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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on June 18, 2026, has been entered.
Status of Claims
This Office action is in response to the amendments filed on June 18, 2026. Claims 1-25 are currently pending, with Claim 1 being amended.
Response to Amendments
In response to Applicant’s amendments, filed June 18, 2026, the Examiner withdraws the previous 35 U.S.C. 102 and 103 rejections.
Response to Arguments
Applicant’s arguments, filed June 18, 2026, with respect to the rejections of Claims 1-25 under Anderson, in view of Afrouzi, have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new grounds of rejection is made in view of Dydek, in view of Zhang, Anderson, and Afrouzi.
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 (i.e., changing from AIA to pre-AIA ) 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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-9 and 23 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent No. 11,561,553 B1, to Dydek, et al (hereinafter referred to as Dydek; newly of record), in view of WIPO Patent Publication No. 2019/018315 A1, to Zhang, et al (hereinafter referred to as Zhang; newly of record).
As per Claim 1, Dydek discloses the features of vehicle localization system (e.g. Col. 3 lines 24-35; a localization system for robots is provided), comprising:
a robotic vehicle (e.g. Col. 3 line 66- Col. 4 line 8; where a robot uses SLAM algorithms to move in the environment) configured to
navigate within an environment based, at least in part, on a predetermined environmental map (e.g. Col. 5 lines 21-31; Col. 8 lines 38-60; where the robot can use the SLAM processing to construct maps and navigate the environment; and the robot can have prior knowledge of the environment);
a first exteroceptive sensor, the first exteroceptive sensor coupled to the robotic vehicle and configured to produce a first data stream (e.g. Col. 4 lines 26-34 and lines 43-61; Col. 9 lines 29-38; where a first module and second module can be configured on the same device or robot for the SLAM operation; and where the first module is of a first type configured on the system, which gathers first simultaneous localization data; and where the sensors can be exteroceptive; where the device can be a robot);
a second exteroceptive sensor, the second exteroceptive sensor coupled to the robotic vehicle and configured to produce a second data stream (e.g. Col. 4 lines 26-34 and lines 43-61; Col. 9 lines 29-38; where a first module and second module can be configured on the same device or robot for the SLAM operation; and where the second module is of a second type configured on the system, which gathers second simultaneous localization data; and where the sensors can be exteroceptive); and
a processor (e.g. Col. 15 line 62- Col. 16 line 16; where the system can include a processor) configured to:
localize the robotic vehicle within the environment using a first modality based on the first data stream to produce a first localization estimate of the robotic vehicle and a second modality based on the second data stream to produce a second localization estimate of the robotic vehicle (e.g. Col. 4 lines 43-61; where the system includes gathering, via a first module of a first type configured on the device (the robot), first simultaneous localization and mapping data, gathering, via a second module of a second type configured on the device (the robot), second simultaneous localization and mapping data),
the first modality and the second modality running in parallel (e.g. Col. 4 lines 43-61; Col. 6 lines 43-50; where the system generates a first map and a second map based on the first and second SLAM processing; and where the system can generate one or more maps in a mapping phase); and
selectively disregard and/or disable one of the first modality or the second modality (e.g. Col. 6 lines 43-50; where the system may determine what types of sensor modules are operational and then select the matching map for localization) and continue to
localize the robotic vehicle within the environment using the localization estimate produced by the other of the first modality or the second modality (e.g. Col. 6 lines 43-50; where system can generate one or more maps in a mapping phase, where a device can be loaded with both maps (or more maps) and then choose which map to use based on a parameter or data associated with the capabilities of the localization components on the device, and the system might determine what types of sensor modules are operational and then select the matching map for localization).
Zhang more explicitly teaches the features of selectively disregard and/or disable one of the first modality or the second modality and continue to localize the robotic vehicle within the environment using the localization estimate produced by the other of the first modality or the second modality.
