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 .
Claims 1-20 have been examined.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-20 are rejected under 35 U.S.C. 102(a)(2) as being disclosed by Sadeghi et al. USP 11/834,077.
As per claims 1, 9 and 15, Sadeghi discloses an autonomous driving agent for a vehicle, comprising: circuitry coupled to one or more sensors of the vehicle, wherein the circuitry is configured to: receive information about a target agent in an environment of the vehicle from the one or more sensors; predict a set of possible future actions for the target agent within the environment of the vehicle; receive a set of probabilities corresponding to the set of possible future actions (col.2, 19-31; col.4, 44-52; fig’s 3, 6); Sadeghi discloses via col.2, 19-31:
6) The objective of safety is typically given a high priority in the context of motion planning. Uncertainty, which is inherent in many vehicle operating environments, creates several challenges to safe local motion planning. Causes of uncertainty can include, among other things: 1) the unpredictability of dynamic objects such as other vehicles, pedestrians, cyclists, which require probabilistic trajectory predictions; 2) vehicle localization (e.g., determining an accurate position of a vehicle); 3) vehicle controller errors (e.g., failure of a vehicle to accurately follow an intended trajectory); or 4) limitations to the vehicle's field-of-view (FOV) that is available from the sensors of the vehicle that sense a surrounding environment of the vehicle.
convert the set of possible future actions for the target agent to a set of constraints;
determine a desired vehicle trajectory for the vehicle based on compatibility between the desired vehicle trajectory and the set of constraints; and control one or more vehicle systems of the vehicle to achieve the desired vehicle trajectory (col.11, 44-67; col.12, 1-3; col.14, 47-67; col.15, 1-11; col.12, 5-25 and 39-51; fig’s 1, 4). Sadeghi discloses via col.11, 44-67 and col.12, 1-3:
(29) The behavior planner 320 receives the planned route or path from the mission planner 310, including the set of intermediate target positions (if any). The behavior planner 320 also receives the vehicle state output by the state generator 125. The behavior planner 320 generates a behavior decision based on the planned route or path and the vehicle state, in order to control the behavior of the vehicle 100 on a more localized and short-term basis than the mission planner 310. The behavior decision may serve as a target or set of constraints for the motion planner 330. The behavior planner 320 may generate a behavior decision that is in accordance with certain rules or driving preferences. For example, the behavior planner 320 may generate a behavior decision that ensures that the vehicle 100 follows certain behavior rules (e.g., left turns should be made from the left-most lane, vehicle speed should be within a speed limit, vehicle should stop at a stop sign, etc.). Such behavior rules may be based on traffic rules, as well as based on guidance for smooth and efficient driving (e.g., vehicle should take a faster lane if possible). The behavior decision may be output by the behavior planner 320 in a variety of suitable formats. For example, the behavior planner 320 may output the behavior decision in the form of signals (such as a safety signal), scalar values, and/or a cost map (or cost image), among other possibilities. The behavior decision output from the behavior planner 320 may serve as constraints on motion planning, for example.
Figure 1 of Sadeghi discloses:
PNG
media_image1.png
739
861
media_image1.png
Greyscale
As per claim 2, Sadeghi discloses wherein the one or more sensors include a camera (col. 2, 32-52; col. 7, 51-67; col.8, -45; figure 1) as per the discussion above and the rejection of corresponding parts of the claims above incorporated herein and further, Sadeghi discloses via col.2, 32-52:
(7) FOV limitations that result in unobserved regions can create a high degree of uncertainty in detecting objects in a vehicle's surrounding environment. FOV limitations can arise for multiple reasons, including for example blind spots due to limited coverage provided by a vehicle' sensors (such as LiDAR, Radar, and Camera based sensors) as well as occluded regions that are created due to interference by dynamic and static objects that obstruct the vehicle's sensors. These FOV limitations can potentially result in unsafe trajectories for the vehicle.
