Vehicle-platoons implementation under autonomous driving system designed for single vehicle

Patent metadata

Field	Value
Publication number	US-2020409391-A1
Application number	US-201916455332-A
Country	US
Kind code	A1
Filing date	Jun 27, 2019
Priority date	Jun 27, 2019
Publication date	Dec 31, 2020
Grant date	—

Abstract

A method, apparatus, and system for enabling platooning between two autonomous vehicles is disclosed. According to one embodiment, a second ADV receives a vehicle status and a first perception result of a first ADV over a vehicle-to-vehicle (V2V) link. The first perception result includes one or more obstacles perceived by the first ADV. A perception process is performed by the second ADV to perceive a driving environment associated with the second ADV, which generates a second perception result. The first perception result performed by the first ADV and the second perception result performed by the second ADV are merged to generate a third perception result. A trajectory is planned based on the vehicle status of the first ADV and the third perception result to cause the second ADV to follow the first ADV in a platoon manner.

First claim

What is claimed is:

1 . A computer-implemented method for operating an autonomous driving vehicle (ADV) to follow another ADV in a platoon manner, the method comprising:
receiving, at a second ADV, a vehicle status and a first perception result from a first ADV over a vehicle-to-vehicle (V2V) link, the first perception result including one or more obstacles perceived by the first ADV; performing a perception process at the second ADV to perceive a driving environment associated with the second ADV, generating a second perception result; merging the first perception result and the second perception result performed by the second ADV to generate a third perception result; and planning a second trajectory based on the vehicle status of the first ADV and the third perception result to cause the second ADV to follow the first ADV in a platoon manner.

2 . The method of claim 1 , further comprising:
receiving a path planning result from the first ADV over the V2V link, the path planning result including a first trajectory planned by the first ADV to autonomously drive the first ADV; and predicting movement of the first ADV based on the first trajectory provided by the path planning result of the first ADV.

3 . The method of claim 2 , further comprising generating a predicted trajectory based on the predicted movement of the first ADV, the predicted trajectory representing a trajectory of the first ADV predicted by the second ADV, wherein the second trajectory is planned in view of the predicted trajectory of the first ADV.

4 . The method of claim 1 , wherein the first perception result represents a front angle perception perceived from a front view of the first ADV.

5 . The method of claim 1 , wherein merging the first perception result with the second perception result comprises substituting the received vehicle status of the first ADV for perceived data associated with the first vehicle perceived in the second perception result of the second ADV.

6 . The method of claim 1 , further comprising reducing a minimum distance buffer between the second ADV and the first ADV to a predetermined platoon distance, wherein the second trajectory is planned in view of the predetermined platoon distance between the first ADV and the second ADV.

7 . The method of claim 1 , wherein the received vehicle status of the first ADV comprises one or more of: a localization of the first ADV in a global coordinate system, a speed of the first ADV, or a heading of the first ADV.

8 . The method of claim 1 , further comprising maintaining one or more minimum distance buffers between the second ADV and one or more identified obstacles relatively unchanged.

9 . The method of claim 1 , further comprising transmitting to a third ADV directly behind the second ADV a second vehicle status, the second perception result, and metadata describing the second trajectory of the second ADV, which are utilized by the third ADV to follow the second ADV in the platoon manner.

10 . 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:
receiving, at a second ADV, a vehicle status and a first perception result from a first ADV over a vehicle-to-vehicle (V2V) link, the first perception result including one or more obstacles perceived by the first ADV; performing a perception process at the second ADV to perceive a driving environment associated with the second ADV, generating a second perception result; merging the first perception result and the second perception result performed by the second ADV to generate a third perception result; and planning a second trajectory based on the vehicle status of the first ADV and the third perception result to cause the second ADV to follow the first ADV in a platoon manner.

11 . The machine-readable medium of claim 10 , wherein the operations further comprise:
receiving a path planning result from the first ADV over the V2V link, the path planning result including a first trajectory planned by the first ADV to autonomously drive the first ADV; and predicting movement of the first ADV based on the first trajectory provided by the path planning result of the first ADV.

12 . The machine-readable medium of claim 11 , wherein the operations further comprise generating a predicted trajectory based on the predicted movement of the first ADV, the predicted trajectory representing a trajectory of the first ADV predicted by the second ADV, wherein the second trajectory is planned in view of the predicted trajectory of the first ADV.

13 . The machine-readable medium of claim 10 , wherein the first perception result represents a front angle perception perceived from a front view of the first ADV.

14 . The machine-readable medium of claim 10 , wherein merging the first perception result with the second perception result comprises substituting the received vehicle status of the first ADV for perceived data associated with the first vehicle perceived in the second perception result of the second ADV.

15 . The machine-readable medium of claim 10 , wherein the operations further comprise reducing a minimum distance buffer between the second ADV and the first ADV to a predetermined platoon distance, wherein the second trajectory is planned in view of the predetermined platoon distance between the first ADV and the second ADV.

16 . The machine-readable medium of claim 10 , wherein the received vehicle status of the first ADV comprises one or more of: a localization of the first ADV in a global coordinate system, a speed of the first ADV, or a heading of the first ADV.

17 . The machine-readable medium of claim 10 , wherein the operations further comprise maintaining one or more minimum distance buffers between the second ADV and one or more identified obstacles relatively unchanged.

18 . The machine-readable medium of claim 10 , wherein the operations further comprise transmitting to a third ADV directly behind the second ADV a second vehicle status, the second perception result, and metadata describing the second trajectory of the second ADV, which are utilized by the third ADV to follow the second ADV in the platoon manner.

19 . A data processing system, comprising:
a processor; and a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations, the operations including
receiving, at a second ADV, a vehicle status and a first perception result from a first ADV over a vehicle-to-vehicle (V2V) link, the first perception result including one or more obstacles perceived by the first ADV,
performing a perception process at the second ADV to perceive a driving environment associated with the second ADV, generating a second perception result,
merging the first perception result and the second perception result performed by the second ADV to generate a third perception result, and
planning a second trajectory based on the vehicle status of the first ADV and the third perception result to cause the second ADV to follow the first ADV in a platoon manner.

20 . The system of claim 19 , wherein the operations further comprise:
receiving a path planning result from the first ADV over the V2V link, the path planning result including a first trajectory planned by the first ADV to autonomously drive the first ADV; and predicting movement of the first ADV based on the first trajectory provided by the path planning

Assignees

• Baidu Usa Llc

Inventors

• Zhu Fan

Classifications

• H04W4/46

  for vehicle-to-vehicle communication [V2V] · CPC title

• G08G1/22

  Platooning, i.e. convoy of communicating vehicles · CPC title

• B60W30/165

  Automatically following the path of a preceding lead vehicle, e.g. "electronic tow-bar" · CPC title

• B60Y2300/10

  Path keeping · CPC title

• B60W60/001 Primary

  Planning or execution of driving tasks · CPC title