Zhang, in a similar field of endeavor, teaches a method for aligning map data for a vehicle, where the system may be configured to handle sensor degradation, such as if a camera is non-functional or if the laser is non-functional, the corresponding module may be bypassed and the rest of the system may be staggered to function reliably to perform localization (e.g. Paragraphs [0063], [0067]-[0068], [00130]-[00131], [0278]).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to modify the multi-modal localization method of Dydek, with the feature of selectively disregarding sensors in the system of Zhang, in order to provide reliable sensing functions in various environments (see at least Paragraphs [0063], [0067] of Zhang).
As per Claim 2, Dydek, in view of Zhang, teaches the features of Claim 1, and Dydek further discloses the features of wherein the vehicle is a ground vehicle (e.g. Col. 4 lines 6-8; Col. 7 lines 16-30; where the robot can have wheels for navigating the environment).
As per Claim 3, Dydek, in view of Zhang, teaches the features of Claim 1, and Dydek further discloses the features of wherein the first exteroceptive sensor comprises one or more cameras (e.g. Col. 9 lines 35-37; Col. 15 lines 42-51; where the exteroceptive sensors includes cameras).
As per Claim 4, Dydek, in view of Zhang, teaches the features of Claim 1, and Dydek further discloses the features of wherein the second exteroceptive sensor comprises a LiDAR (e.g. Col. 9 lines 35-37; Col. 15 lines 42-51; where the exteroceptive sensors include radars and lasers; where the module can include LiDAR).
As per Claim 5, Dydek, in view of Zhang, teaches the features of Claim 1, and Dydek further discloses the features of further comprising:
a first proprioceptive sensor, the first proprioceptive sensor being coupled to the vehicle and being configured to produce a third data stream (e.g. Col. 7 lines 16-38; where the system uses wheel odometry to measure the robot’s current location with respect to a global reference coordinate system; or the system acquires position estimates from inertial navigation), the processor being configured to
localize the robotic vehicle using a third modality based on the third data stream in combination with the first modality or the second modality (e.g. Col. 9 lines 29-48; where the interoceptive and exteroceptive sensors can be used together to compensate for errors like odometry drift).
As per Claim 6, Dydek, in view of Zhang, teaches the features of Claim 1, and Dydek further discloses the features of wherein the processor is further configured to localize the vehicle without adding infrastructure to the environment (e.g. Col. 9 lines 11-17; Col. 10 lines 23-26; Col. 16 lines 60-67; where the robot can operate in the absence of purpose-specification localization infrastructure; and where the first and second sensors are located on the robot to generate SLAM data).
As per Claim 7, Dydek, in view of Zhang, teaches the features of Claim 1, and Zhang further teaches the features of wherein the processor is further configured to selectively disregard and/or disable the first localization modality or the second localization modality in real-time in response to a change in an operational environment as compared to the predetermined environmental map.
Zhang, in a similar field of endeavor, teaches a method for aligning map data for a vehicle, where the system may be configured to handle sensor degradation, such as if a camera is non-functional or if the laser is non-functional, the corresponding module may be bypassed and the rest of the system may be staggered to function reliably; and where the mapping system may enable real-time SLAM functions and provide real-time performance by integrating the computational module (e.g. Paragraphs [0064], [0067]-[0068], [00232]).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to modify the multi-modal localization method of Dydek, with the feature of determining real-time sensor data in the system of Zhang, in order to provide reliable sensing functions in various environments (see at least Paragraphs [0063], [0067] of Zhang).
As per Claim 8, Dydek, in view of Zhang, teaches the features of Claim 1, and Zhang further teaches the features of wherein the processor is further configured to disregard and/or disable the first or second localization modality in response to an absence of visual features in the operational environment.
Zhang, in a similar field of endeavor, teaches a method for aligning map data for a vehicle, where the system may be configured to handle sensor degradation, such as if a camera is non-functional or if the laser is non-functional, the corresponding module may be bypassed and the rest of the system may be staggered to function reliably; where the mapping system may operate in dark, texture-less and structure-less environments, and if the camera is non-functional (e.g., due to darkness, dramatic lighting changes, or loss of visual features tracking) the corresponding module may be bypassed (e.g. Paragraphs [0063], [0067]-[0068], [00124]).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to modify the multi-modal localization method of Dydek, with the feature of determining a presence or absence of visual features in the system of Zhang, in order to provide reliable sensing functions in various environments (see at least Paragraphs [0063], [0067] of Zhang).
