous Driving”; ¶45).
Levinson in view of Fok in view of Tebbens in view of Hou fail to explicitly disclose wherein a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane selecting a prior version of the road or terrain map based on a result of said analyzing indicating that the quality of the new version of the road or terrain map is invalidated.
Miwa, however, teaches selecting a prior version of the road or terrain map based on a result of said analyzing indicating that the quality of the new version of the road or terrain map is invalidated (See at least Miwa Col. 11 lines 17-36 “When displaying a map with sections 1 to 4 using updated map data, the updated management data (A′) designates section data (C1, C4) corresponding with sections 1, 4 having non-updated section data and also designates updated section data (C2′, C3′), which has updated section data for sections 2, 3, as having priority over section data (C2, C3) from before the update. Then, in the case of a malfunction occurring with the updated section data, the management data (A) before the update is activated instead of the updated management data (A′), this update management data (A) before the update does not designate the updated section data (C2′, C3′) but designates the section data C1 to C4, with which a map corresponding to sections 1 to 4 is displayed. According to the map update system of embodiments of the present invention, because the update section data before the update also remains in the map data storing unit 32 in the navigation device 3, even if a malfunction occurs in the updated data, a map can be continuously displayed by switching to the data before the update” | Claim 2 “display the navigation map based on the updated section data and the current section data designated both by the updated management data, and display the navigation map based on the current section data designated by the current management data, instead of the updated management data, in a case where the updated section data including an error.”).
It would have been obvious to one of ordinary skill in the art to have modified the method of Levinson in view of Fok in view of Tebbens in view of Hou to include selecting a prior version of the road or terrain map based on a result of said analyzing indicating that the quality of the new version of the road or terrain map is invalidated, as taught by Miwa as disclosed above, such that the vehicle is controlled using the selected prior version of the map, in order to ensure accurate maps are used for autonomous travel (Miwa Paragraph 9 “An aspect relates to enabling continuous and stable display of a map in a navigation device.”).
Levinson in view of Fok in view of Tebbens in view of Hou in view of Miwa fail to explicitly disclose that a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane.
Bonanni teaches that wherein a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane (See at least Bonanni FIGS. 13A-15 and Paragraph 111 “In some embodiments, the disclosed techniques involve modifying or determining a particular route for the AV so that the AV can obtain updated map data by collecting environmental information with sensors on the AV while transporting a user of the AV (e.g., a rider such as, for example, a paying rideshare customer) to their destination. In some embodiments, the disclosed techniques involve determining route planning data for a route of an AV (e.g., including modifying a driving behavior of the AV) so that the AV can collect updated map data for one or more sections of the route while also transporting the user of the AV to a specified destination.” | Paragraph 115 “In the embodiment shown in FIG. 13A, the selected route is determined by choosing edges 1310 that, collectively, minimize the cost (for example, the amount of time) to travel from start point 1302 to end point 1304. In some embodiments, the cost of traveling a particular route—represented in this example as the amount of time to travel the route—is calculated using formula (1)” | Paragraph 116 “As discussed above, the AV can be tasked with obtaining updated map data. In some embodiments, this can be performed while transporting the rider from start point 1302 to end point 1304. Specifically, the route used to transport the rider from start point 1302 to end point 1304 is determined (e.g., by planning module 404) in a manner that selectively incorporates edges 1310 according to the benefit obtained by traversing particular edges (e.g., the opportunity to collect updated map data for an unmapped road or a road that has not been recently surveyed). This permits use of the AV to obtain the updated map data” | Paragraphs 133-134 “FIG. 14 is a flow chart of an example process 1400 (also referred to as a method) for determining a route (e.g., a trajectory) of an autonomous vehicle (e.g., AV 100) in order to update map data used for navigating an autonomous vehicle in accordance with the embodiments discussed above … At 1402, the system (e.g., 120, 300, 400, or a combination thereof) obtains, using a processing circuit (e.g., planning module 404) (e.g., computing processor 146), map data including a starting location (e.g., starting point 1302) and a destination location (e.g., end point 1304) (e.g., a route starting location and a route destination location).”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Levinson in view of Fok in view of Tebbens in view of Hou in view of Miwa to include that wherein a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane, as taught by Bonanni as disclosed above, in order to ensure accurate locations for quality testing of maps (Bonanni Paragraph 3 “Because road conditions can change over time, maps used to navigate an autonomous vehicle may need to be updated to accurately convey the current configuration and condition of the roads.”).
With respect to claim 5, Levinson in view of Fok in view of Tebbens in view of Hou in view of Miwa in view of Bonanni teach that the quality of the new version of the road or terrain map is invalidated based on the data comprising additional data about a first physical detail of the geographic area which causes the vehicle to be unable to traverse a road as expected, and the quality of the new version of the road or terrain map is validated based on the data being absent of said additional data (See at least Fok FIG. 3 “316” and “322” and Paragraph 51 “Process 300 may be repeated for one or more of the validation tests that do not pass. The results may be used to update and/or modify the new and/or updated maps (e.g., the way points). In some embodiments, a failing result may cause the new and/or updated map to be re-segmented in a different way at 308. The new segmentation may then be tested and/or validated by steps 310-314. As such, for one or more validations tests that do not pass, the autonomous software and/or map may be modified at 322 in an attempt to correct failures before be re-tested.”)
With respect to claim 7, and similarly claim 17, Levinson in view of Fok in view of Tebbens in view of Hou in view of Miwa in view of Bonanni teach that said analyzing comprises considering the quality of the new version of the road or terrain map to be validated based on said results indicating that when the vehicle traversed all the simulation routes during the simulating without experiencing a fault of a type or without having to perform a dangerous maneuver (The validation of map quality is completed when there is a pass: See at least Fok FIG 3 “316” and “320” and at least Paragraphs 49-51).
