Adaptive autonomous vehicle planner logic

• US 9,910,441 B2
• Filed: 11/04/2015
• Issued: 03/06/2018
• Est. Priority Date: 11/04/2015
• Status: Active Grant

• Current Assignee: Zoox Inc. (Amazon.com, Inc.)
• Original Assignee: Zoox Inc. (Amazon.com, Inc.)
• Inventors: Levinson, Jesse Sol, Sibley, Gabriel Thurston, Kentley-Klay, Timothy David
• Primary Examiner(s): LANG, MICHAEL DEAN
• Application Number:
  US14/756,992
• Publication Number:
  US 20170123429A1
• Time in Patent Office: 853 Days
• CPC Class Codes: B60W 2050/0064 using a remote, e.g. cordless, transmitter or receiver unit, e.g. remote keypad or mobile phone
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2420/408 Radar; Laser, e.g. lidar
• CPC Class Codes: B60W 2420/54 Audio sensitive means, e.g. ultrasound
• CPC Class Codes: B60W 2554/20 Static objects
• CPC Class Codes: B60W 2554/4026 Cycles
• CPC Class Codes: B60W 2554/4029 Pedestrians
• CPC Class Codes: B60W 2554/406 Traffic density
• CPC Class Codes: B60W 2555/20 Ambient conditions, e.g. wind or rain
• CPC Class Codes: B60W 50/00 Details of control systems for road vehicle drive control not related to the control of a particular sub-unit , e.g. process diagnostic or vehicle driver interfaces
• CPC Class Codes: B60W 60/0011 involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles
• CPC Class Codes: B60W 60/0027 using trajectory prediction for other traffic participants
• CPC Class Codes: G01C 21/34 Route searching; Route guidance
• CPC Class Codes: G01C 21/3407 specially adapted for specific applications
• CPC Class Codes: G01S 13/865 Combination of radar systems with lidar systems
• CPC Class Codes: G01S 13/867 Combination of radar systems with cameras
• CPC Class Codes: G01S 13/87 Combinations of radar systems, e.g. primary radar and secondary radar
• CPC Class Codes: G01S 17/87 Combinations of systems using electromagnetic waves other than radio waves
• CPC Class Codes: G01S 17/931 of land vehicles
• CPC Class Codes: G01S 2013/9316 combined with communication equipment with other vehicles or with base stations
• CPC Class Codes: G01S 2013/9322 : using additional data, e.g. driver condition, road state or weather data
• CPC Class Codes: G01S 7/4972 : Alignment of sensor
• CPC Class Codes: G05D 1/0212 : with means for defining a desired trajectory involving a plurality of land vehicles G05D1/0287
• CPC Class Codes: G05D 1/0214 : in accordance with safety or protection criteria, e.g. avoiding hazardous areas monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13
• CPC Class Codes: G05D 1/0255 : using acoustic signals, e.g. ultra-sonic singals sonar systems designed for anti-collision purposes G01S15/93
• CPC Class Codes: G05D 1/0257 : using a radar radar systems designed for anti-collision purposes between land vehicles or between land vehicle and fixed obstacles G01S13/931
• CPC Class Codes: G05D 1/0297 : by controlling means in a control room

Abstract

Various embodiments relate generally to autonomous vehicles and associated mechanical, electrical and electronic hardware, computer software and systems, and wired and wireless network communications to provide an autonomous vehicle fleet as a service. More specifically, systems, devices, and methods are configured to generate trajectories to influence navigation of autonomous vehicles. In particular, a method may include receiving path data to navigate from a first geographic location to a second geographic location, generating data representing a trajectory with which to control motion of the autonomous vehicle based on the path data, generating data representing a contingent trajectory, monitoring generation of the trajectory, and implementing the contingent trajectory subsequent to an absence of the trajectory.

Claims

1. A method comprising:

receiving path data with which to guide motion of an autonomous vehicle from a first geographic location to a second geographic location;

receiving perception data from a perception engine, the perception data comprising static map data, current object state data, and predicted object state data;

receiving, from a localizer, local pose data of the autonomous vehicle;

substantially simultaneously generating at least a plurality of trajectories and a plurality of contingent trajectories based, at least in part, on the path data, the local pose data, the static map data, the current object state data, and the predicted object state data;

selecting a trajectory from the plurality of trajectories to use to control one or more vehicle components;

selecting a contingent trajectory from the plurality of contingent trajectories to use to control the one or more vehicle components;

controlling the one or more vehicle components of the autonomous vehicle according to the trajectory to direct motion of the autonomous vehicle along the trajectory;

monitoring generation of the trajectory;

detecting cessation of the generation of the trajectory; and

responsive to detecting the cessation of the generation of the trajectory, controlling the one or more vehicle components according to the contingent trajectory.