As per Claim 9, Dydek, in view of Zhang, teaches the features of Claim 1, and Zhang further teaches the features of wherein the processor is further configured to disregard and/or disable the first or second localization modality in response to an absence of geometric features.
Zhang, in a similar field of endeavor, teaches a method for aligning map data for a vehicle, where when the system determines that the features may not have laser range coverage or cannot be triangulated due to the fact that they are not necessarily tracked lone enough or located in the direction of camera motion, the system can associate depth information to visual features, laser points, or triangulation, which may be used alone or in combination to build the registered point cloud, and if there is some degeneracy in a specific direction in the state space then the solution in that direction can be discarded (e.g. Paragraphs [0096]).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to modify the multi-modal localization method of Dydek, with the feature of determining the presence or absence of geometric features in the system of Zhang, in order to provide reliable sensing functions in various environments (see at least Paragraphs [0063], [0067] of Zhang).
As per Claim 23, Dydek, in view of Zhang, teaches the features of Claim 1, and Zhang further teaches the features of wherein the processor is further configured to prioritize one of the first or the second localization modality to localize the robotic vehicle based on one or more factors related to time, space, and/or robotic vehicle action.
Zhang, in a similar field of endeavor, teaches a method for aligning map data for a vehicle, where if visual features are insufficiently available, the system bypasses the visual-inertial odometry module, and the laser feedback compensates for the camera feedback when the correcting velocity drift and biases of the IMU, indicating that the camera feedback has a higher priority when the camera data is not degraded (e.g. Paragraphs [00130], [00132]).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to modify the multi-modal localization method of Dydek, with the feature of determining prioritizing a sensor modality in the system of Zhang, in order to provide reliable sensing functions in various environments (see at least Paragraphs [0063], [0067] of Zhang).
Claims 10, 22, and 24-25 are rejected under 35 U.S.C. 103 as being unpatentable over Dydek, in view of Zhang, as applied to Claim 1 above, and further in view of U.S. Patent Publication No. 2010/0063651 A1, to Anderson (hereinafter referred to Anderson; previously of record).
As per Claim 10, Dydek, in view of Zhang, teaches the features of Claim 1, but the combination of Dydek, in view of Zhang, fails to teach every feature of wherein the processor is further configured selectively disregard and/or disable the first or second localization modality to support vehicle navigation both on and off a pre-trained path.
However, Anderson, in a similar field of endeavor, teaches a method for high-integrity machine localization, where the learned knowledge base contains knowledge learned as the vehicle spends time in a specific work area, and the system may reference the knowledge base to select which sensors for use in planning paths; and where the system accesses map data and the a priori knowledge base for path mapping, and determines if deviation from the path is necessary due to an obstacle (i.e. off a planned path), and the system determines the detection range for sensors offering good visibility of terrain in the path of the vehicle, and when the vehicle experiences diminished detection range, the system selects which sensors to activate (e.g. Paragraphs [0034], [0039], [0042], [0078]).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to further modify the multi-modal localization method of Dydek, in view of Zhang, with the feature of supporting navigation on and off a pre-trained path in the system of Anderson, in order to facilitate early recognition and avoidance of obstacles (see at least Paragraph [0027] of Anderson).
As per Claim 22, Dydek, in view of Zhang, teaches the features of Claim 1, but the combination of Dydek, in view of Zhang, fails to teach every feature of wherein the processor is further configured to perform context-aware modality switching.
However, Anderson, in a similar field of endeavor, teaches a method for high-integrity machine localization, where the system identifies the operating conditions in the environment through sensor data received form a sensor system, and determines if the sensor data does not correspond to the preset operating conditions in the sensor table, the system selects the sensors to activate; and where the system may determine which sensors to activate based on a condition of rain, snow, fog, and frost which may limit the vision or range of certain sensors (e.g. Paragraphs [0062], [0069], [0072], [0074], [0076]).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to further modify the multi-modal localization method of Dydek, in view of Zhang, with the feature of switching modalities based on the context in the system of Anderson, in order to obtain a different perspective of the environment when a sensor is activated (see at least Paragraph [0066] of Anderson).