With respect to claim 8, and similarly claim 18, son in view of Fok in view of Tebbens in view of Hou in view of Miwa in view of Bonanni teach that the shape and/or size of the selected portion is dynamically selected based on a combined score produced using a weighted combination of at least two of the time of day, the vehicle destination, the lane length and the estimated time of travel on a lane (See at least Bonanni FIGS. 13A-15 and Paragraph 111 “In some embodiments, the disclosed techniques involve modifying or determining a particular route for the AV so that the AV can obtain updated map data by collecting environmental information with sensors on the AV while transporting a user of the AV (e.g., a rider such as, for example, a paying rideshare customer) to their destination. In some embodiments, the disclosed techniques involve determining route planning data for a route of an AV (e.g., including modifying a driving behavior of the AV) so that the AV can collect updated map data for one or more sections of the route while also transporting the user of the AV to a specified destination.” | Paragraph 115 “In the embodiment shown in FIG. 13A, the selected route is determined by choosing edges 1310 that, collectively, minimize the cost (for example, the amount of time) to travel from start point 1302 to end point 1304. In some embodiments, the cost of traveling a particular route—represented in this example as the amount of time to travel the route—is calculated using formula (1) … where A and B denote the starting and ending points (e.g., start point 1302 and end point 1304), respectively, of the trip. The optimal value, or solution, for the cost function of formula (1) is represented as minimum travel time T*. In this embodiment, minimum travel time T* is achieved using the bolded edges 1310 shown in FIG. 13A.” | Paragraph 116 “As discussed above, the AV can be tasked with obtaining updated map data. In some embodiments, this can be performed while transporting the rider from start point 1302 to end point 1304. Specifically, the route used to transport the rider from start point 1302 to end point 1304 is determined (e.g., by planning module 404) in a manner that selectively incorporates edges 1310 according to the benefit obtained by traversing particular edges (e.g., the opportunity to collect updated map data for an unmapped road or a road that has not been recently surveyed). This permits use of the AV to obtain the updated map data” | Paragraphs 133-134 “FIG. 14 is a flow chart of an example process 1400 (also referred to as a method) for determining a route (e.g., a trajectory) of an autonomous vehicle (e.g., AV 100) in order to update map data used for navigating an autonomous vehicle in accordance with the embodiments discussed above … At 1402, the system (e.g., 120, 300, 400, or a combination thereof) obtains, using a processing circuit (e.g., planning module 404) (e.g., computing processor 146), map data including a starting location (e.g., starting point 1302) and a destination location (e.g., end point 1304) (e.g., a route starting location and a route destination location).”).
With respect to claim 11, Levinson teaches A system, comprising:
a processor; a non-transitory computer-readable storage medium comprising programming instructions that are configured to cause the processor to implement a method for map quality assurance (See at least Levinson Paragraph 89);
detecting a trigger event comprising an object detection by a vehicle while in use; responsive to said detecting, triggering performance of a vehicle simulation by at least one computing device onboard the vehicle while the vehicle is still in use performing the vehicle simulation as part of a map validation process by the onboard computing device to validate a road or terrain map for possibly facilitating control of the vehicle currently in use, the map validation process (See at least Levinson FIG. 2 and Paragraphs 18-19 “FIG. 2 is an example of a flow diagram for monitoring a group of autonomous vehicles according to some embodiments. At 202, flow 200 begins when a group of autonomous vehicles is monitored. At least one autonomous vehicle includes an autonomous vehicle controller configured to autonomously move the vehicle from a first geographic region to a second geographic region. At 204, data representative of an event associated with the calculated confidence level of the vehicle is detected. An event may be a condition or situation that affects the operation of an autonomous vehicle or may affect its operation. The event may be inside or outside the autonomous vehicle. For example, an obstruction blocking a road and a reduction or loss of communication can be seen as an event. An event may include an unexpected or abnormal number or type of external object (or track) perceived by traffic conditions or congestion and the perception engine. The event may be based on weather conditions, such as weather-related conditions (eg loss of friction due to ice or rain) or low angles to the horizon making sunlight bright in the eyes of a human driver of another vehicle (For example, at sunset). These and other conditions can be seen as events that cause a remote operator service call or cause the vehicle to perform a safe stop trajectory. At 206, data representing a subset of candidate trajectories may be received from the autonomous vehicle in response to the detection of the event. For example, a planner of an autonomous vehicle controller can calculate and evaluate multiple trajectories (eg, thousands or more) per unit time such as 1 second. In some embodiments, the candidate trajectory may be a relatively higher confidence level at which the autonomous vehicle can safely be advanced in consideration of the event (eg, using an alternative route provided by the remote operator) Which is a subset of the trajectory. It should be noted that some candidate trajectories may be ranked higher than other candidate trajectories or may be associated with higher confidence than other candidate trajectories. According to some examples, a subset of candidate trajectories may be generated by any number of planners, such as a planner, a remote operator computing device (eg, a remote operator can determine and provide an approximate path) It can be derived from the source or can be combined as a subset of candidate trajectories. At 208, route guidance data may be identified at one or more processors. The route guidance data may be configured to aid the remote operator in selecting a trajectory to be guided from one or more of the candidate trajectories. In some instances, the route guidance data indicates a confidence level or probability indicating a certainty that a particular candidate trajectory can reduce or ignore the likelihood that the event may affect the operation of the autonomous vehicle Specify a value. The guided trajectory as a candidate trajectory to be chosen may be input at 210 at the input from the remote operator (eg, the remote operator may select at least one candidate trajectory from a group of differently ranked candidate trajectories, Which can be selected as the guided trajectory). Selection may be made via an operator interface listing several candidate trajectories, for example in order from highest confidence level to lowest confidence level. At 212 the selection of a candidate trajectory as a guided trajectory may be sent to the vehicle which is guided to resolve the condition by causing the vehicle to perform the operation specified by the remote operator Perform orbit. As such, autonomous vehicles can transition from non-canonical operating states.” | Paragraph 54 “The simulator interface controller 1414 is configured to provide an interface between the simulator 1440 and the remote operator computing device 1404. For example, sensor data from a group of autonomous vehicles is applied to reference data updater 1438 via autonomous ("AV") group data 1470, whereby reference data updater 1438 generates an updated map and route data 1439 I think that it is configured to do. In some embodiments, the updated map and route data 1439 may be released beforehand as updates to data in the map data repositories 1420 and 1422 or as updates to data in the route data repository 1424 it can. In this case, such data may include, for example, a lower threshold for requesting remote operator service may be implemented when a map tile containing pre-updated information is used by an autonomous vehicle Beta version "as shown in FIG. Further, the updated map and route data 1439 may be introduced to the simulator 1440 to verify the updated map data. Upon receiving the full release (eg, at the end of the beta test), the previously lowered threshold for requesting remote operator service is canceled. The user interface graphics controller 1410 provides rich graphics to the remote operator 1408 so that a group of autonomous vehicles can be simulated within the simulator 1440 and the simulated autonomous vehicle Can be accessed via the remote operator computing device 1404 as if the groups are real”).
