US 11,238,733 B2Granted

Group driving style learning framework for autonomous vehicles

AssigneeBaidu USA LLC

InventorsYifei Jiang, Dong Li, Jiaming Tao, Jiangtao Hu, Liyun Li, Guang Yang, Jingao Wang

Life of this patent

Estimating the term…

Loading patent…

Abstract

A social driving style learning framework or system for autonomous vehicles is utilized, which can dynamically learn the social driving styles from surrounding vehicles and adopt the driving style as needed. Each of the autonomous vehicles within a particular driving area is equipped with the driving style learning system to perceive the driving behaviors of the surrounding vehicles to derive a set of driving style elements. Each autonomous vehicle transmits the driving style elements to a centralized remote server. The server aggregates the driving style elements collected from the autonomous vehicles to determine a driving style corresponding to that particular driving area. The server transmits the driving style back to each of the autonomous vehicles. The autonomous vehicles can then decide whether to adopt the driving style, for example, to follow the traffic flow with the rest of the vehicles nearby.

Claims22

Dependent claims

A non-transitory machine-readable medium storing instructions, which when executed by a processor, cause the processor to perform operations of operating an autonomous vehicle, the operations comprising:

perceiving, by a first autonomous vehicle, driving behaviors of one or more first surrounding vehicles, each of the one or more first surrounding vehicles surrounding the first autonomous vehicle;
determining, for each of the one or more first surrounding vehicles, first information describing one or more driving style elements based on a driving behavior of the surrounding vehicle;
transmitting second information describing a first set of driving style elements representing driving behaviors of the one or more first surrounding vehicles from the first autonomous vehicle to a second autonomous vehicle over a wireless network, the second information comprising some or all of the first information;
receiving third information describing a second set of driving style elements from the second autonomous vehicle, the second set of driving style elements determined by the second autonomous vehicle based on a perception of driving behaviors of one or more second surrounding vehicles surrounding the second autonomous vehicle;
determining a driving style based on at least some of the second information and at least some of the third information, wherein the driving style includes fourth information describing how the first autonomous vehicle should drive at a point in time in view of the one or more first surrounding vehicles, the one or more second surrounding vehicles, or both;
and
operating the first autonomous vehicle based on planning and control data generated based, at least in part, on the driving style, wherein operating the first autonomous vehicle comprises controlling the first autonomous vehicle, driving the first autonomous vehicle, or both.

4 more elements

A computer-implemented method for operating autonomous driving vehicles, the method comprising:

receiving, at a server, first information describing one or more driving style elements associated with a plurality of autonomous driving vehicles (ADVs) over a network;
determining one or more driving areas based on locations of the plurality of ADVs;
and
for each of the one or more driving areas,
identifying a first set of ADVs that are within a predetermined proximity of the driving area, the first set of ADVs comprising one or more ADVs from the plurality of ADVs,
performing an analysis on second information describing one or more driving style elements that are associated with the first set of ADVs, the first information comprising the second information,
determining a driving style corresponding to the driving area based on the analysis, and
transmitting the driving style to a second set of ADVs that are within the predetermined proximity of the driving area, the second set of ADVs comprising one or more ADVs from the plurality of ADVs and the driving style including third information describing how each ADV from the second set of ADVs should drive in the driving area.

5 more elements

A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations of operating autonomous driving vehicles, the operations comprising:

receiving, at a server, first information describing one or more driving style elements from a plurality of autonomous driving vehicles (ADVs) over a network;
determining one or more driving areas based on locations of the plurality of ADVs;
and
for each of the one or more driving areas,
identifying a first set of ADVs that are within a predetermined proximity of the driving area, the first set of ADVs comprising one or more ADVs from the plurality of ADVs,
performing an analysis on second information describing one or more driving style elements that are associated with the first set of ADVs, the first information comprising the second information,
determining a driving style corresponding to the driving area based on the analysis, and
transmitting the driving style to a second set of ADVs that are within the predetermined proximity of the driving area, the second set of ADVs comprising one or more ADVs from the plurality of ADVs and the driving style including third information describing how each ADV from the second set of ADVs should drive in the driving area.

5 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/040,494Filed 19 Jul 2018 · continuation
Priority: 13 Oct 2016
Published: US 2018/0107942 A16 Dec 2018
Granted: 1 Feb 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification26 codes

G08G 1/096725
Where the received information might be used to generate an automatic action on the vehicle control: where the received information generates an…
B60W 30/09
Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences: taking automatic action…
B60W 30/0956
Predicting travel path or likelihood of collision: the prediction being responsive to traffic or environmental parameters
B60W 60/0016
Specially adapted for safety: of the vehicle or its occupants

Family

Application15/292,970Parent of this continuation · filed 13 Oct 2016
US 2018/0349802 A1Pre-grant publication · published 6 Dec 2018
US 10,049,328 B2Parent of this continuation
US 2018/0107942 A1Published application
US 11,238,733 B2This patent

From the US filing history. Foreign family members aren’t listed.