As per claims 3, 10 and 16, Sadeghi discloses wherein the circuitry is configured to determine the desired trajectory using model predictive control (col.2, 19-31; col.4, 44-52; fig’s 6, 3; col.19, 11-26; col.13, 41-61; fig’s 1, 4) as per the discussion above and the rejection of corresponding parts of the claims above incorporated herein and further, Sadeghi discloses via col. 19, 1-26:
(68) Based on the above premise, with reference again to FIG. 4, as indicated at block 422, risk assessment module 338 is configured to predict a probability of the ego vehicle 100 colliding with another vehicle or a non-vehicle dynamic agent for candidate trajectory T.sub.i. In order to do so, risk assessment module 338 is configured to predict, for each of a plurality of future times t (each time t corresponding to a time step in planning interval [0, T]) a collision probability for the ego vehicle 100 following the candidate trajectory T.sub.i. This probability is based on predicting: (i) whether another vehicle will be located in the same grid cell in vehicle occupancy grid G.sub.v as the ego vehicle 100 at a future time t, and (ii) whether a non-vehicle agent will be located in the same grid cell in non-vehicle agent occupancy grid G.sub.p as the ego vehicle 100 at future time t.
As per claims 4, 11 and 17, Sadeghi discloses wherein using model predictive control includes solving an objective function that promotes comfort and reduces travel time for the vehicle (col.12, 39-51; col.19, 12-26; fig’s 1, 4; col. 24, 31-47; col.2, 4-18; col.12, 5-25 and 39-51; fig’s, 3, 6) as per the discussion above and the rejection of corresponding parts of the claims above incorporated herein and further, Sadeghi discloses via col.12, 39-51:
(33) The trajectory evaluator 334 receives as input information including the current vehicle state, the planned route or path, road network data (e.g., map data), and the candidate trajectories generated by the trajectory generator 332. In some embodiments, the information also includes the predicted future vehicle states. Based on the received information, the trajectory evaluator 334 assigns a set of evaluation values to each candidate trajectory. Among other things, the assigned set of evaluation values may be reflective of whether the candidate trajectory successfully achieves the goal of relatively safe, comfortable and speedy driving (e.g., mobility) within the constraints of the behavior decision, in accordance with various predetermined objectives.
As per claims 5, 12 and 18, Sadeghi discloses wherein the objective function includes a vector comprised of a concatenated position, velocity, acceleration, and jerk for each time step (col.1, 32-48; col.1, 13-36; fig’s 1, 4; col.10, 45-57; col.6, 51-67; col.7, 1-18; fig’s 3, 6) as per the discussion above and the rejection of corresponding parts of the claims above incorporated herein and further, Sadeghi discloses via col.1, 32-48:
(3) The planning system may include multiple planners (which may also be referred to as planning units, planning sub-systems, planning modules, etc.) arranged in a hierarchy. The planning system generally includes: a mission planner, a behavior planner, and a motion planner. The motion planner receives as input a planned behavior for the autonomous vehicle generated by the behavior planner as well as information about the environment and information about the vehicle, performs motion planning to generate a trajectory for the autonomous vehicle, and outputs the trajectory for the autonomous vehicle to follow. In the present disclosure, a trajectory is a sequence, over multiple time steps, of a spatial position for the autonomous vehicle (in a geometrical coordinate system) and other parameters. Other parameters may include vehicle orientation, vehicle velocity, vehicle acceleration, vehicle jerk or any combination thereof.
As per claims 6, 13 and 19, Sadeghi discloses wherein the vector incorporates information from the set of probabilities (fig’s 3, 4; col.3, 30-52; col.19, 1-26; fig’s 1, 6)
as per the discussion above and the rejection of corresponding parts of the claims above incorporated herein and further, Sadeghi discloses via col.3, 30-52:
(13) In various aspects, a method for operating an autonomous vehicle is disclosed that includes: computing a current vehicle state for the autonomous vehicle based on observations by a sensing system, the current vehicle state including environmental data about an environment that the autonomous vehicle interacts with; computing, based on the current vehicle state and a target goal, a plurality of candidate trajectories for a current planning horizon interval; computing respective collision probability scores for the plurality of candidate trajectories based on the current vehicle state, the collision probability score for each candidate trajectory indicating a probability of the autonomous vehicle colliding along the candidate trajectory with an object in the environment during the current planning horizon interval; computing respective information gain scores for the plurality of candidate trajectories based on the current vehicle state, the information gain score for each candidate trajectory indicating an respective information gain for a next planning horizon interval that is subsequent to the current planning horizon interval; and selecting a planned trajectory from the plurality of candidate trajectories based on the respective collision probability scores and respective information gain scores.