Levinson, however, fails to explicitly disclose obtaining, by the at least one computing device onboard the vehicle, the road or terrain map which has been updated to create a new version of the road or terrain map, wherein the road or terrain map comprises data about physical details of a geographic area in a real world environment; selecting, by the at least one computing device, a portion of the new version of the road or terrain map to be quality tested based on a current location of the vehicle, wherein a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane; generating, by the at least one computing device, a plurality of simulation routes for a simulated vehicle using the selected portion of the new version of the road or terrain map, wherein the simulation routes have different start locations for the simulated vehicle and different end locations for the simulated vehicle; selecting, by the at least one computing device, a simulation route from the plurality of simulation routes based on a result produced by an algorithm seeded with a map identifier, a map portion identifier, and lane identifiers; performing operations, by the at least one computing device, to simulate vehicle operations along the entire selected simulation route in the new version of the road or terrain map during a single simulation scenario, wherein the selected simulation route comprises a start location, an end location and two or more test lanes of interest, the start and end locations both reside outside of the two or more test lanes of interest, and the two or more test lanes of interest are tested in the single simulation scenario; analyzing, by the at least one computing device, results from the simulating to determine whether a quality of the new version of the road or terrain map is validated or invalidated; selecting, by the at least one computing device, a prior version of the road or terrain map based on a result of said analyzing indicating that the quality of the new version of the road or terrain map is invalidated; and controlling, by the at least one computing device, autonomous or semi-autonomous operations of the vehicle using the prior version of the road or terrain map which was selected.
Fok teaches obtaining, by the at least one computing device, a road or terrain map which has been updated to create a new version of the road or terrain map, wherein the road or terrain map comprises data about physical details of a geographic area in a real world environment (See at least Fok FIG. 3 “304”)
generating, by the at least one computing device, a plurality of simulation routes for a simulated vehicle using the selected portion of the new version of the road or terrain map, wherein the simulation routes have different start locations for the simulated vehicle and different end locations for the simulated vehicle (Generating multiple simulation routes: See at least Fok Fig. 3 “308” and Paragraph 47 “test route”; ¶ 1 “validation tests . . . tests may be generated based on a simulated autonomous vehicle traversing the one or more road features” | Paragraph 52).
performing operations, by the at least one computing device, to simulate vehicle operations along the entire selected simulation route in the new version of the road or terrain map during a single simulation scenario, wherein the selected simulation route comprises a start location, an end location and two or more test lanes of interest, the start and end locations both reside outside of the two or more test lanes of interest, and the two or more test lanes of interest are tested in the single simulation scenario (Simulate vehicle traveling on each route: See at least Fok Fig. 3 ”312” and “314” and Paragraphs 48 and 49 “The one or more validation tests may be executed over the different ones of the multiple test route subsections at 314. Executing the one or more validation tests may include simulating an autonomous vehicle to transverse the test route subsections”) (Fok Fig 4 shows starting point 402 and 404 are outside of lanes that the vehicle will travel during simulation: See also at least Paragraph 52).
analyzing, by the at least one computing device, results from the simulating to determine whether a quality of the new version of the road or terrain map is validated or invalidated (Analyzing results to determine validity of map: See at least Fok Fig. 3 “316” and Paragraphs 50-51 i.e., “process 300 may include determining whether the one or more validation tests pass or fail, and outputting the results”).
selecting a version of the map based on said results of said analyzing (See at least Fok FIG. 3).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Levinson to include obtaining, by the at least one computing device, a road or terrain map which has been updated to create a new version of the road or terrain map, wherein the road or terrain map comprises data about physical details of a geographic area in a real world environment; generating, by the at least one computing device, a plurality of simulation routes for a simulated vehicle using the selected portion of the new version of the road or terrain map, wherein the simulation routes have different start locations for the simulated vehicle and different end locations for the simulated vehicle; performing operations, by the at least one computing device, to simulate vehicle operations along the entire selected simulation route in the new version of the road or terrain map during a single simulation scenario, wherein the selected simulation route comprises a start location, an end location and two or more test lanes of interest, the start and end locations both reside outside of the two or more test lanes of interest, and the two or more test lanes of interest are tested in the single simulation scenario; analyzing, by the at least one computing device, results from the simulating to determine whether a quality of the new version of the road or terrain map is validated or invalidated; and selecting a version of the map based on said results of said analyzing, as taught by Fok as disclosed above, in order to ensure an accurate and efficient validation process of a vehicle map (Fok Paragraph 1 “The present disclosure relates generally to validating maps, and in particular, some embodiments relate to automatically generating map validation tests corresponding to multiple test route subsections.”).
Levinson in view of Fok, however, fails to explicitly disclose that the computing device is onboard the vehicle; selecting, by the at least one computing device, a portion of the new version of the road or terrain map to be quality tested based on a current location of the vehicle, wherein a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane, selecting, by the at least one computing device, a simulation route from the plurality of simulation routes based on a result produced by an algorithm seeded with a map identifier, a map portion identifier, and lane identifiers; and controlling, by the at least one computing device, autonomous or semi-autonomous operations of the vehicle using the prior version of the map which was selected.