2. The method of claim 1, further comprising generating one or more commands to control motion of the autonomous vehicle, wherein controlling motion of the autonomous vehicle according to the contingent trajectory includes causing the autonomous vehicle to execute the commands to perform a safe-stop maneuver to a geolocation based on the contingent trajectory.

3. The method of claim 1, further comprising:

receiving a subset of sensor data; and

responsive to receiving the subset of sensor data, controlling the one or more vehicle components according to the contingent trajectory,

wherein one or more of the static map data, the current object state data, the local pose data, or the predicted object state data is based, at least in part, on the subset of sensor data, and

the subset of sensor data comprises one or more of lidar data, radar data, or sonar data.

4. The method of claim 3, wherein:

generating the plurality of trajectories includes calculating the plurality of trajectories based at least in part on the path data, the local pose data, the static map data, the current object state data, and the predicted object state data; and

generating the plurality of contingent trajectories includes calculating the plurality of contingent trajectories based at least in part on the path data, the local pose data, the static map data, the current object state data, and the predicted object state data.

5. The method of claim 1, wherein generating the at least the plurality of trajectories and the plurality of contingent trajectories further comprises:

iteratively generating a group of trajectories at multiple autonomous vehicle controllers, the group of trajectories including the trajectory; and

iteratively generating a group of contingent trajectories at the multiple autonomous vehicle controllers, the group of contingent trajectories including the contingent trajectory.

6. The method of claim 1, wherein controlling the one or more vehicle components according to the contingent trajectory comprises:

transmitting control signals to the one or more vehicle components to effect a safe-stop of the autonomous vehicle, wherein

the control signals are determined based on a receding horizon.

7. The method of claim 1, the method further comprising:

determining a confidence level, the confidence level indicative of an ability of the autonomous vehicle to traverse a path;

transmitting, based on the confidence level, a message to a teleoperator; and

receiving a command from a teleoperator to control the autonomous vehicle according to the contingent trajectory;

wherein the perception data comprises one or more dynamic objects and one or more static objects.

8. The method of claim 1, further comprising:

receiving sensor data as probabilistic distributions;

forming the perception data associated with an external object based on the probabilistic distributions; and

inferring a characteristic value associated with the external object to form an inferred characteristic value,

wherein generating the at least the plurality of trajectories and the plurality of contingent trajectories is further based on the inferred characteristic value.

9. The method of claim 1, wherein generating the trajectory comprises:

classifying subsets of input data including the path data as subsets of action to form classified subsets of data; and

identifying a subset of trajectories including the trajectory based on the classified subsets of data.

10. The method of claim 1, wherein detecting the cessation of the generation of the trajectory includes detecting data indicative of inoperable logic of a planner module of the autonomous vehicle.

11. A system comprising:

one or more vehicle components of an autonomous vehicle for controlling motion of the autonomous vehicle;

one or more processors communicatively coupled to the one or more vehicle components;

a localizer;

a perception engine;

a trajectory tracker; and

a memory storing instructions executable by the one or more processors and that, when executed by the one or more processors, configure the system to perform operations including;

receiving path data with which to guide motion of the autonomous vehicle from a first geographic location to a second geographic location;

receiving local pose data from the localizer;

receiving an object, a current object track, and a predicted object track from the perception engine;

substantially simultaneously generating at least a plurality of candidate trajectories and a plurality of candidate contingent trajectories based, at least in part, on the path data, the local pose data, the object, the current object track, and the predicted object track, the plurality of candidate trajectories and the plurality of candidate contingent trajectories being generated as the autonomous vehicle traverses a path;

selecting, by the trajectory tracker, a trajectory from the plurality of candidate trajectories;

selecting, by the trajectory tracker, a contingent trajectory from the plurality of candidate contingent trajectories;

controlling, by the trajectory tracker, the one or more vehicle components to direct motion of the autonomous vehicle according to the trajectory;

monitoring, by the trajectory tracker, generation of the trajectory;

detecting, by the trajectory tracker, an impairment in the generation of the trajectory; and

responsive to detecting the impairment of the generation of the trajectory, controlling, by the trajectory tracker, the one or more vehicle components to direct motion of the autonomous vehicle according to the contingent trajectory.