As per claim 7, Sadeghi discloses wherein the target agent is another vehicle (col.9, 1-31; col.12, 5-25; col. 10, 45-57; fig’s 3, 1; col.14, 47-67; col.15, 1-11; col.16, 45-67; col.17, 1-18; fig’s 4, 6) as per the discussion above and the rejection of corresponding parts of the claims above incorporated herein and further, Sadeghi discloses via col.9, 20-31:
The perception system 120 may also perform more extensive processing of the data about the vehicle 100 and the data about the environment, for example to generate an Occupancy Grid Map (OGM) and predicted future OGMs, to detect and classify objects of interest (e.g., other vehicles, pedestrians, etc.), to detect position and speed of objects categorized by their class, to detect road lane markings and the position of the centre of lane, etc. Thus, the data output by the perception system 120 may include both analyzed (or estimated) data (e.g., OGMs and object classifications) about the environment as well as simple data about the vehicle 100 (e.g., vehicle speed, vehicle acceleration, etc.).
As per claim 8, Sadeghi discloses wherein the target agent is a pedestrian (col.9, 1-31; col.12, 5-25; col. 10, 45-57; fig’s 3, 1; col.14, 47-67; col.15, 1-11; col.16, 45-67; col.17, 1-18; fig’s 4, 6) as per the discussion above and the rejection of corresponding parts of the claims above incorporated herein and further, Sadeghi discloses via col. 12, 5-25:
(31) The behavior decision is received as input commands to the motion planner 330. For example, the input commands provided to the motion planner 330 (i.e. the behavior decision) may include motion planning constraints. The motion planner 330 should find a trajectory that satisfies the behavior decision, and that navigates the environment in a relatively safe, comfortable, and speedy way. The motion planner 330 should be designed to provide a safe and robust trajectory on both structured and unstructured environments. A structured environment is generally an environment having well-defined drivable and non-drivable areas (e.g., a highway having clear lane markings), and which may have defined driving rules that all vehicles are expected to follow. An unstructured environment is generally an environment in which drivable and non-drivable areas are less defined (or undefined) (e.g., an open field), and which may have fewer or no driving rules for expected vehicle behavior. Regardless of whether the environment is structured or unstructured, the environment may also be highly dynamic (e.g., pedestrians and other vehicles are each moving) and each dynamic obstacle may have different and independent behaviors.
As per claim 14, Sadeghi discloses wherein the processor is configured to convert the set of possible future actions for the target agent to the set of constraints using a spacetime cell planner (col.11, 44-67; col.12, 1-3; col.14, 47-67; col.15, 1-11; col.12, 5-25 and 39-51; fig’s 1, 4) as per the discussion above and the rejection of corresponding parts of the claims above incorporated herein and further, Sadeghi discloses via col.11, 44-67 and col.12, 1-3:
(29) The behavior planner 320 receives the planned route or path from the mission planner 310, including the set of intermediate target positions (if any). The behavior planner 320 also receives the vehicle state output by the state generator 125. The behavior planner 320 generates a behavior decision based on the planned route or path and the vehicle state, in order to control the behavior of the vehicle 100 on a more localized and short-term basis than the mission planner 310. The behavior decision may serve as a target or set of constraints for the motion planner 330. The behavior planner 320 may generate a behavior decision that is in accordance with certain rules or driving preferences. For example, the behavior planner 320 may generate a behavior decision that ensures that the vehicle 100 follows certain behavior rules (e.g., left turns should be made from the left-most lane, vehicle speed should be within a speed limit, vehicle should stop at a stop sign, etc.). Such behavior rules may be based on traffic rules, as well as based on guidance for smooth and efficient driving (e.g., vehicle should take a faster lane if possible). The behavior decision may be output by the behavior planner 320 in a variety of suitable formats. For example, the behavior planner 320 may output the behavior decision in the form of signals (such as a safety signal), scalar values, and/or a cost map (or cost image), among other possibilities. The behavior decision output from the behavior planner 320 may serve as constraints on motion planning, for example.