Tebbens teaches selecting, by the at least one computing device, a simulation route from the plurality of simulation routes based on a result produced by an algorithm seeded with a map identifier, a map portion identifier, and lane identifiers (See at least Tebbens Paragraph 107 “Scenario database 505 stores various driving scenarios. Examples of driving scenarios include any situation or circumstance that a vehicle may encounter in the real-world. An example scenario can include a scenario that is associated with (e.g., involves, concentrates on, and/or the like) an avoidance maneuver at a particular map location performed with one or more agents (e.g., other vehicles, pedestrians) present in the vicinity, in a variety of different road geometries (e.g., near or at junctions and intersections, lane splittings and lane reductions, turns and filtering lanes, etc.). Each scenario can be designed to emphasize certain aspects of a behavior to be tested. Each of the scenarios can define limits of acceptable behavior, determine common anomalies, which include both behavioral patterns of human drivers to be avoided, and unreasonable decisions made by the vehicle. Scenarios include checks to validate the full complexity of potential behaviors in the scenario. FIGS. 6A-6D illustrate example scenarios.” | Paragraph 156 “FIG. 18 illustrates using the rule-based trajectory evaluation system to compare two candidate trajectories and select one of the trajectories based on a number of rulebook violations, in accordance with one or more embodiments. Trajectories 1804 a, 1804 b generated for a particular scenario configuration 1801 are evaluated 1805 for violations of rules in rulebook(s) 1803. In an embodiment, the results of the evaluations (e.g., violation score of the most important violated rule, or a weighted sum of violations) are scores that can be compared to determine which trajectory has the least violation of the rulebook 1803, and the trajectory with the least violation is selected as the best trajectory for the ego vehicle to take for scenario 1803.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Levinson in view of Fok to include selecting, by the at least one computing device, a simulation route from the plurality of simulation routes based on a result produced by an algorithm seeded with a map identifier, a map portion identifier, and lane identifiers, as taught by Tebbens as disclosed above, in order to ensure efficient simulation route selection (Tebbens Paragraph 1 “The description that follows relates generally to tools for validating the behavior of an autonomous vehicle under different driving scenarios”).
Levinson in view of Fok in view of Tebbens, however, fails to explicitly disclose that the computing device is onboard the vehicle; selecting a portion of the new version of the road or terrain map to be quality tested based on a current location of the vehicle, wherein a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane; and controlling, by the at least one computing device, autonomous or semi-autonomous operations of the vehicle using the prior version of the map which was selected.
Hou, however, teaches that the computing device is onboard the vehicle (See at least Hou Paragraph 61 “While FIG. 1B describes certain operations as being performed by the vehicle 120 or the server 130, this is not meant to be limiting. The operations performed by the vehicle 120 and the server 130 as described herein can be performed by either entity.”)
selecting a portion of the new version of the road or terrain map to be quality tested based on a current location of the vehicle (Vehicle location is used to determines area of the map to be validated: See at least Hou FIG. 7 “710” and “712” and Paragraphs 180-181 “At block 710, the telemetry analysis system identifies particular telemetry data of interest. For example, the telemetry data of interest may be identified by vehicle position data, vehicle orientation data, time stamp data, and/or the like. At block 712, the telemetry data of interest may be used to validate the route, to validate the map used to generate the map”).
controlling, by the at least one computing device, autonomous or semi-autonomous operations of the vehicle using the version of the road or terrain map which was selected (Vehicle follows map when map and its route when determined it is validated: See at least Hou Paragraph 154-155 “ The vehicle may also determine that it cannot determine whether or not there is an exception event or the likelihood of an exception event. If the likelihood does not exceed the corresponding threshold, at block 514, the vehicle continues using the current route for navigation” and Fig. 5 “514”).
It would have been obvious to one of ordinary skill in the art to have modified the method of Levinson in view of Fok in view of Tebbens to include that the computing device is onboard the vehicle and selecting a portion of the new version of the road or terrain map to be quality tested based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane, as taught by Hou as disclosed above, such that the map which has been updated to create a new version of the map is obtained by the vehicle’s onboard computing device, and controlling, by the at least one computing device, autonomous or semi-autonomous operations of the vehicle using the version of the map which was selected, as taught by Hou as disclosed above, in order to ensure safe travel of the autonomous vehicle (Hou Paragraph 6 “In response to detecting that the environment is such that it is impossible or disadvantageous to continue using the initial route at a given route node, the corresponding alternative route may be identified and selected”) and because Fok suggests using validated maps for autonomous vehicle control (¶ 22 “vehicles may utilize validated maps to enable autonomous Driving”; ¶45).
Levinson in view of Fok in view of Tebbens in view of Hou fail to explicitly disclose wherein a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane selecting a prior version of the road or terrain map based on a result of said analyzing indicating that the quality of the new version of the road or terrain map is invalidated.
Miwa, however, teaches selecting a prior version of the road or terrain map based on a result of said analyzing indicating that the quality of the new version of the road or terrain map is invalidated (See at least Miwa Col. 11 lines 17-36 “When displaying a map with sections 1 to 4 using updated map data, the updated management data (A′) designates section data (C1, C4) corresponding with sections 1, 4 having non-updated section data and also designates updated section data (C2′, C3′), which has updated section data for sections 2, 3, as having priority over section data (C2, C3) from before the update. Then, in the case of a malfunction occurring with the updated section data, the management data (A) before the update is activated instead of the updated management data (A′), this update management data (A) before the update does not designate the updated section data (C2′, C3′) but designates the section data C1 to C4, with which a map corresponding to sections 1 to 4 is displayed. According to the map update system of embodiments of the present invention, because the update section data before the update also remains in the map data storing unit 32 in the navigation device 3, even if a malfunction occurs in the updated data, a map can be continuously displayed by switching to the data before the update” | Claim 2 “display the navigation map based on the updated section data and the current section data designated both by the updated management data, and display the navigation map based on the current section data designated by the current management data, instead of the updated management data, in a case where the updated section data including an error.”).
It would have been obvious to one of ordinary skill in the art to have modified the method of Levinson in view of Fok in view of Tebbens in view of Hou to include selecting a prior version of the road or terrain map based on a result of said analyzing indicating that the quality of the new version of the road or terrain map is invalidated, as taught by Miwa as disclosed above, such that the vehicle is controlled using the selected prior version of the map, in order to ensure accurate maps are used for autonomous travel (Miwa Paragraph 9 “An aspect relates to enabling continuous and stable display of a map in a navigation device.”).
Levinson in view of Fok in view of Tebbens in view of Hou in view of Miwa fail to explicitly disclose that a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane.
