Control systems, control methods and controllers for an autonomous vehicle

US10955842B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-10955842-B2
Application numberUS-201815988630-A
CountryUS
Kind codeB2
Filing dateMay 24, 2018
Priority dateMay 24, 2018
Publication dateMar 23, 2021
Grant dateMar 23, 2021

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

Systems and methods are provided for controlling an autonomous vehicle (AV). A scene understanding module of a high-level controller selects a particular combination of sensorimotor primitive modules to be enabled and executed for a particular driving scenario from a plurality of sensorimotor primitive modules. Each one of the particular combination of the sensorimotor primitive modules addresses a sub-task in a sequence of sub-tasks that address a particular driving scenario. A primitive processor module executes the particular combination of the sensorimotor primitive modules such that each generates a vehicle trajectory and speed profile. An arbitration module selects one of the vehicle trajectory and speed profiles having the highest priority ranking for execution, and a vehicle control module processes the selected one of vehicle trajectory and speed profiles to generate control signals used to execute one or more control actions to automatically control the AV.

First claim

Opening claim text (preview).

What is claimed is: 1. A method for controlling an autonomous vehicle, the method comprising: selecting, at a scene understanding module of a high-level controller, a particular combination of sensorimotor primitive modules to be enabled and executed for a particular driving scenario from a plurality of sensorimotor primitive modules, wherein each one of the particular combination of the sensorimotor primitive modules addresses a sub-task in a sequence of sub-tasks that address a particular driving scenario; executing, at a primitive processor module, the particular combination of the sensorimotor primitive modules such that each generates a vehicle trajectory and a speed profile; selecting, at an arbitration module, one of the vehicle trajectories and the speed profiles having a highest priority ranking for execution , wherein the highest priority ranking is based on a priority ranking associated with each type of sensorimotor primitive module; and processing, at a vehicle control module, the selected one of the vehicle trajectories and the speed profiles to generate control signals used to execute one or more control actions to automatically control the autonomous vehicle. 2. The method for controlling the autonomous vehicle according to claim 1 , further comprising: applying, at the arbitration module, priority logic rules to define a priority order of execution for each of the vehicle trajectories and the speed profiles; wherein the selecting, at the arbitration module, the one of the vehicle trajectories and the speed profiles having the highest priority ranking for execution comprises: selecting, at the arbitration module, one of the vehicle trajectory and speed profiles having the highest priority ranking for execution based on the priority order; and wherein the processing, at the vehicle control module, the selected one of the vehicle trajectories and the speed profiles to generate the control signals comprises: processing, at the vehicle control module, the selected one of the vehicle trajectories and the speed profiles by applying a neuromorphic control model to the selected one of the vehicle trajectories and the speed profiles to generate the control signals. 3. The method for controlling the autonomous vehicle according to claim 2 , wherein the processing, at the vehicle control module of the vehicle controller module, the selected one of the vehicle trajectories and the speed profiles, comprises: generating, at an inverse dynamic mapping module of the vehicle control module, the control signals based on the selected one of the vehicle trajectories and the speed profiles from the arbitration module and a predicted vehicle trajectory and speed profile; and generating, at a forward dynamic mapping module of the vehicle control module based on the control signals feedback from the inverse dynamic mapping module, the predicted vehicle trajectory and speed profile. 4. The method for controlling the autonomous vehicle according to claim 2 , wherein the priority logic rules define a relative priority for each vehicle trajectory and speed profile. 5. The method for controlling the autonomous vehicle according to claim 1 , further comprising: prior to the selecting, at a scene understanding module of a high-level controller, the particular combination: processing, at a map generator module of the high-level controller, sensor data from a sensor system to generate a world representation of a particular driving scenario as represented by the sensor data, navigation route data that indicates a route of the autonomous vehicle, and vehicle position information that indicates a location of the autonomous vehicle at a particular instant of time, wherein the world representation comprises a feature map; and processing, at the scene understanding module, the navigation route data that indicates a route of the autonomous vehicle, the vehicle position information that indicates location of the autonomous vehicle and the feature map to define an autonomous driving task; and decomposing, at the scene understanding module, the autonomous driving task into a sequence of sub-tasks that address the particular driving scenario; after processing, at the vehicle control module, the selected one of the vehicle trajectories and the speed profiles: processing, at a low-level controller, the control signals from the vehicle control module to generate commands that control one or more of actuators of the autonomous vehicle in accordance with the control signals to schedule and execute one or more control actions to be performed to automatically control the autonomous vehicle to automate the autonomous driving task encountered in the particular driving scenario and achieve the selected one of the vehicle trajectories and the speed profiles, wherein the actuators include one or more of a steering controller, a brake system, and a throttle system. 6. The method for controlling the autonomous vehicle according to claim 1 , wherein each sensorimotor primitive module is executable to generate the vehicle trajectory and the speed profile for automatically controlling the autonomous vehicle to cause the autonomous vehicle to perform a specific driving maneuver. 7. The method for controlling the autonomous vehicle according to claim 1 , wherein each sensorimotor primitive module maps information from a world representation to the vehicle trajectory and the speed profile, and wherein each vehicle trajectory and speed profile maps to one or more control signals that cause one or more control actions that automatically control the autonomous vehicle to cause the autonomous vehicle to perform a specific driving maneuver that addresses the particular driving scenario encountered during the autonomous driving task and operation of the autonomous vehicle. 8. An autonomous vehicle control system, comprising: a sensor system that is configured to provide sensor data; a map generator module that is configured to process the sensor data to generate a world representation of the particular driving scenario as represented by the sensor data, navigation route data that indicates a route of an autonomous vehicle, and vehicle position information that indicates location of the autonomous vehicle at a particular instant of time, the word representation comprising a feature map; a vehicle controller module comprising: a memory configured to store a plurality of sensorimotor primitive modules; a scene understanding module that is configured to select, based on the feature map, a particular combination of the sensorimotor primitive modules to be enabled and executed for a particular driving scenario, wherein each one of the particular combination of the sensorimotor primitive modules addresses a sub-task in a sequence of sub-tasks that address the particular driving scenario; a primitive processor module configured to execute the particular combination of the sensorimotor primitive modules such that each generates a vehicle trajectory and a speed profile; an arbitration module configured to select one of the vehicle trajectories and the speed profiles having a highest priority ranking for execution, wherein the highest priority ranking is based on a priority ranking associated with each type of sensorimotor primitive module; and a vehicle control module configured to process the selected one of the vehicle trajectories and the speed profiles to generate control signals used to execute one or more control actions to automatically control an autonomous vehicle. 9. The autonomous vehicle control system according to claim 8 , wherein the arbitration module is further configured to: apply priority logic rules to define a priority order of execution for each of the v

Assignees

Inventors

Classifications

  • specially adapted for safety · CPC title

  • Image sensing, e.g. optical camera · CPC title

  • using trajectory prediction for other traffic participants · CPC title

  • using neural networks · CPC title

  • exterior to a vehicle by using sensors mounted on the vehicle · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US10955842B2 cover?
Systems and methods are provided for controlling an autonomous vehicle (AV). A scene understanding module of a high-level controller selects a particular combination of sensorimotor primitive modules to be enabled and executed for a particular driving scenario from a plurality of sensorimotor primitive modules. Each one of the particular combination of the sensorimotor primitive modules address…
Who is the assignee on this patent?
Gm Global Tech Operations Llc
What technology area does this patent fall under?
Primary CPC classification B60W60/0027. Mapped technology areas include Operations & Transport.
When was this patent published?
Publication date Tue Mar 23 2021 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 1 related publication on this page (citations in our corpus or others sharing the same primary CPC).