Sadeghi discloses via figure 3:
PNG
media_image2.png
703
770
media_image2.png
Greyscale
As per claim 20, Sadeghi discloses wherein determining the desired vehicle trajectory includes using a path planner and a speed planner (col.11, 4-21; fig’s 1,4; col.12, 39-51; col.11, 44-67; col.12, 1-3; fig’s 3, 6; abstract) as per the discussion above and the rejection of corresponding parts of the claims above incorporated herein and further, Sadeghi discloses via col. 11, 44-67, col.12, 1-3:
(29) The behavior planner 320 receives the planned route or path from the mission planner 310, including the set of intermediate target positions (if any). The behavior planner 320 also receives the vehicle state output by the state generator 125. The behavior planner 320 generates a behavior decision based on the planned route or path and the vehicle state, in order to control the behavior of the vehicle 100 on a more localized and short-term basis than the mission planner 310. The behavior decision may serve as a target or set of constraints for the motion planner 330. The behavior planner 320 may generate a behavior decision that is in accordance with certain rules or driving preferences. For example, the behavior planner 320 may generate a behavior decision that ensures that the vehicle 100 follows certain behavior rules (e.g., left turns should be made from the left-most lane, vehicle speed should be within a speed limit, vehicle should stop at a stop sign, etc.). Such behavior rules may be based on traffic rules, as well as based on guidance for smooth and efficient driving (e.g., vehicle should take a faster lane if possible). The behavior decision may be output by the behavior planner 320 in a variety of suitable formats. For example, the behavior planner 320 may output the behavior decision in the form of signals (such as a safety signal), scalar values, and/or a cost map (or cost image), among other possibilities. The behavior decision output from the behavior planner 320 may serve as constraints on motion planning, for example.
Claim Rejections - 35 USC § 103
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.
Claims 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sadeghi et al. USP 11/834,077, and further in view of Deng et al. USP 11/377,120.
As per claims 1, 9 and 15, Sadeghi discloses an autonomous driving agent for a vehicle, comprising: circuitry coupled to one or more sensors of the vehicle, wherein the circuitry is configured to: receive information about a target agent in an environment of the vehicle from the one or more sensors; predict a set of possible future actions for the target agent within the environment of the vehicle; receive a set of probabilities corresponding to the set of possible future actions (col.2, 19-31; col.4, 44-52; fig’s 3, 6); Sadeghi discloses via col.2, 19-31:
6) The objective of safety is typically given a high priority in the context of motion planning. Uncertainty, which is inherent in many vehicle operating environments, creates several challenges to safe local motion planning. Causes of uncertainty can include, among other things: 1) the unpredictability of dynamic objects such as other vehicles, pedestrians, cyclists, which require probabilistic trajectory predictions; 2) vehicle localization (e.g., determining an accurate position of a vehicle); 3) vehicle controller errors (e.g., failure of a vehicle to accurately follow an intended trajectory); or 4) limitations to the vehicle's field-of-view (FOV) that is available from the sensors of the vehicle that sense a surrounding environment of the vehicle.
convert the set of possible future actions for the target agent to a set of constraints;
determine a desired vehicle trajectory for the vehicle based on compatibility between the desired vehicle trajectory and the set of constraints; and control one or more vehicle systems of the vehicle to achieve the desired vehicle trajectory (col.11, 44-67; col.12, 1-3; col.14, 47-67; col.15, 1-11; col.12, 5-25 and 39-51; fig’s 1, 4).
Sadeghi discloses all the limitations of the invention, however, arguendo, if Sadeghi is or might be interpreted such that it might not explicitly disclose predicting future actions, then Deng discloses predicting future actions (col.6, 20-36; col.21, 52-65; ab; col.14, 49-62; col.1, 35-67; col.2, 1-37; col.5, 1-40; fig’s 15-19). If this interpretation is taken, then it would have been obvious, before the effective filing date of the claimed invention, to modify Sadeghi to include predicting future actions such as that taught by Deng in order to for the operations to access prediction data including one or more predicted trajectories for the object over a future time interval (Deng, col.2, 19-21).