Bonanni teaches that wherein a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane (See at least Bonanni FIGS. 13A-15 and Paragraph 111 “In some embodiments, the disclosed techniques involve modifying or determining a particular route for the AV so that the AV can obtain updated map data by collecting environmental information with sensors on the AV while transporting a user of the AV (e.g., a rider such as, for example, a paying rideshare customer) to their destination. In some embodiments, the disclosed techniques involve determining route planning data for a route of an AV (e.g., including modifying a driving behavior of the AV) so that the AV can collect updated map data for one or more sections of the route while also transporting the user of the AV to a specified destination.” | Paragraph 115 “In the embodiment shown in FIG. 13A, the selected route is determined by choosing edges 1310 that, collectively, minimize the cost (for example, the amount of time) to travel from start point 1302 to end point 1304. In some embodiments, the cost of traveling a particular route—represented in this example as the amount of time to travel the route—is calculated using formula (1)” | Paragraph 116 “As discussed above, the AV can be tasked with obtaining updated map data. In some embodiments, this can be performed while transporting the rider from start point 1302 to end point 1304. Specifically, the route used to transport the rider from start point 1302 to end point 1304 is determined (e.g., by planning module 404) in a manner that selectively incorporates edges 1310 according to the benefit obtained by traversing particular edges (e.g., the opportunity to collect updated map data for an unmapped road or a road that has not been recently surveyed). This permits use of the AV to obtain the updated map data” | Paragraphs 133-134 “FIG. 14 is a flow chart of an example process 1400 (also referred to as a method) for determining a route (e.g., a trajectory) of an autonomous vehicle (e.g., AV 100) in order to update map data used for navigating an autonomous vehicle in accordance with the embodiments discussed above … At 1402, the system (e.g., 120, 300, 400, or a combination thereof) obtains, using a processing circuit (e.g., planning module 404) (e.g., computing processor 146), map data including a starting location (e.g., starting point 1302) and a destination location (e.g., end point 1304) (e.g., a route starting location and a route destination location).”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Levinson in view of Fok in view of Tebbens in view of Hou in view of Miwa to include that wherein a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane, as taught by Bonanni as disclosed above, in order to ensure accurate locations for quality testing of maps (Bonanni Paragraph 3 “Because road conditions can change over time, maps used to navigate an autonomous vehicle may need to be updated to accurately convey the current configuration and condition of the roads.”).
With respect to claim 21, Fok teaches a non-transitory computer-readable medium that stores instructions that, when executed by at least one computing device, will cause the at least one computing device to perform operations comprising:
a processor; a non-transitory computer-readable storage medium comprising programming instructions that are configured to cause the processor to implement a method for map quality assurance (See at least Levinson Paragraph 89);
detecting a trigger event comprising an object detection by a vehicle while in use; responsive to said detecting, triggering performance of a vehicle simulation by at least one computing device onboard the vehicle while the vehicle is still in use performing the vehicle simulation as part of a map validation process by the onboard computing device to validate a road or terrain map for possibly facilitating control of the vehicle currently in use, the map validation process (See at least Levinson FIG. 2 and Paragraphs 18-19 “FIG. 2 is an example of a flow diagram for monitoring a group of autonomous vehicles according to some embodiments. At 202, flow 200 begins when a group of autonomous vehicles is monitored. At least one autonomous vehicle includes an autonomous vehicle controller configured to autonomously move the vehicle from a first geographic region to a second geographic region. At 204, data representative of an event associated with the calculated confidence level of the vehicle is detected. An event may be a condition or situation that affects the operation of an autonomous vehicle or may affect its operation. The event may be inside or outside the autonomous vehicle. For example, an obstruction blocking a road and a reduction or loss of communication can be seen as an event. An event may include an unexpected or abnormal number or type of external object (or track) perceived by traffic conditions or congestion and the perception engine. The event may be based on weather conditions, such as weather-related conditions (eg loss of friction due to ice or rain) or low angles to the horizon making sunlight bright in the eyes of a human driver of another vehicle (For example, at sunset). These and other conditions can be seen as events that cause a remote operator service call or cause the vehicle to perform a safe stop trajectory. At 206, data representing a subset of candidate trajectories may be received from the autonomous vehicle in response to the detection of the event. For example, a planner of an autonomous vehicle controller can calculate and evaluate multiple trajectories (eg, thousands or more) per unit time such as 1 second. In some embodiments, the candidate trajectory may be a relatively higher confidence level at which the autonomous vehicle can safely be advanced in consideration of the event (eg, using an alternative route provided by the remote operator) Which is a subset of the trajectory. It should be noted that some candidate trajectories may be ranked higher than other candidate trajectories or may be associated with higher confidence than other candidate trajectories. According to some examples, a subset of candidate trajectories may be generated by any number of planners, such as a planner, a remote operator computing device (eg, a remote operator can determine and provide an approximate path) It can be derived from the source or can be combined as a subset of candidate trajectories. At 208, route guidance data may be identified at one or more processors. The route guidance data may be configured to aid the remote operator in selecting a trajectory to be guided from one or more of the candidate trajectories. In some instances, the route guidance data indicates a confidence level or probability indicating a certainty that a particular candidate trajectory can reduce or ignore the likelihood that the event may affect the operation of the autonomous vehicle Specify a value. The guided trajectory as a candidate trajectory to be chosen may be input at 210 at the input from the remote operator (eg, the remote operator may select at least one candidate trajectory from a group of differently ranked candidate trajectories, Which can be selected as the guided trajectory). Selection may be made via an operator interface listing several candidate trajectories, for example in order from highest confidence level to lowest confidence level. At 212 the selection of a candidate trajectory as a guided trajectory may be sent to the vehicle which is guided to resolve the condition by causing the vehicle to perform the operation specified by the remote operator Perform orbit. As such, autonomous vehicles can transition from non-canonical operating states.” | Paragraph 54 “The simulator interface controller 1414 is configured to provide an interface between the simulator 1440 and the remote operator computing device 1404. For example, sensor data from a group of autonomous vehicles is applied to reference data updater 1438 via autonomous ("AV") group data 1470, whereby reference data updater 1438 generates an updated map and route data 1439 I think that it is configured to do. In some embodiments, the updated map and route data 1439 may be released beforehand as updates to data in the map data repositories 1420 and 1422 or as updates to data in the route data repository 1424 it can. In this case, such data may include, for example, a lower threshold for requesting remote operator service may be implemented when a map tile containing pre-updated information is used by an autonomous vehicle Beta version "as shown in FIG. Further, the updated map and route data 1439 may be introduced to the simulator 1440 to verify the updated map data. Upon receiving the full release (eg, at the end of the beta test), the previously lowered threshold for requesting remote operator service is canceled. The user interface graphics controller 1410 provides rich graphics to the remote operator 1408 so that a group of autonomous vehicles can be simulated within the simulator 1440 and the simulated autonomous vehicle Can be accessed via the remote operator computing device 1404 as if the groups are real”).
