Autonomous vehicle: modular architecture

• US 10,377,375 B2
• Filed: 09/29/2016
• Issued: 08/13/2019
• Est. Priority Date: 09/29/2016
• Status: Active Grant

• Current Assignee: Arriver Software LLC, Charles Stark Draper Laboratory Incorporated
• Original Assignee: Charles Stark Draper Laboratory Incorporated
• Inventors: Jones, Troy, Lennox, Scott, Sgueglia, John, Demerly, Jon, Zervoglos, Nicholas Alexander, Yang, Hsin-Hsiang
• Primary Examiner(s): Black, Thomas G
• Assistant Examiner(s): Thomas, Ana D
• Application Number:
  US15/280,454
• Publication Number:
  US 20180086336A1
• Time in Patent Office: 1,048 Days
• CPC Class Codes: B60W 10/04 including control of propulsion units
• CPC Class Codes: B60W 10/18 including control of braking systems
• CPC Class Codes: B60W 10/20 including control of steering systems
• CPC Class Codes: B60W 2400/00 Indexing codes relating to detected, measured or calculated conditions or factors
• 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 2540/00 Input parameters relating to occupants
• CPC Class Codes: B60W 2540/045 Occupant permissions
• CPC Class Codes: B60W 2554/00 Input parameters relating to objects
• CPC Class Codes: B60W 2554/4042 Longitudinal speed
• CPC Class Codes: B60W 2554/4049 Relationship among other objects, e.g. converging dynamic objects
• CPC Class Codes: B60W 2554/802 Longitudinal distance
• CPC Class Codes: B60W 2710/18 Braking system
• CPC Class Codes: B60W 2710/20 Steering systems
• CPC Class Codes: B60W 2720/10 Longitudinal speed
• CPC Class Codes: B60W 2900/00 Indexing codes relating to the purpose of, or problem solved of road vehicle drive control systems not otherwise provided for in groups B60W30/00
• CPC Class Codes: B60W 30/09 Taking automatic action to avoid collision, e.g. braking and steering
• CPC Class Codes: B60W 30/095 Predicting travel path or likelihood of collision
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: B60W 30/18163 Lane change; Overtaking manoeuvres
• CPC Class Codes: B60W 50/0097 : Predicting future conditions
• CPC Class Codes: B60W 50/02 : Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
• 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 60/0016 : of the vehicle or its occupants
• CPC Class Codes: B60W 60/00272 : relying on extrapolation of current movement
• CPC Class Codes: B60W 60/00276 : for two or more other traffic participants
• CPC Class Codes: B60W 60/005 : Handover processes Handing over between remote control and on-board control or handing over between remote control arrangements G05D1/227
• CPC Class Codes: B60W 60/0055 : only part of driving tasks shifted to occupants
• CPC Class Codes: B60W 60/0059 : Estimation of the risk associated with autonomous or manual driving, e.g. situation too complex, sensor failure or driver incapacity
• CPC Class Codes: G05B 15/02 : electric
• CPC Class Codes: G05D 1/0088 : characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00

Abstract

An architecture for an autonomous vehicle uses a top-down approach to enable fully automated driving. The architecture is modular and compatible with hardware from different manufacturers. Each modular component can be tailored for individual cars, which have different vehicle control subsystems and different sensor subsystems.

Claims

1. A method of operating an autonomous vehicle, the method comprising:

determining, at an automated driving controller (ADC), one or more planned driving corridors that are predicted to be drivable by the vehicle and safely separated from surrounding vehicles and other objects;

determining, at a vehicle controller (VC), based on the one or more planned driving corridors, one or more vehicle trajectories which are predicted to avoid collisions with the surrounding vehicles and other objects;

selecting, at the VC, one of the determined trajectories as active based on criteria of collision likelihood;

sending steering, throttle, and braking commands from the VC to one or more respective actuator controllers within the vehicle to follow the active trajectory.

2. The method of claim 1, further comprising:

at a perception controller (PC), generating a stochastic prediction of free space available for driving based on locations of observed vehicles or other objects;

at the ADC, determining the driving corridors from the stochastic prediction of free space;

at the PC, generating a kinematic prediction of the free space available for driving by performing kinematic-based predictions of the locations of vehicles and objects within a threshold radius;

at the VC;

determining one or more corridor trajectories in a given corridor that meet ride comfort design goals;

determining an emergency trajectory from an updated kinematic free space prediction;

selecting a nominal or emergency trajectory based on a collision-avoidance likelihood, the collision-avoidance likelihood being based on the updated kinematic free space prediction;

generating updated steering, throttle, and braking commands to follow the selected trajectory corridor; and

sending updated commands to the actuator controllers for execution.

3. The method of claim 1, further comprising:

at the ADC;

planning a route of roadways for the autonomous vehicle to travel to a destination, wherein determining the corridor within the route of roadways is based on information determined by a plurality of sensors about a driving surface and objects surrounding the autonomous vehicle.

4. The method of claim 1, further comprising:

translating inputs from a plurality of sensor subsystems to a vendor-neutral format at a sensor interface server (SIS).

5. The method of claim 1, further comprising:

determining a position and an attitude of the autonomous vehicle from a plurality of sensor inputs at a localization controller (LC).

6. The method of claim 1, further comprising:

determining objects around the autonomous vehicle and on drivable surfaces, detected by a plurality of sensor subsystems, at a perception controller (PC).