As per Claim 24, Dydek, in view of Zhang, teaches the features of Claim 1, and but the combination of Dydek, in view of Zhang, fails to teach every feature of wherein the processor is further configured to prioritize one of the first or the second localization modality to localize the robotic vehicle based on pre-trained explicit annotations.
However, Anderson, in a similar field of endeavor, teaches a method for high-integrity machine localization, where the sensor system (500) may include redundancy sensors that may be used to compensate for the loss and/or inability of another sensor to maintain the needed information to control the vehicle, and the sensor may be selected such that one or more of the sensors is always capable of sensing information needed to operate the vehicle and the sensors may be used for localization based on the sensor that is activated; and where the learned knowledge base contains information about the operating environment, including streets, tree locations, etc., which may be used to plan actions, and the information can be used to classify and assign attributes to the identified objects in the environment, such as classifying an item as a “telephone pole” (e.g. Paragraphs [0051]-[0052], [0064], [0068], [0071]-[0072]).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to further modify the multi-modal localization method of Dydek, in view of Zhang, with the feature of using a sensor based on pre-trained annotations in the system of Anderson, in order to ensure high integrity perception when the dynamic conditions change (see at least Paragraph [0040] of Anderson).
As per Claim 25, Dydek, in view of Zhang, teaches the features of Claim 1, but the combination of Dydek, in view of Zhang, fails to teach every feature of wherein the processor is further configured to prioritize the first or the second localization modality to localize the robotic vehicle based on one or more specified time(s), time(s) of day, and/or locations.
However, Anderson, in a similar field of endeavor, teaches a method for high-integrity machine localization, where the sensor system (500) may include redundancy sensors that may be used to compensate for the loss and/or inability of another sensor to obtain the needed information to control the vehicle; and where sensor may be selected such that one or the sensors is always capable of sensing information needed to operate the vehicle); and where the knowledge base contains information about the operating environment for specific times of the year and based on the amount of time a vehicle spends in a specific work area; and where the system detects a dynamic condition that impacts the movement of the vehicle, such as moving the vehicle to a new location, detection of an obstacle, etc., or a detection of changes of season, sun, clouds, artificial illumination, full moon light, rain snow, etc., and the vehicle uses the information collected by the sensor system to identifying a location of a vehicle and conduct localization by retrieving a map associated with the location of the vehicle (e.g. Paragraphs [0040], [0051]-[0052], [0068], [0070], [0078]).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to further modify the multi-modal localization method of Dydek, in view of Zhang, with the feature of prioritizing modalities based on specified times in the system of Anderson, in order to ensure high integrity perception when the dynamic conditions change (see at least Paragraph [0040] of Anderson).
Claim 11-21 is rejected under 35 U.S.C. 103 as being unpatentable over Dydek, in view of Zhang, as applied to Claim 1 above, and further in view of U.S. Patent No. 11,274,929 B1, to Afrouzi, et al (hereinafter referred to Afrouzi; previously of record).
As per Claim 11, Dydek, in view of Zhang, teaches the features of Claim 1, but the combination of Dydek, in view of Zhang, fails to teach every feature of wherein the processor is further configured to generate a first map layer associated with the first data stream and to register a localization of the robotic vehicle to the first map layer based on the first data stream.
However, Afrouzi, in a similar field of endeavor, teaches a method for constructing a map for a robot, where layered maps may be used and generated by the processor, and a layer of a map may be a map generated based solely on the observations of a particular sensor type, and a layer of a map may construct the map from stored values in memory (e.g. Col. 53 line 66- Col. 54 line 22).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to further modify the multi-modal localization method of Dydek, in view of Zhang, with the feature of generating map layers in the system of Afrouzi, in order assist in avoiding blind spots (see at least Col. 53 lines 65-67 of Afrouzi).
As per Claim 12, Dydek, in view of Zhang and Afrouzi, teaches the features of Claim 11, and Afrouzi further teaches the features of wherein the first map layer is pre-computed offline.