Deng further discloses via col.6, 20-36:
(28) As part of performing the operations described herein, the vehicle computing system can access, receive, obtain, and/or retrieve data including vehicle data and/or perception data. The vehicle data can include information associated with the state of a vehicle (e.g., a speed, velocity, acceleration, orientation, and/or location of the vehicle) in an environment. Furthermore, the perception data can include location information associated with one or more locations of the vehicle and/or objects around the vehicle; and classification information associated with one or more object classes of one or more objects (e.g. an object (single object) or a plurality of objects) in the environment. The perception data can be based at least in part on one or more sensor outputs from one or more sensors (e.g., one or more cameras, Light Detection and Ranging (LiDAR) devices, sonar devices, and/or radar devices) of the vehicle that are configured to determine the state of the environment.
Deng further discloses via col.5, 1-40:
… include a probability of a potential interaction between the vehicle and the objects in the surrounding environment. For example, the scenario exposure can be used to indicate the risk of potential impediment, interference, contact, or other interaction between the vehicle and objects around the vehicle based on the relative location of the vehicle and the objects. Furthermore, the vehicle computing system can access prediction data (e.g., prediction data from a motion prediction system of the vehicle) that can include predicted trajectories of an object over a future time interval. Expected speed data can be determined based on a plurality of hypothetical speeds of the vehicle and a plurality of hypothetical distances between the vehicle and the object. Further, the expected speed data can include a plurality of expected speeds of the vehicle when the vehicle is a hypothetical distance from the predicted location of the object at some future time.
(24) A combination of the scenario exposure, the prediction data, and the expected speed data can be used to generate a speed profile (or velocity profile) for the vehicle over a distance (e.g., the distance between the vehicle and the object). In some embodiments, the speed profile and/or the velocity profile can be associated with one or more trajectories of an object (e.g., an autonomous vehicle) in an environment. For example, the trajectory associated with the speed profile and/or velocity profile of a vehicle can include a set of speeds and positions along the path that the vehicle can traverse during some future time interval. The speed profile can include a set of vehicle speeds that satisfy a set of threshold criteria which can include a maximum speed at which the vehicle can travel to avoid contacting the object. Further, when contact with the object is unavoidable, the speed profile can minimize the severity of that contact. Unavoidable contact can arise, for example, in scenarios in which objects around the vehicle exhibit atypical, uncommon, unexpected, or erratic movement. Examples of unexpected actions can include another vehicle suddenly moving in front of the autonomous vehicle in the autonomous vehicle's lane (e.g., cutting-off the vehicle).
Deng discloses via figures 15 and 16:
PNG
media_image3.png
960
592
media_image3.png
Greyscale
PNG
media_image4.png
828
576
media_image4.png
Greyscale
Sadeghi discloses via col.11, 44-67 and col.12, 1-3:
(29) The behavior planner 320 receives the planned route or path from the mission planner 310, including the set of intermediate target positions (if any). The behavior planner 320 also receives the vehicle state output by the state generator 125. The behavior planner 320 generates a behavior decision based on the planned route or path and the vehicle state, in order to control the behavior of the vehicle 100 on a more localized and short-term basis than the mission planner 310. The behavior decision may serve as a target or set of constraints for the motion planner 330. The behavior planner 320 may generate a behavior decision that is in accordance with certain rules or driving preferences. For example, the behavior planner 320 may generate a behavior decision that ensures that the vehicle 100 follows certain behavior rules (e.g., left turns should be made from the left-most lane, vehicle speed should be within a speed limit, vehicle should stop at a stop sign, etc.). Such behavior rules may be based on traffic rules, as well as based on guidance for smooth and efficient driving (e.g., vehicle should take a faster lane if possible). The behavior decision may be output by the behavior planner 320 in a variety of suitable formats. For example, the behavior planner 320 may output the behavior decision in the form of signals (such as a safety signal), scalar values, and/or a cost map (or cost image), among other possibilities. The behavior decision output from the behavior planner 320 may serve as constraints on motion planning, for example.