12. The system of claim 11, further comprising:

one or more trajectory trackers, the one or more trajectory trackers configured to;

monitor the generation of the trajectory;

detect the impairment of the generation of the trajectory; and

transmit the contingent trajectory to the one or more vehicle components of the autonomous vehicle to control motion of the autonomous vehicle.

13. The system of claim 12, wherein the operations further comprise:

transmitting a message to a teleoperator; and

receiving a response from the teleoperator, at least one of the one or more trajectory trackers being configured to receive one or more of lidar data, radar data, or sonar data.

14. The system of claim 11, further comprising:

one or more of a sensor to capture sensor data or a communications interface to receive the sensor data, and wherein the operations further include;

generating map data from the sensor data or receiving the map data via the communications interface, the map data including a three-dimensional model of an environment of the autonomous vehicle; and

generating perception data from the sensor data or receiving the perception data via the communications interface, the perception data including data associated with an external object; and

wherein;

generating the at least the plurality of candidate trajectories and the plurality of candidate contingent trajectories is further based, at least in part, on one or more of the map data, the perception data, or the path data, individual candidate trajectories and individual contingent trajectories having confidence levels associated therewith;

selecting the trajectory from the plurality of candidate trajectories is based, at least in part, on a confidence level associated with the trajectory; and

selecting the contingent trajectory from the plurality of candidate contingent trajectories is based, at least in part, on a confidence level associated with the contingent trajectory.

15. The system of claim 14, wherein:

the trajectory is generated to control motion of the autonomous vehicle in accordance with a receding horizon control technique,

the contingent trajectory is generated to control motion of the autonomous vehicle in response to detecting that generation of the trajectory by the system is impaired, and

detecting that the generation of the trajectory is impaired comprises;

determining one or more states of operation based, at least in part, on one or more of the map data, the object, the current object track, or the predicted object track;

determining a detected trajectory based, at least in part on, one or more of the perception data or the map data; and

determining that the generation of the trajectory is impaired based on a confidence level associated with the detected trajectory.

16. The system of claim 15, wherein the trajectory is generated by a planner module stored in the memory, and the impairment of the generation of the trajectory is attributable to one or more of a failure of the planner module or a non-normative state of operation of the autonomous vehicle.

17. The system of claim 11, wherein the one or more vehicle components include one or more of:

a propulsion unit;

a drivetrain;

a steering unit;

or

a braking unit.

18. The system of claim 11, wherein detecting the impairment in the generation of the trajectory includes detecting data indicative of inoperable logic of a planner module of the autonomous vehicle.

19. One or more non-transitory computer-readable media storing processor-executable instructions that, when executed, cause one or more processors to perform operations, the operations comprising:

determining, at a global planner, path data, the path data comprising information with which to guide motion of an autonomous vehicle from a first geographic location to a second geographic location;

substantially simultaneously generating at least a plurality of candidate trajectories and a plurality of candidate contingent trajectories based, at least in part, on the path data;

determining confidence levels associated with the plurality of candidate trajectories and the plurality of candidate contingent trajectories based, at least in part, on one or more of map data, current object state data, or predicted object state data;

selecting a trajectory from the plurality of candidate trajectories, based, at least in part, on a confidence level associated with the trajectory;

selecting a contingent trajectory from the plurality of candidate contingent trajectories, based, at least in part, on a confidence level associated with the contingent trajectory;

directing motion of the autonomous vehicle according to the trajectory;

monitoring generation of the trajectory;

detecting an impairment of the generation of the trajectory; and

responsive to detecting the impairment of the generation of the trajectory, directing motion of the autonomous vehicle according to the contingent trajectory.

20. The one or more non-transitory computer-readable media of claim 19, wherein the operations further comprise validating one or more of the trajectory or the contingent trajectory based, at least in part, on validation criteria;

and wherein;

the trajectory is generated in accordance with a receding horizon control technique;

the contingent trajectory is generated to control motion of the autonomous vehicle to a third geographic location responsive to detecting that generation of the trajectory is impaired; and

validating the one or more of the trajectory or the contingent trajectory comprises validating probability distributions against the validation criteria and confirming that the probability distributions are within one or more of predicted values or tolerances.

21. The one or more non-transitory computer-readable media of claim 19, wherein detecting the impairment of the generation of the trajectory includes detecting data indicative of inoperable logic of a planner module of the autonomous vehicle.