Secondary fallback software stack for autonomous vehicle

Patent metadata

Field	Value
Publication number	US-2023406293-A1
Application number	US-202217841494-A
Country	US
Kind code	A1
Filing date	Jun 15, 2022
Priority date	Jun 15, 2022
Publication date	Dec 21, 2023
Grant date	—

Abstract

Systems and methods for a vehicle to use a fallback control system orthogonal to a primary control system are provided. A method includes collecting, by a fallback control system of a vehicle, sensor data generated by one or more sensors of the vehicle; determining, by the fallback control system using a first process different from a second process of a primary control system of the vehicle, an alternative action for the vehicle based on the sensor data; and sending, by the fallback control system based on the alternative action, an instruction for modifying an action associated with the primary control system upon a faulty condition associated with the primary control system.

First claim

What is claimed is:

1 . A method comprising:
collecting, by a fallback control system of a vehicle, sensor data generated by one or more sensors of the vehicle; determining, by the fallback control system using a first process different from a second process of a primary control system of the vehicle, an alternative action for the vehicle based on the sensor data; and sending, by the fallback control system based on the alternative action, an instruction for modifying an action associated with the primary control system upon a detection of a faulty condition associated with the primary control system.

2 . The method of claim 1 , wherein the alternative action determined by the fallback control system includes at least stopping the vehicle.

3 . The method of claim 1 , wherein the determining the alternative action comprises:
performing, by the fallback control system, at least one of a perception, a prediction, or a planning using the first process different from the second process of the primary control system.

4 . The method of claim 1 , wherein:
the first process used for determining the alternative action is based on rules; and the second process of the primary control system is based on machine learning.

5 . The method of claim 1 , wherein the determining the alternative action for the vehicle comprises:
computing an alternative path for the vehicle using at least one less planning constraint than the primary control system.

6 . The method of claim 1 , wherein the determining the alternative action for the vehicle comprises:
computing an alternative path for the vehicle based on free space planning.

7 . A method comprising:
determining, by a primary planner of a vehicle, a first action for the vehicle using a first process; determining, by a fallback planner of the vehicle independent of the primary planner, an alternative action for the vehicle using a second process nonoverlapping with the first process, wherein the alternative action includes at least stopping the vehicle; sending an indication of the alternative action; and computing, by the fallback planner, a collision-free path for the vehicle responsive to a determination of an area at which the vehicle stopped after performing the alternative action fails to satisfy one or more area criteria.

8 . The method of claim 7 , wherein the computing the collision-free path for the vehicle comprises:
determining candidate exit roads, each including one or more exit lanes; filtering the exit lanes of the candidate exit roads based on one or more exit criteria; and selecting a first exit lane from the filtered exit lanes based at least in part on a distance between a location of the vehicle and the first exit lane.

9 . The method of claim 8 , wherein the computing the collision-free path for the vehicle further comprises:
determining whether a path from the location of the vehicle to the first exit lane is statically and dynamically collision-free.

10 . The method of claim 7 , wherein:
the first process used by the primary planner for determining the first action is based on a non-convex solver; and the second process used by the fallback planner for determining the alternative action is based on a free space planner.

11 . The method of claim 7 , wherein the computing the collision-free path is further based on free space planning, and wherein the free space planning is based on:
an occupancy grid map including an indication of one or more free spaces; and motion information associated with one or more tracked objects in the occupancy grid map.

12 . The method of claim 7 , further comprising:
determining the area at which the vehicle stopped fails to satisfy the one or more area criteria based on the area being associated with at least one of an intersection, an oncoming traffic lane, or an emergency driveway.

13 . The method of claim 7 , further comprising:
determining the area at which the vehicle stopped after performing the alternative action fails to satisfy the one or more area criteria, wherein the one or more area criteria is associated with an imminent collision between the vehicle and an object in the area.

14 . The method of claim 7 , wherein the determining the alternative action by the fallback planner is performed concurrently with the determining the first action by the primary planner.

15 . A vehicle comprising:
a primary control system to determine a first action for the vehicle based on first sensor data associated with an environment outside of the vehicle; a fallback control system to determine, independent of the primary control system, an alternative action for the vehicle based on second sensor data associated with the environment using at least one of a different perception process, a different prediction process, or a different planning process than the primary control system; and a path multiplexer to switch a control of the vehicle from the primary control system to the fallback control system responsive to a faulty condition associated with the primary control system by generating a first control command based on the alternative action.

16 . The vehicle of claim 15 , wherein the second sensor data used by the fallback control system to determine the alternative action is a subset of the first sensor data used by the primary control system to determine the first action, wherein the subset is less than all of the first sensor data.

17 . The vehicle of claim 15 , wherein the second sensor data used by the fallback control system to determine the alternative action is separate from the first sensor data used by the primary controls system to determine the first action.

18 . The vehicle of claim 15 , wherein:
the primary control system determines the first action further using machine learning; and the fallback control system determines the alternative action using heuristic-based rules.

19 . The vehicle of claim 15 , wherein:
the primary control system determines the first action by computing a first path for the vehicle based on a first set of constraints; and the fallback control system determines the alternative action for the vehicle by computing a second path for the vehicle based on a second set of constraints different from the first set of constraints.

20 . The vehicle of claim 15 , wherein:
the primary control system determines the first action by selecting the first action from a full set of candidate actions; and the fallback control system determines the alternative action by selecting the alternative action from a reduced set of candidate actions.

Assignees

• Gm Cruise Holdings Llc

Inventors

• Fasola Juan
• Lo Eugene
• Zhou Xiaoyu
• Kushwaha Shreyans

Classifications

• B60W30/09 Primary

  Taking automatic action to avoid collision, e.g. braking and steering · CPC title

• B60W50/0205 Primary

  Diagnosing or detecting failures; Failure detection models · CPC title

• B60W50/035

  Bringing the control units into a predefined state, e.g. giving priority to particular actuators · CPC title

• B60W50/038

  Limiting the input power, torque or speed · CPC title

• B60W60/0015

  specially adapted for safety · CPC title