Figure 1 of Sadeghi discloses:
PNG
media_image1.png
739
861
media_image1.png
Greyscale
As per claim 2, Sadeghi discloses wherein the one or more sensors include a camera (col. 2, 32-52; col. 7, 51-67; col.8, -45; figure 1) as per the discussion above and the rejection of corresponding parts of the claims above incorporated herein and further, Sadeghi discloses via col.2, 32-52:
(7) FOV limitations that result in unobserved regions can create a high degree of uncertainty in detecting objects in a vehicle's surrounding environment. FOV limitations can arise for multiple reasons, including for example blind spots due to limited coverage provided by a vehicle' sensors (such as LiDAR, Radar, and Camera based sensors) as well as occluded regions that are created due to interference by dynamic and static objects that obstruct the vehicle's sensors. These FOV limitations can potentially result in unsafe trajectories for the vehicle.
As per claims 3, 10 and 16, Sadeghi discloses wherein the circuitry is configured to determine the desired trajectory using model predictive control (col.2, 19-31; col.4, 44-52; fig’s 6, 3; col.19, 11-26; col.13, 41-61; fig’s 1, 4) as per the discussion above and the rejection of corresponding parts of the claims above incorporated herein and further, Sadeghi discloses via col. 19, 1-26:
(68) Based on the above premise, with reference again to FIG. 4, as indicated at block 422, risk assessment module 338 is configured to predict a probability of the ego vehicle 100 colliding with another vehicle or a non-vehicle dynamic agent for candidate trajectory T.sub.i. In order to do so, risk assessment module 338 is configured to predict, for each of a plurality of future times t (each time t corresponding to a time step in planning interval [0, T]) a collision probability for the ego vehicle 100 following the candidate trajectory T.sub.i. This probability is based on predicting: (i) whether another vehicle will be located in the same grid cell in vehicle occupancy grid G.sub.v as the ego vehicle 100 at a future time t, and (ii) whether a non-vehicle agent will be located in the same grid cell in non-vehicle agent occupancy grid G.sub.p as the ego vehicle 100 at future time t.
As per claims 4, 11 and 17, Sadeghi discloses wherein using model predictive control includes solving an objective function that promotes comfort and reduces travel time for the vehicle (col.12, 39-51; col.19, 12-26; fig’s 1, 4; col. 24, 31-47; col.2, 4-18; col.12, 5-25 and 39-51; fig’s, 3, 6) as per the discussion above and the rejection of corresponding parts of the claims above incorporated herein and further, Sadeghi discloses via col.12, 39-51:
(33) The trajectory evaluator 334 receives as input information including the current vehicle state, the planned route or path, road network data (e.g., map data), and the candidate trajectories generated by the trajectory generator 332. In some embodiments, the information also includes the predicted future vehicle states. Based on the received information, the trajectory evaluator 334 assigns a set of evaluation values to each candidate trajectory. Among other things, the assigned set of evaluation values may be reflective of whether the candidate trajectory successfully achieves the goal of relatively safe, comfortable and speedy driving (e.g., mobility) within the constraints of the behavior decision, in accordance with various predetermined objectives.
As per claims 5, 12 and 18, Sadeghi discloses wherein the objective function includes a vector comprised of a concatenated position, velocity, acceleration, and jerk for each time step (col.1, 32-48; col.1, 13-36; fig’s 1, 4; col.10, 45-57; col.6, 51-67; col.7, 1-18; fig’s 3, 6) as per the discussion above and the rejection of corresponding parts of the claims above incorporated herein and further, Sadeghi discloses via col.1, 32-48:
(3) The planning system may include multiple planners (which may also be referred to as planning units, planning sub-systems, planning modules, etc.) arranged in a hierarchy. The planning system generally includes: a mission planner, a behavior planner, and a motion planner. The motion planner receives as input a planned behavior for the autonomous vehicle generated by the behavior planner as well as information about the environment and information about the vehicle, performs motion planning to generate a trajectory for the autonomous vehicle, and outputs the trajectory for the autonomous vehicle to follow. In the present disclosure, a trajectory is a sequence, over multiple time steps, of a spatial position for the autonomous vehicle (in a geometrical coordinate system) and other parameters. Other parameters may include vehicle orientation, vehicle velocity, vehicle acceleration, vehicle jerk or any combination thereof.