Afrouzi teaches a method for constructing a map for a robot, where layered maps may be used and generated by the processor, and a layer of a map may be a map generated based solely on the observations of a particular sensor type, and a layer of a map may construct the map from stored values in memory, based on previous observations and evaluations of an environment while offline (e.g. Col. 53 line 66- Col. 54 line 22; Col. 99 lines 5-7).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to further modify the multi-modal localization method of Dydek, in view of Zhang, with the feature of pre-computing map layers in the system of Afrouzi, in order to reduce the footprint of the map and reduce computational costs (see at least Col. 84 lines 55-57 of Afrouzi).
As per Claim 13, Dydek, in view of Zhang and Afrouzi, teaches the features of Claim 11, and Afrouzi further teaches the features of wherein the first map layer is generated during a training mode.
Afrouzi teaches a method for constructing a map while performing work, where a training period of the robot may include the robot inspecting the environment various times with the same sensor, and the training may occur over one or multiple sessions, to generate a first map layer (e.g. Col. 55 lines 13-59).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to further modify the multi-modal localization method of Dydek, in view of Zhang, with the feature of generating a map during a training period in the system of Afrouzi, in order to validate the data of the first map (see at Col. 55 lines 13-17 of Afrouzi).
As per Claim 14, Dydek, in view of Zhang and Afrouzi, teaches the features of Claim 11, and Afrouzi further teaches the features of wherein the processor is further configured to generate a second map layer associated with the second data stream and to register a localization of the robotic vehicle to the second map layer based on the second data stream.
Afrouzi teaches a method for constructing a map for a robot, where layered maps may be used and generated by the processor, and a layer of a map may be a map generated based solely on the observations of a particular sensor type, where the map may include three layers and each layer may be a map generated solely on the observations of a particular sensor type (e.g. Col. 53 line 66- Col. 54 line 22).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to further modify the multi-modal localization method of Dydek, in view of Zhang, with the feature of generating map layers in the system of Afrouzi, in order to validate the data of the first map (see at Col. 55 lines 13-17 of Afrouzi).
As per Claim 15, Dydek, in view of Zhang and Afrouzi, teaches the features of Claim 11, and Afrouzi further teaches the features of wherein the second map layer is computed in real time.
Afrouzi teaches a method for constructing a map for a robot, where the map may be generated in real-time (e.g. Col. 59 lines 19-20; Col. 54 lines 12-22; Col. 95 line 60- Col. 96 line 2).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to further modify the multi-modal localization method of Dydek, in view of Zhang, with the feature of generating a map in real-time in the system of Afrouzi, with the feature of determining map data in real-time in the system of Afrouzi, in order to determine and implement a more efficient path as the robot is traveling (see at Col. 96 lines 17-24, Col. 111 lines 27-33 of Afrouzi).
As per Claim 16, Dydek, in view of Zhang and Afrouzi, teaches the features of Claim 14, and Afrouzi further teaches the features of wherein the second map layer is generated during robotic vehicle operation.
Afrouzi teaches a method for constructing a map for a robot, where the robot maps an area while performing work; and where the processor of the robot may construct a map of the environment using data from one or more sensors while the robot performs work within recognized areas of the environment (e.g. Col. 21 lines 33-34; Col. 22 lines 60-62).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to further modify the multi-modal localization method of Dydek, in view of Zhang, with the feature of generating a map during vehicle operation in the system of Afrouzi, in order to determine and implement a more efficient path as the robot is traveling (see at Col. 96 lines 17-24, Col. 111 lines 27-33 of Afrouzi).
As per Claim 17, Dydek, in view of Zhang and Afrouzi, teaches the features of Claim 14, and Afrouzi further teaches the features of wherein the second map layer is ephemeral.
Afrouzi teaches a method for constructing a map for a robot, where the map is stored in memory for future use, and the map may be in temporary memory such that a stored map is only available during an operational session; and the robot may construct a temporary partial map of its surroundings as it moves in the environment (e.g. Col. 33 lines 27-42; Col. 55 lines 7-18).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to further modify the multi-modal localization method of Dydek, in view of Zhang, with the feature of having a map layer be ephemeral in the system of Afrouzi, in order to determine remove a dynamic obstacle from the map or memory after some time (see at Col. 103 lines 42-46, Col. 177 lines 7-19 of Afrouzi).