Levinson, however, fails to explicitly disclose obtaining, by the at least one computing device onboard the vehicle, the road or terrain map which has been updated to create a new version of the road or terrain map, wherein the road or terrain map comprises data about physical details of a geographic area in a real world environment; selecting, by the at least one computing device, a portion of the new version of the road or terrain map to be quality tested based on a current location of the vehicle, wherein a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane; generating, by the at least one computing device, a plurality of simulation routes for a simulated vehicle using the selected portion of the new version of the road or terrain map, wherein the simulation routes have different start locations for the simulated vehicle and different end locations for the simulated vehicle; selecting, by the at least one computing device, a simulation route from the plurality of simulation routes based on a result produced by an algorithm seeded with a map identifier, a map portion identifier, and lane identifiers; performing operations, by the at least one computing device, to simulate vehicle operations along the entire selected simulation route in the new version of the road or terrain map during a single simulation scenario, wherein the selected simulation route comprises a start location, an end location and two or more test lanes of interest, the start and end locations both reside outside of the two or more test lanes of interest, and the two or more test lanes of interest are tested in the single simulation scenario; analyzing, by the at least one computing device, results from the simulating to determine whether a quality of the new version of the road or terrain map is validated or invalidated; selecting, by the at least one computing device, a prior version of the road or terrain map based on a result of said analyzing indicating that the quality of the new version of the road or terrain map is invalidated; and controlling, by the at least one computing device, autonomous or semi-autonomous operations of the vehicle using the prior version of the road or terrain map which was selected.
Fok teaches obtaining, by the at least one computing device, a road or terrain map which has been updated to create a new version of the road or terrain map, wherein the road or terrain map comprises data about physical details of a geographic area in a real world environment (See at least Fok FIG. 3 “304”)
generating, by the at least one computing device, a plurality of simulation routes for a simulated vehicle using the selected portion of the new version of the road or terrain map, wherein the simulation routes have different start locations for the simulated vehicle and different end locations for the simulated vehicle (Generating multiple simulation routes: See at least Fok Fig. 3 “308” and Paragraph 47 “test route”; ¶ 1 “validation tests . . . tests may be generated based on a simulated autonomous vehicle traversing the one or more road features” | Paragraph 52).
performing operations, by the at least one computing device, to simulate vehicle operations along the entire selected simulation route in the new version of the road or terrain map during a single simulation scenario, wherein the selected simulation route comprises a start location, an end location and two or more test lanes of interest, the start and end locations both reside outside of the two or more test lanes of interest, and the two or more test lanes of interest are tested in the single simulation scenario (Simulate vehicle traveling on each route: See at least Fok Fig. 3 ”312” and “314” and Paragraphs 48 and 49 “The one or more validation tests may be executed over the different ones of the multiple test route subsections at 314. Executing the one or more validation tests may include simulating an autonomous vehicle to transverse the test route subsections”) (Fok Fig 4 shows starting point 402 and 404 are outside of lanes that the vehicle will travel during simulation: See also at least Paragraph 52).
analyzing, by the at least one computing device, results from the simulating to determine whether a quality of the new version of the road or terrain map is validated or invalidated (Analyzing results to determine validity of map: See at least Fok Fig. 3 “316” and Paragraphs 50-51 i.e., “process 300 may include determining whether the one or more validation tests pass or fail, and outputting the results”).
selecting a version of the map based on said results of said analyzing (See at least Fok FIG. 3).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Levinson to include obtaining, by the at least one computing device, a road or terrain map which has been updated to create a new version of the road or terrain map, wherein the road or terrain map comprises data about physical details of a geographic area in a real world environment; generating, by the at least one computing device, a plurality of simulation routes for a simulated vehicle using the selected portion of the new version of the road or terrain map, wherein the simulation routes have different start locations for the simulated vehicle and different end locations for the simulated vehicle; performing operations, by the at least one computing device, to simulate vehicle operations along the entire selected simulation route in the new version of the road or terrain map during a single simulation scenario, wherein the selected simulation route comprises a start location, an end location and two or more test lanes of interest, the start and end locations both reside outside of the two or more test lanes of interest, and the two or more test lanes of interest are tested in the single simulation scenario; analyzing, by the at least one computing device, results from the simulating to determine whether a quality of the new version of the road or terrain map is validated or invalidated; and selecting a version of the map based on said results of said analyzing, as taught by Fok as disclosed above, in order to ensure an accurate and efficient validation process of a vehicle map (Fok Paragraph 1 “The present disclosure relates generally to validating maps, and in particular, some embodiments relate to automatically generating map validation tests corresponding to multiple test route subsections.”).
Levinson in view of Fok, however, fails to explicitly disclose that the computing device is onboard the vehicle; selecting, by the at least one computing device, a portion of the new version of the road or terrain map to be quality tested based on a current location of the vehicle, wherein a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane, selecting, by the at least one computing device, a simulation route from the plurality of simulation routes based on a result produced by an algorithm seeded with a map identifier, a map portion identifier, and lane identifiers; and controlling, by the at least one computing device, autonomous or semi-autonomous operations of the vehicle using the prior version of the map which was selected.
Tebbens teaches selecting, by the at least one computing device, a simulation route from the plurality of simulation routes based on a result produced by an algorithm seeded with a map identifier, a map portion identifier, and lane identifiers (See at least Tebbens Paragraph 107 “Scenario database 505 stores various driving scenarios. Examples of driving scenarios include any situation or circumstance that a vehicle may encounter in the real-world. An example scenario can include a scenario that is associated with (e.g., involves, concentrates on, and/or the like) an avoidance maneuver at a particular map location performed with one or more agents (e.g., other vehicles, pedestrians) present in the vicinity, in a variety of different road geometries (e.g., near or at junctions and intersections, lane splittings and lane reductions, turns and filtering lanes, etc.). Each scenario can be designed to emphasize certain aspects of a behavior to be tested. Each of the scenarios can define limits of acceptable behavior, determine common anomalies, which include both behavioral patterns of human drivers to be avoided, and unreasonable decisions made by the vehicle. Scenarios include checks to validate the full complexity of potential behaviors in the scenario. FIGS. 6A-6D illustrate example scenarios.” | Paragraph 156 “FIG. 18 illustrates using the rule-based trajectory evaluation system to compare two candidate trajectories and select one of the trajectories based on a number of rulebook violations, in accordance with one or more embodiments. Trajectories 1804 a, 1804 b generated for a particular scenario configuration 1801 are evaluated 1805 for violations of rules in rulebook(s) 1803. In an embodiment, the results of the evaluations (e.g., violation score of the most important violated rule, or a weighted sum of violations) are scores that can be compared to determine which trajectory has the least violation of the rulebook 1803, and the trajectory with the least violation is selected as the best trajectory for the ego vehicle to take for scenario 1803.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Levinson in view of Fok to include selecting, by the at least one computing device, a simulation route from the plurality of simulation routes based on a result produced by an algorithm seeded with a map identifier, a map portion identifier, and lane identifiers, as taught by Tebbens as disclosed above, in order to ensure efficient simulation route selection (Tebbens Paragraph 1 “The description that follows relates generally to tools for validating the behavior of an autonomous vehicle under different driving scenarios”).