7. The method of claim 1, further comprising:

providing an interface for interaction between an operator, passengers, and humans external to the vehicle at a human interaction controller (HIC).

8. The method of claim 1, further comprising:

interacting with other-self driving cars or automated systems through a machine interface controller (MC).

9. The method of claim 1, further comprising:

coordinating exchanges, at a system controller (SC), of control between an operator and elements of the autonomous vehicle.

10. The method of claim 9, further comprising:

monitoring the elements of the autonomous vehicle for failures or other abnormal behavior, managing corrective actions to resolve failures.

11. The method of claim 1, further comprising:

at the VC, driving outside of the ADC determined corridor in response to determining a likelihood of collision within that corridor.

12. The method of claim 1, further comprising:

minimizing use of communication bandwidth in an architecture of the autonomous vehicle by providing;

a sensor interface server (SIS) configured to translate and filter sensor data sent to other elements of the architecture;

a perception controller (PC) configured to fuse sensor measurements from a plurality of sensors into a single estimate of perceptions of the environment around the autonomous vehicle; and

a localization controller (LC) configured to fuse outputs from multiple sensor measurements into a single position and attitude of the autonomous vehicle in the world.

13. The method of claim 1, further comprising:

measuring availability of the operator of the autonomous vehicle to assist in driving the vehicle; and

providing a variable level of automated function by the autonomous vehicle based on the measured availability of the operator at a human interface controller (HC).

14. The method of claim 1, further comprising:

at a human interface controller (HC);

translating internal status of the autonomous vehicle to a human understandable format; and

presenting the translated internal status in the human understandable format to the operator.

15. A system for operating an autonomous vehicle, the system comprising:

an automated driving controller (ADC) configured to determine, one or more planned driving corridors that are predicted to be drivable by the vehicle and safely separated from surrounding vehicles and other objects; and

a vehicle controller (VC) configured to;

determine, based on the one or more planned driving corridors, one or more vehicle trajectories which are predicted to avoid collisions with the surrounding vehicles and other objects;

select one of the determined trajectories as active based on criteria of collision likelihood; and

send steering, throttle, and braking commands to one or more respective actuator controllers within the vehicle to follow the active trajectory.

16. The system of claim 15, further comprising:

a perception controller (PC) configured to generate a stochastic prediction of free space available for driving based on locations of observed vehicles or other objects;

wherein the ADC is further configured to determine the driving corridors from the stochastic prediction of free space;

wherein the PC is further configured to generate a kinematic prediction of the free space available for driving by performing kinematic-based predictions of the locations of vehicles and objects within a threshold radius;

wherein the VC is further configured to;

determine one or more corridor trajectories in a given corridor that meet ride comfort design goals;

determine an emergency trajectory corridor from an updated kinematic free space prediction;

select a nominal or emergency trajectory based on a collision-avoidance likelihood, the collision-avoidance likelihood being based on the updated kinematic free space prediction;

generate updated steering, throttle, and braking commands to follow the selected trajectory corridor; and

send updated commands to the actuator controllers for execution.

17. The system of claim 15, wherein the ADC is further configured to plan a route of roadways for the autonomous vehicle to travel to a destination, wherein determining the corridor within the route of roadways is based on information determined by a plurality of sensors about the driving surface and objects surrounding the autonomous vehicle.

18. The system of claim 15, further comprising:

a sensor interface server (SIS) configured to translate inputs from a plurality of sensor subsystems to a vendor-neutral format.

19. The system of claim 15, further comprising:

a localization controller configured to determine a position and an attitude of the autonomous vehicle from a plurality of sensor inputs.

20. The system of claim 15, further comprising:

a perception controller (PC) configured to determine objects around the autonomous vehicle and on drivable surfaces, detected by a plurality of sensor subsystems.

21. The system of claim 15, further comprising:

a human interaction controller (HC) configured to provide an interface for interaction between an operator, passengers, and humans external to the vehicle.

22. The system of claim 16, further comprising:

machine interaction controller (MC) configured to interact with other-self driving cars or automated systems.

23. The system of claim 15, further comprising:

a system controller (SC) configured to coordinate exchanges of control between the operator and elements of the modular architecture of the autonomous vehicle.

24. The system of claim 23, wherein the SC is further configured to monitor the elements of the autonomous vehicle for failures or other abnormal behavior, managing corrective actions to resolve failures.

25. The system of claim 15, wherein the vehicle controller is further configured to drive outside the ADC generated corridor in response to determining a high likelihood of collision within that corridor.

26. The system of claim 15, further comprising:

a sensor interface server (SIS) configured to translate and filter sensor data sent to other elements of the architecture;

a perception controller (PC) configured to fuse sensor measurements from the plurality of sensors into a single estimate of perceptions of the environment around the autonomous vehicle; and

a localization controller (LC) configured to fuse outputs from multiple sensors measurements into a single position and attitude of the autonomous vehicle in the world;

wherein the sensor interface server, perception controller, and localization controller minimize use of communication bandwidth in an architecture of the autonomous vehicle.

27. The system of claim 15, further comprising:

a human interaction controller (HC) configured to measure availability of the operator of the autonomous vehicle to assist in driving the vehicle, and provide a variable level of automated function by the autonomous vehicle based on the measured availability of the operator.

28. The system of claim 15, further comprising:

a human interaction controller (HC) configured to translate internal status of the autonomous vehicle to a human-understandable format, and present the translated internal status in the human-understandable format to the operator.