As per Claim 18, Dydek, in view of Zhang and Afrouzi, teaches the features of Claim 14, and Afrouzi further teaches the features of wherein the processor is configured to dynamically update the second map layer.
Afrouzi teaches a method for constructing a map for a robot, where the robot may determine dynamic map information for the environment, changing and updating the map in real-time as new data is sensed; and the processor may create a dynamic and constantly evolving map (e.g. Col. 35 lines 54-57; Col. 95 lines 28-38).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to further modify the multi-modal localization method of Dydek, in view of Zhang, with the feature of dynamically updating the map in the system of Afrouzi, in order to determine and implement a more efficient path as the robot is traveling (see at Col. 96 lines 17-24, Col. 111 lines 27-33 of Afrouzi).
As per Claim 19, Dydek, in view of Zhang and Afrouzi, teaches the features of Claim 14, and Afrouzi further teaches the features of wherein the processor is configured to spatially register the second map layer to the first map layer.
Afrouzi teaches a method for constructing a map for a robot, where the processor may generate a map based on depths to a portion of objects within the environment, and as the robot moves from a first position to a second position within the environment and collects more data, the spatial model may be updated to more accurately represent the environment; and where the movement of the robot may be measured and tracked by an encoder, IMU, and/or optical tracking sensor and images captured by an image sensor may be combined together to form a spatial representation based on overlap of data and/or measured movement of the robot (e.g. Col. 52 lines 58-63; Col. 64 lines 7-16).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to further modify the multi-modal localization method of Dydek, in view of Zhang, with the feature of spatially registering a map in the system of Afrouzi, in order to validate the map data (see at Col. 55 lines 13-28 of Afrouzi).
As per Claim 20, Dydek, in view of Zhang and Afrouzi, teaches the features of Claim 14, and Afrouzi further teaches the features of wherein the processor is further configured to spatially register the first map layer and the second map layer to a common coordinate frame.
Afrouzi teaches a method for constructing a map while performing work, where the processor can transform the vectors measured relative to different coordinate systems and describing the environment to be transformed into a single coordinate system (e.g. Col. 34 lines 59-63).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to further modify the multi-modal localization method of Dydek, in view of Zhang, with the feature of utilizing a common coordinate system in the system of Afrouzi, in order to validate and establish a more accurate map (see at Col. 21 lines 6-10, Col. 35 lines 42-49 of Afrouzi).
As per Claim 21, Dydek, in view of Zhang and Afrouzi, teaches the features of Claim 20, and Afrouzi further teaches the features of wherein the processor is configured to spatially register semantic annotations to the first map layer.
Afrouzi teaches a method for constructing a map while performing work, where the robot may assign unique tags, such as a number or a label to a subarea (such as a human-readable name of a room, like “kitchen”), and may assign instructions to perform a task associated with the label; and where the classification algorithm may be pre-trained or pre-labeled, and associated with maps indicating the position of walls, furniture, doors, and the like in a room, and identification of rooms and path segments (e.g. Col. 58 lines 47-60).
It would have been obvious to a person of ordinary skill in the art on or before the effective filing date of the Applicant's invention, with a reasonable expectation for success, to further modify the multi-modal localization method of Dydek, in view of Zhang, with the feature of utilizing a common coordinate system in the system of Afrouzi, with the feature of spatially registering a map in the system of Afrouzi, in order to validate the map data (see at Col. 55 lines 13-28 of Afrouzi).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Akbarzadeh, et al (U.S. 12,607,480 B2), which teaches a method for map creation and localization for autonomous driving applications.
Czarnian, et al (U.S. 12,145,619 B2), which teaches a method for self-localization of a vehicle with selective sensor activation.
Dalal, et al (U.S. 12,433,463 B2), which teaches a method for mapping a localizing a robot.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MERRITT LEVY whose telephone number is (571)270-5595. The examiner can normally be reached Mon-Fri 0630-1600.
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, Abby Flynn can be reached at (571) 272-9855. 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.
/MERRITT LEVY/Examiner, Art Unit 3663
Prosecution Insights