Levinson in view of Fok in view of Tebbens, however, fails to explicitly disclose that the computing device is onboard the vehicle; selecting a portion of the new version of the road or terrain map to be quality tested based on a current location of the vehicle, wherein a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane; and controlling, by the at least one computing device, autonomous or semi-autonomous operations of the vehicle using the prior version of the map which was selected.
Hou, however, teaches that the computing device is onboard the vehicle (See at least Hou Paragraph 61 “While FIG. 1B describes certain operations as being performed by the vehicle 120 or the server 130, this is not meant to be limiting. The operations performed by the vehicle 120 and the server 130 as described herein can be performed by either entity.”)
selecting a portion of the new version of the road or terrain map to be quality tested based on a current location of the vehicle (Vehicle location is used to determines area of the map to be validated: See at least Hou FIG. 7 “710” and “712” and Paragraphs 180-181 “At block 710, the telemetry analysis system identifies particular telemetry data of interest. For example, the telemetry data of interest may be identified by vehicle position data, vehicle orientation data, time stamp data, and/or the like. At block 712, the telemetry data of interest may be used to validate the route, to validate the map used to generate the map”).
controlling, by the at least one computing device, autonomous or semi-autonomous operations of the vehicle using the version of the road or terrain map which was selected (Vehicle follows map when map and its route when determined it is validated: See at least Hou Paragraph 154-155 “ The vehicle may also determine that it cannot determine whether or not there is an exception event or the likelihood of an exception event. If the likelihood does not exceed the corresponding threshold, at block 514, the vehicle continues using the current route for navigation” and Fig. 5 “514”).
It would have been obvious to one of ordinary skill in the art to have modified the method of Levinson in view of Fok in view of Tebbens to include that the computing device is onboard the vehicle and selecting a portion of the new version of the road or terrain map to be quality tested based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane, as taught by Hou as disclosed above, such that the map which has been updated to create a new version of the map is obtained by the vehicle’s onboard computing device, and controlling, by the at least one computing device, autonomous or semi-autonomous operations of the vehicle using the version of the map which was selected, as taught by Hou as disclosed above, in order to ensure safe travel of the autonomous vehicle (Hou Paragraph 6 “In response to detecting that the environment is such that it is impossible or disadvantageous to continue using the initial route at a given route node, the corresponding alternative route may be identified and selected”) and because Fok suggests using validated maps for autonomous vehicle control (¶ 22 “vehicles may utilize validated maps to enable autonomous Driving”; ¶45).
Levinson in view of Fok in view of Tebbens in view of Hou fail to explicitly disclose wherein a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane selecting a prior version of the road or terrain map based on a result of said analyzing indicating that the quality of the new version of the road or terrain map is invalidated.
Miwa, however, teaches selecting a prior version of the road or terrain map based on a result of said analyzing indicating that the quality of the new version of the road or terrain map is invalidated (See at least Miwa Col. 11 lines 17-36 “When displaying a map with sections 1 to 4 using updated map data, the updated management data (A′) designates section data (C1, C4) corresponding with sections 1, 4 having non-updated section data and also designates updated section data (C2′, C3′), which has updated section data for sections 2, 3, as having priority over section data (C2, C3) from before the update. Then, in the case of a malfunction occurring with the updated section data, the management data (A) before the update is activated instead of the updated management data (A′), this update management data (A) before the update does not designate the updated section data (C2′, C3′) but designates the section data C1 to C4, with which a map corresponding to sections 1 to 4 is displayed. According to the map update system of embodiments of the present invention, because the update section data before the update also remains in the map data storing unit 32 in the navigation device 3, even if a malfunction occurs in the updated data, a map can be continuously displayed by switching to the data before the update” | Claim 2 “display the navigation map based on the updated section data and the current section data designated both by the updated management data, and display the navigation map based on the current section data designated by the current management data, instead of the updated management data, in a case where the updated section data including an error.”).
It would have been obvious to one of ordinary skill in the art to have modified the method of Levinson in view of Fok in view of Tebbens in view of Hou to include selecting a prior version of the road or terrain map based on a result of said analyzing indicating that the quality of the new version of the road or terrain map is invalidated, as taught by Miwa as disclosed above, such that the vehicle is controlled using the selected prior version of the map, in order to ensure accurate maps are used for autonomous travel (Miwa Paragraph 9 “An aspect relates to enabling continuous and stable display of a map in a navigation device.”).
Levinson in view of Fok in view of Tebbens in view of Hou in view of Miwa fail to explicitly disclose that a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane.