As per claims 6, 13 and 19, Sadeghi discloses wherein the vector incorporates information from the set of probabilities (fig’s 3, 4; col.3, 30-52; col.19, 1-26; fig’s 1, 6)
as per the discussion above and the rejection of corresponding parts of the claims above incorporated herein and further, Sadeghi discloses via col.3, 30-52:
(13) In various aspects, a method for operating an autonomous vehicle is disclosed that includes: computing a current vehicle state for the autonomous vehicle based on observations by a sensing system, the current vehicle state including environmental data about an environment that the autonomous vehicle interacts with; computing, based on the current vehicle state and a target goal, a plurality of candidate trajectories for a current planning horizon interval; computing respective collision probability scores for the plurality of candidate trajectories based on the current vehicle state, the collision probability score for each candidate trajectory indicating a probability of the autonomous vehicle colliding along the candidate trajectory with an object in the environment during the current planning horizon interval; computing respective information gain scores for the plurality of candidate trajectories based on the current vehicle state, the information gain score for each candidate trajectory indicating an respective information gain for a next planning horizon interval that is subsequent to the current planning horizon interval; and selecting a planned trajectory from the plurality of candidate trajectories based on the respective collision probability scores and respective information gain scores.
As per claim 7, Sadeghi discloses wherein the target agent is another vehicle (col.9, 1-31; col.12, 5-25; col. 10, 45-57; fig’s 3, 1; col.14, 47-67; col.15, 1-11; col.16, 45-67; col.17, 1-18; fig’s 4, 6) as per the discussion above and the rejection of corresponding parts of the claims above incorporated herein and further, Sadeghi discloses via col.9, 20-31:
The perception system 120 may also perform more extensive processing of the data about the vehicle 100 and the data about the environment, for example to generate an Occupancy Grid Map (OGM) and predicted future OGMs, to detect and classify objects of interest (e.g., other vehicles, pedestrians, etc.), to detect position and speed of objects categorized by their class, to detect road lane markings and the position of the centre of lane, etc. Thus, the data output by the perception system 120 may include both analyzed (or estimated) data (e.g., OGMs and object classifications) about the environment as well as simple data about the vehicle 100 (e.g., vehicle speed, vehicle acceleration, etc.).
As per claim 8, Sadeghi discloses wherein the target agent is a pedestrian (col.9, 1-31; col.12, 5-25; col. 10, 45-57; fig’s 3, 1; col.14, 47-67; col.15, 1-11; col.16, 45-67; col.17, 1-18; fig’s 4, 6) as per the discussion above and the rejection of corresponding parts of the claims above incorporated herein and further, Sadeghi discloses via col. 12, 5-25:
(31) The behavior decision is received as input commands to the motion planner 330. For example, the input commands provided to the motion planner 330 (i.e. the behavior decision) may include motion planning constraints. The motion planner 330 should find a trajectory that satisfies the behavior decision, and that navigates the environment in a relatively safe, comfortable, and speedy way. The motion planner 330 should be designed to provide a safe and robust trajectory on both structured and unstructured environments. A structured environment is generally an environment having well-defined drivable and non-drivable areas (e.g., a highway having clear lane markings), and which may have defined driving rules that all vehicles are expected to follow. An unstructured environment is generally an environment in which drivable and non-drivable areas are less defined (or undefined) (e.g., an open field), and which may have fewer or no driving rules for expected vehicle behavior. Regardless of whether the environment is structured or unstructured, the environment may also be highly dynamic (e.g., pedestrians and other vehicles are each moving) and each dynamic obstacle may have different and independent behaviors.
As per claim 14, Sadeghi discloses wherein the processor is configured to convert the set of possible future actions for the target agent to the set of constraints using a spacetime cell planner (col.11, 44-67; col.12, 1-3; col.14, 47-67; col.15, 1-11; col.12, 5-25 and 39-51; fig’s 1, 4) as per the discussion above and the rejection of corresponding parts of the claims above incorporated herein and further, Sadeghi discloses via col.11, 44-67 and col.12, 1-3:
(29) The behavior planner 320 receives the planned route or path from the mission planner 310, including the set of intermediate target positions (if any). The behavior planner 320 also receives the vehicle state output by the state generator 125. The behavior planner 320 generates a behavior decision based on the planned route or path and the vehicle state, in order to control the behavior of the vehicle 100 on a more localized and short-term basis than the mission planner 310. The behavior decision may serve as a target or set of constraints for the motion planner 330. The behavior planner 320 may generate a behavior decision that is in accordance with certain rules or driving preferences. For example, the behavior planner 320 may generate a behavior decision that ensures that the vehicle 100 follows certain behavior rules (e.g., left turns should be made from the left-most lane, vehicle speed should be within a speed limit, vehicle should stop at a stop sign, etc.). Such behavior rules may be based on traffic rules, as well as based on guidance for smooth and efficient driving (e.g., vehicle should take a faster lane if possible). The behavior decision may be output by the behavior planner 320 in a variety of suitable formats. For example, the behavior planner 320 may output the behavior decision in the form of signals (such as a safety signal), scalar values, and/or a cost map (or cost image), among other possibilities. The behavior decision output from the behavior planner 320 may serve as constraints on motion planning, for example.
