Driver intention-based lane assistant system for autonomous driving vehicles

US10668925B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-10668925-B2
Application numberUS-201715695885-A
CountryUS
Kind codeB2
Filing dateSep 5, 2017
Priority dateSep 5, 2017
Publication dateJun 2, 2020
Grant dateJun 2, 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.

In one embodiment, a lane assistant system is configured to provide lane assistance to a driver of an autonomous driving vehicle (ADV) based on the driver's intention determined at the point in time by capturing and analyzing user actions and driving environment surrounding the ADV. By analyzing the user actions and the driving environment surrounding the vehicle, the driver's intention can be determined. The driver's intention can be utilized to interpret whether the driver indeed intends to change lane. Based on the driver's intention, the lane assistance can be provided, either allowing the vehicle change or exit the current lane, or automatically providing warning or correction of the moving direction of the vehicle.

First claim

Opening claim text (preview).

What is claimed is: 1. A computer-implemented method for operating an autonomous driving vehicle, the method comprising: obtaining route and map data related to a route along which an autonomous driving vehicle (ADV) is to travel; detecting, while traveling along the route, that the ADV is drifting towards an edge of a current lane of a road on which the ADV is moving by comparing a moving direction of the ADV against lane markings of the current lane; in response to detecting that the ADV is drifting towards the edge of the current lane of the road, determining one or more user actions performed by a driver of the ADV prior to detecting that the ADV is drifting, determining, using one or more sensors mounted on the ADV, a driving environment surrounding the ADV, the driving environment including information describing lane configuration of the road, examining the route and map data associated with the road on which the ADV is moving to determine whether there is another lane adjacent to the current lane on the edge to which the ADV is drifting, and determining a user intention of possible lane changing based on the user actions, the determined driving environment, and the determination of whether there is another lane adjacent to the current lane on the edge, wherein the user intention indicates that the driver does not intend to change lanes if there is no adjacent lane on the edge to which the ADV is drifting; allowing the ADV to continue drifting towards the edge of the road if the user intention indicates that the driver intends to change lane; and automatically modifying the moving direction of the ADV to cause the ADV to move away from the edge and to remain within the current lane if the user intention indicates that the driver does not intend to change lane. 2. The method of claim 1 , wherein determining a user intention of possible lane changing comprises: determining whether a turn signal conforming to a drifting direction has been turned on; and indicating that the driver intends to change lane if the turn signal conforming to a drifting direction has been turned on. 3. The method of claim 1 , wherein determining a user intention of possible lane changing comprises: examining routing information associated with the current road to determine whether there is a continuing path exiting from the current lane towards a side to which the ADV is drifting; and indicating that the driver intends to change lane if there is a continuing path exiting from the current lane towards a side to which the ADV is drifting. 4. The method of claim 1 , wherein determining a user intention of possible lane changing comprises: determining whether there is another vehicle moving at a blind spot of the ADV in an adjacent lane to which the ADV is drifting; and indicating that the driver does not intend to change lane if there is another vehicle moving at a blind spot of the ADV in the adjacent lane to which the ADV is drifting. 5. The method of claim 1 , wherein determining a user intention of possible lane changing comprises: determining whether there is an obstacle in front of the ADV based on perception data perceiving the driving environment; and indicating that the driver intends to change lane if there is an obstacle in front of the ADV. 6. The method of claim 5 , wherein the obstacle is moving slower than the ADV, and wherein a different between a speed of the obstacle and a speed of the ADV is above a predetermined threshold. 7. The method of claim 1 , wherein determining a user intention of possible lane changing comprises: determining whether there is a rough road surface of the current lane ahead of the ADV based on sensor data obtained from one or more sensors; and indicating that the driver intends to change lane if there is a rough road surface ahead of the ADV. 8. The method of claim 1 further comprising providing a lane departure warning alert when the user intention indicates that the driver does not intend to change lanes, wherein automatic modification of the moving direction of the ADV is in response to not receiving correction actions from the driver within a period of time since the lane departure warning alert was provided. 9. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations, the operations comprising: obtaining route and map data related to a route along which an autonomous driving vehicle (ADV) is to travel; detecting, while traveling along the route, that the ADV is drifting towards an edge of a current lane of a road on which the ADV is moving by comparing a moving direction of the ADV against lane markings of the current lane; in response to detecting that the ADV is drifting towards the edge of the current lane of the road, determining one or more user actions performed by a driver of the ADV prior to detecting that the ADV is drifting, determining, using one or more sensors mounted on the ADV, a driving environment surrounding the ADV, the driving environment including information describing lane configuration of the road, examining the route and map data associated with the road on which the ADV is moving to determine whether there is another lane adjacent to the current lane on the edge to which the ADV is drifting, and determining a user intention of possible lane changing based on the user actions, the determined driving environment, and the determination of whether there is another lane adjacent to the current lane on the edge, wherein the user intention indicates that the driver does not indent to change lanes if there is no adjacent lane on the edge to which the ADV is drifting; allowing the ADV to continue drifting towards the edge of the road if the user intention indicates that the driver intends to change lane; and automatically modifying the moving direction of the ADV to cause the ADV to move away from the edge and to remain within the current lane if the user intention indicates that the driver does not intend to change lane. 10. The machine-readable medium of claim 9 , wherein determining a user intention of possible lane changing comprises: determining whether a turn signal conforming to a drifting direction has been turned on; and indicating that the driver intends to change lane if the turn signal conforming to a drifting direction has been turned on. 11. The machine-readable medium of claim 9 , wherein determining a user intention of possible lane changing comprises: examining routing information associated with the current road to determine whether there is a continuing path exiting from the current lane towards a side to which the ADV is drifting; and indicating that the driver intends to change lane if there is a continuing path exiting from the current lane towards a side to which the ADV is drifting. 12. The machine-readable medium of claim 9 , wherein determining a user intention of possible lane changing comprises: determining whether there is another vehicle moving at a blind spot of the ADV in an adjacent lane to which the ADV is drifting; and indicating that the driver does not intend to change lane if there is another vehicle moving at a blind spot of the ADV in the adjacent lane to which the ADV is drifting. 13. The machine-readable medium of claim 9 , wherein determining a user intention of possible lane changing comprises: determining whether there is an obstacle in front of the ADV based on perception data perceiving the driving environment; and indicating that the driver intends to change lane if there is an obstacle in front of the ADV.

Assignees

Inventors

Classifications

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 US10668925B2 cover?
In one embodiment, a lane assistant system is configured to provide lane assistance to a driver of an autonomous driving vehicle (ADV) based on the driver's intention determined at the point in time by capturing and analyzing user actions and driving environment surrounding the ADV. By analyzing the user actions and the driving environment surrounding the vehicle, the driver's intention can be …
Who is the assignee on this patent?
Baidu Usa Llc
What technology area does this patent fall under?
Primary CPC classification G08G1/167. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Jun 02 2020 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 3 related publications on this page (citations in our corpus or others sharing the same primary CPC).