Bonanni teaches that wherein a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane (See at least Bonanni FIGS. 13A-15 and Paragraph 111 “In some embodiments, the disclosed techniques involve modifying or determining a particular route for the AV so that the AV can obtain updated map data by collecting environmental information with sensors on the AV while transporting a user of the AV (e.g., a rider such as, for example, a paying rideshare customer) to their destination. In some embodiments, the disclosed techniques involve determining route planning data for a route of an AV (e.g., including modifying a driving behavior of the AV) so that the AV can collect updated map data for one or more sections of the route while also transporting the user of the AV to a specified destination.” | Paragraph 115 “In the embodiment shown in FIG. 13A, the selected route is determined by choosing edges 1310 that, collectively, minimize the cost (for example, the amount of time) to travel from start point 1302 to end point 1304. In some embodiments, the cost of traveling a particular route—represented in this example as the amount of time to travel the route—is calculated using formula (1)” | Paragraph 116 “As discussed above, the AV can be tasked with obtaining updated map data. In some embodiments, this can be performed while transporting the rider from start point 1302 to end point 1304. Specifically, the route used to transport the rider from start point 1302 to end point 1304 is determined (e.g., by planning module 404) in a manner that selectively incorporates edges 1310 according to the benefit obtained by traversing particular edges (e.g., the opportunity to collect updated map data for an unmapped road or a road that has not been recently surveyed). This permits use of the AV to obtain the updated map data” | Paragraphs 133-134 “FIG. 14 is a flow chart of an example process 1400 (also referred to as a method) for determining a route (e.g., a trajectory) of an autonomous vehicle (e.g., AV 100) in order to update map data used for navigating an autonomous vehicle in accordance with the embodiments discussed above … At 1402, the system (e.g., 120, 300, 400, or a combination thereof) obtains, using a processing circuit (e.g., planning module 404) (e.g., computing processor 146), map data including a starting location (e.g., starting point 1302) and a destination location (e.g., end point 1304) (e.g., a route starting location and a route destination location).”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Levinson in view of Fok in view of Tebbens in view of Hou in view of Miwa to include that wherein a shape and/or size of the selected portion is dynamically selected based on at least one of a time of day, a vehicle destination, a lane length and an estimated time of travel on a lane, as taught by Bonanni as disclosed above, in order to ensure accurate locations for quality testing of maps (Bonanni Paragraph 3 “Because road conditions can change over time, maps used to navigate an autonomous vehicle may need to be updated to accurately convey the current configuration and condition of the roads.”).
Claims 4 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Levinson (JP 2018538647 A) (“Levinson”) (Translation Attached) in view of Fok (US 20210356277 A1) (“Fok”) in view of Tebbens (US 20220187837 A1) (“Tebbens”) in view of Hou (US 20200209002 A1) (“Hou”) in view of Miwa (US 10533859 B2) (“Miwa”) in view of Bonanni (US 20210207968 A1) (“Bonanni”) further in view of Fowe (US 20150312327 A1) (“Fowe”).
With respect to claim 4, and similarly claim 14, Levinson in view of Fok in view of Tebbens in view of Hou in view of Miwa in view of Bonanni teach that the routes comprise a plurality of lanes through which the vehicle is to traverse during the simulating (Vehicle route includes a lane change: See at least Hou Fig. 2 a-b and Paragraph 175)
Levinson in view of Fok in view of Tebbens in view of Hou in view of Miwa in view of Bonanni, however, fail to explicitly disclose that the route comprises a single lane.
Fowe, however, teaches of a route comprising a single lane (Route of a single lane is presented: See at least Fowe Paragraph 6).
It would have been obvious to one of ordinary skill in the art to have modified the method of Levinson in view of Fok in view of Tebbens in view of Hou in view of Miwa in view of Bonanni so that the route through which a vehicle is to traverse during the simulation would be a route comprising a single lane, as taught by Fowe as disclosed above, in order to obtain specific data of map quality representing specific lanes (Fowe Paragraph 1 “The present teachings relate generally to navigation, maps, Advanced Traveler Information Systems (ATIS), Advanced Driver Assistance Systems (ADAS), Highly Assisted Driving (HAD), and the like.”).
Claims 10 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Levinson (JP 2018538647 A) (“Levinson”) (Translation Attached) in view of Fok (US 20210356277 A1) (“Fok”) in view of Tebbens (US 20220187837 A1) (“Tebbens”) in view of Hou (US 20200209002 A1) (“Hou”) in view of Miwa (US 10533859 B2) (“Miwa”) in view of Bonanni (US 20210207968 A1) (“Bonanni”) further in view of Brown (US 20220081004 A1) (“Brown”).
With respect to claim 10, and similarly claim 20, Levinson in view of Fok in view of Tebbens in view of Hou in view of Miwa in view of Bonanni fail to explicitly disclose that that the method is performed responsive to generation of the road or terrain map, generation of autonomous vehicle software, an update to autonomous vehicle software, an object detection by the vehicle while in use.
Brown teaches that that the method is performed responsive to generation of the road or terrain map, generation of autonomous vehicle software, an update to autonomous vehicle software, an object detection by the vehicle while in use (See at least Brown FIG. 5 and Paragraphs 87-90 “In step 514, while navigating around the unknown object 204, the control subsystem 1400 sends a plurality of second messages 402 to the operation server 1500. The plurality of second messages 402 includes sensor data 216 c associated with the unknown object 204. For example, the sensor data 216 c may include a feed of images/videos of the unknown object 204 from a plurality of angles (as the lead AV 1602-1 is navigating around the unknown object 204). Similarly, the sensor data 216 c may include feeds of other types of data, such as LiDAR data, etc., as described in FIG. 4 … In step 518, the operation server 1500 updates the map data 1510, such that the updated map data 1510 reflects the unknown object 204 located at the particular location coordinates occupying the particular lane(s) 202.” | Paragraph118 “The operation server 1500 may also send a re-routing plan 702 to the AV 1602-3 that includes instructions to stop at an intermediate AV launchpad/landing pad 706, if based on traffic data 1524 of the alternative routes to the destination, the driving time using any of the alternative routes is more a threshold driving time (e.g., five hours). The operation server 1500 may determine the safety of each alternative route by executing simulations of autonomous driving in each alternative route (see descriptions of autonomous driving simulations in FIG. 15).”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to have modified the method of Levinson in view of Fok in view of Tebbens in view of Hou in view of Miwa in view of Bonanni to include that that the method is performed responsive to generation of the road or terrain map, generation of autonomous vehicle software, an update to autonomous vehicle software, an object detection by the vehicle while in use, as taught by Brown as disclosed above, in order to ensure accurate real time map quality (Brown Paragraph 1 “The present disclosure relates generally to autonomous vehicles. More particularly, the present disclosure is related to detecting unknown object by a lead Autonomous Vehicle (AV) and updating routing plans for following AVs.”).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to IBRAHIM ABDOALATIF ALSOMAIRY whose telephone number is (571)272-5653. The examiner can normally be reached M-F 7:30-5:30.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Faris Almatrahi can be reached at 313-446-4821. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/IBRAHIM ABDOALATIF ALSOMAIRY/ Examiner, Art Unit 3667 /KENNETH J MALKOWSKI/Primary Examiner, Art Unit 3667