Sadeghi discloses via figure 3:
PNG
media_image2.png
703
770
media_image2.png
Greyscale
As per claim 20, Sadeghi discloses wherein determining the desired vehicle trajectory includes using a path planner and a speed planner (col.11, 4-21; fig’s 1,4; col.12, 39-51; col.11, 44-67; col.12, 1-3; fig’s 3, 6; abstract) as per the discussion above and the rejection of corresponding parts of the claims above incorporated herein and further, Sadeghi discloses via col. 11, 44-67, col.12, 1-3:
(29) The behavior planner 320 receives the planned route or path from the mission planner 310, including the set of intermediate target positions (if any). The behavior planner 320 also receives the vehicle state output by the state generator 125. The behavior planner 320 generates a behavior decision based on the planned route or path and the vehicle state, in order to control the behavior of the vehicle 100 on a more localized and short-term basis than the mission planner 310. The behavior decision may serve as a target or set of constraints for the motion planner 330. The behavior planner 320 may generate a behavior decision that is in accordance with certain rules or driving preferences. For example, the behavior planner 320 may generate a behavior decision that ensures that the vehicle 100 follows certain behavior rules (e.g., left turns should be made from the left-most lane, vehicle speed should be within a speed limit, vehicle should stop at a stop sign, etc.). Such behavior rules may be based on traffic rules, as well as based on guidance for smooth and efficient driving (e.g., vehicle should take a faster lane if possible). The behavior decision may be output by the behavior planner 320 in a variety of suitable formats. For example, the behavior planner 320 may output the behavior decision in the form of signals (such as a safety signal), scalar values, and/or a cost map (or cost image), among other possibilities. The behavior decision output from the behavior planner 320 may serve as constraints on motion planning, for example.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Urtasun et al. (U.S. patent application publication 2021/0200212) discloses generating motion plans for autonomous vehicles. An autonomous vehicle can include a machine-learned motion planning system including one or more machine-learned models configured to generate target trajectories for the autonomous vehicle. The model(s) include a behavioral planning stage configured to receive situational data based at least in part on the one or more outputs of the set of sensors and to generate behavioral planning data based at least in part on the situational data and a unified cost function. The model(s) includes a trajectory planning stage configured to receive the behavioral planning data from the behavioral planning stage and to generate target trajectory data for the autonomous vehicle based at least in part on the behavioral planning data and the unified cost function.
Bagnell et al. (U.S. patent 12/448,001) discloses (a) obtaining context data descriptive of an environment surrounding an autonomous vehicle, the context data based on map data and perception data; (b) generating, by a proposer and based on the context data: (i) a plurality of candidate trajectories, and (ii) a plurality of actor forecasts for a plurality of actors in the environment; (c) generating, by a ranker and based on the context data, the plurality of candidate trajectories, and the plurality of actor forecasts, a ranking of the plurality of candidate trajectories; and (d) controlling a motion of the autonomous vehicle based on a candidate trajectory selected based on the ranking of the plurality of candidate trajectories, wherein the proposer comprises a first machine-learned model and the ranker comprises a second machine-learned model, and wherein the first machine-learned model and the second machine-learned model use a common backbone architecture.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BEHRANG BADII whose telephone number is (571)272-6879. The examiner can normally be reached Monday-Friday.
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, Hunter Lonsberry can be reached at 571-272-7298. 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.
/Behrang Badii/
Primary Examiner
Art Unit 3665
Prosecution Insights