Controlling an autonomous vehicle based upon computed lane boundaries

US10829121B1 · US · B1

Patent metadata
FieldValue
Publication numberUS-10829121-B1
Application numberUS-201816052750-A
CountryUS
Kind codeB1
Filing dateAug 2, 2018
Priority dateAug 2, 2018
Publication dateNov 10, 2020
Grant dateNov 10, 2020

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.

Described herein are technologies relating to controlling an autonomous vehicle based upon a computed lane boundary. The computed lane boundary defines a travel path for the autonomous vehicle when the autonomous vehicle turns across a lane of traffic at an intersection of two or more roadways. The autonomous vehicle navigates turn based upon the computed lane boundary, which allows the autonomous vehicle to enter the intersection without crossing into a lane of oncoming traffic.

First claim

Opening claim text (preview).

What is claimed is: 1. An autonomous vehicle (AV), comprising: a sensor system that is configured to output data that is indicative of surroundings of the AV; an engine; a braking system; a steering system; and a computing system that is in communication with the sensor system, the engine, the braking system, and the steering system, the computing system comprises: a processor; and memory storing: a map of a geographic region, wherein the map comprises: a first lane boundary for a first roadway, the first lane boundary representative of a first painted lane boundary between traffic lanes on the first roadway, wherein the traffic lanes comprise a first lane for traffic travelling in a first direction and a second lane for traffic travelling in a second direction that is opposite the first direction; a second lane boundary for a second roadway that intersects the first roadway, the second lane boundary representative of a second painted lane boundary on the second roadway, wherein the second roadway comprises a third lane for traffic travelling in a third direction; a third lane boundary that connects the first lane boundary with the second lane boundary, wherein the third lane boundary is computed and fails to be representative of a painted lane boundary on either the first roadway or the second roadway, wherein the third lane boundary defines a travel boundary for when the AV travels from the first lane of the first roadway to the third lane of the second roadway and across the second lane of the first roadway, wherein the third lane boundary is computed based upon:  the first lane boundary; and  the second lane boundary, wherein the third lane boundary is labeled in the map as being a computed lane boundary rather than representative of a painted lane boundary; and instructions that, when executed by the processor, cause the processor to perform acts comprising: receiving the data output by the sensor system; and based upon the data output by the sensor system and the map, controlling at least one of the engine, the braking system, or the steering system to cause the AV to exit the first lane of the first roadway and enter the third lane of the second roadway based upon the third lane boundary, wherein the at least one of the engine, the braking system, or the steering system is controlled to cause the AV to cross the third lane boundary due to the third lane boundary being labeled as the computed lane boundary in the map, and further wherein the AV is caused to cross the third lane boundary to reduce a distance that the AV is to travel to enter the third lane of the second roadway compared to if the AV were to enter the third lane of the second roadway when failing to cross the third lane boundary. 2. The AV of claim 1 , wherein controlling the at least one of the engine, the braking system, or the steering system comprises: causing the AV to enter an intersection of the first roadway and the second roadway; causing the AV to wait for a vehicle travelling in the second direction to pass the AV while the AV is in the intersection; and causing the AV to exit the intersection and enter the third lane of the second roadway. 3. The AV of claim 2 , wherein the third lane boundary is computed based further upon whether an angle between the first lane boundary and the second lane boundary is acute or obtuse. 4. The AV of claim 1 , wherein the sensor system is one of a lidar sensor system, a radar sensor system, or a camera sensor system. 5. The AV of claim 1 , wherein the engine is an electric engine. 6. The AV of claim 1 , wherein the acts further comprise computing the third lane boundary as the AV travels over roadways. 7. The autonomous vehicle of claim 1 , wherein the third lane boundary is computed based further upon a turn radius of the AV, and further wherein the third lane boundary comprises a first Bezier curve that extends from the first lane boundary to a point and a second Bezier curve that extends from the point to the second lane boundary, and further wherein the first Bezier curve has a length that is computed based upon a distance between an endpoint of the first lane boundary and an endpoint of the second lane boundary. 8. The AV of claim 7 , wherein the length of the first Bezier curve is computed based further upon an angle between the first lane boundary and the second lane boundary when the first lane boundary and the second lane boundary are extended to intersect with one another. 9. The AV of claim 7 , wherein the length of the first Bezier curve is computed based further upon a depth of an intersection between the first roadway and the second roadway. 10. The AV of claim 7 , wherein the length of the first Bezier curve is computed based further upon a width of an intersection between the first roadway and the second roadway. 11. A method performed by a processor of a computing system, the method comprising: receiving, in computer-readable storage of the computing system, a map of roadways, wherein the map of roadways comprises: a first lane boundary for a first roadway, the first lane boundary represents a first painted lane boundary on the first roadway that separates traffic lanes of the first roadway, the traffic lanes comprise a first traffic lane for vehicles travelling in a first direction and a second traffic lane for vehicles travelling in a second direction that is opposite the first direction; and a second lane boundary for a second roadway that intersects the first roadway, the second lane boundary represents a second painted lane boundary on the second roadway, wherein the second roadway comprises a third lane; computing a third lane boundary that couples the first lane boundary to the second lane boundary, wherein the third lane boundary is computed based upon the first lane boundary and the second lane boundary; and updating, in the computer-readable storage, the map of roadways to include the third lane boundary, wherein the third lane boundary is labeled in the map as being a computed lane boundary rather than a lane boundary that represents a painted lane boundary in the roadways, wherein an autonomous vehicle (AV) is provided with the updated map, wherein the AV, when exiting the first traffic lane and entering the third traffic lane, crosses the second traffic lane based upon the third lane boundary, wherein when completing a turn from the first traffic lane to the third traffic lane, the AV crosses the third lane boundary due to the third lane boundary being labeled as being the computed lane boundary rather than the lane boundary that represents a painted lane boundary, and further wherein the AV crosses the third lane boundary to reduce a distance travelled by the AV when exiting the first traffic lane and entering the third traffic lane compared to if the AV were to fail to cross the third lane boundary when exiting the first traffic lane and entering the third traffic lane. 12. The method of claim 11 , wherein the third lane boundary is computed such that the third lane boundary comprises a straightened section that extends linearly from the first lane boundary to a point and a curved section that extends from the point to the second lane boundary, wherein the straightened section has a length, and further wherein the length of the straightened section is based upon a distance between an endpoint of the first lane boundary and an endpoint of the second lane boundary. 13. The method of claim 12 , wherein the length of the straightened section is further computed based upon a turn radius of the AV. 14. The method of claim 12 , wherein the length of the straightened section

Assignees

Inventors

Classifications

  • Following a predefined trajectory, e.g. a line marked on the floor or a flight path · CPC title

  • Handing over between remote control and on-board control; Handing over between remote control arrangements · CPC title

  • Lane change; Overtaking manoeuvres · CPC title

  • including control of steering systems · CPC title

  • including control of braking systems · 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 US10829121B1 cover?
Described herein are technologies relating to controlling an autonomous vehicle based upon a computed lane boundary. The computed lane boundary defines a travel path for the autonomous vehicle when the autonomous vehicle turns across a lane of traffic at an intersection of two or more roadways. The autonomous vehicle navigates turn based upon the computed lane boundary, which allows the autonom…
Who is the assignee on this patent?
Gm Global Tech Operations Llc
What technology area does this patent fall under?
Primary CPC classification B60W30/18163. Mapped technology areas include Operations & Transport.
When was this patent published?
Publication date Tue Nov 10 2020 00:00:00 GMT+0000 (Coordinated Universal Time) (B1). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 4 related publications on this page (citations in our corpus or others sharing the same primary CPC).