System for building a vehicle-to-cloud real-time traffic map for autonomous driving vehicles (ADVS)

Patent metadata

Field	Value
Publication number	US-11269352-B2
Application number	US-201815916127-A
Country	US
Kind code	B2
Filing date	Mar 8, 2018
Priority date	Dec 15, 2017
Publication date	Mar 8, 2022
Grant date	Mar 8, 2022

Abstract

In one embodiment, a system monitors states of an autonomous driving vehicle (ADV) using a number of sensors mounted on the ADV. The system perceives a driving environment surrounding the ADV using at least a portion of the sensors. The system analyzes the states in view of the driving environment to determine a real-time traffic condition at a point in time. The system determines whether the real-time traffic condition of the driving environment matches at least a predetermined traffic condition. The system transmits data concerning the real-time traffic condition to a remote server over a network to allow the remote server to generate an updated map having real-time traffic information, in response to determining the real-time traffic condition is unknown. In response to receiving the updated map, the system plans and controls the ADV based on the updated map.

First claim

What is claimed is:

1. A computer-implemented method for operating an autonomous driving vehicle, the method comprising:
monitoring a state change of an autonomous driving vehicle (ADV) using a plurality of sensors mounted on the ADV;
detecting a driving environment surrounding the ADV using at least a portion of the sensors;
analyzing causes for the state change of the ADV in view of the driving environment surrounding the ADV to determine a real-time traffic condition of the driving environment at a point in time;
determining whether the real-time traffic condition of the driving environment is unknown by matching the real-time traffic condition with at least one of a plurality of predetermined traffic conditions, wherein the plurality of predetermined traffic conditions comprise slow traffic on highway moving less than a predetermined threshold, slow traffic on highway moving between about a predetermined range, road construction, and temporary detour;
in response to the real-time traffic condition being determined to be unknown, determining whether the real-time traffic condition is reported by more than a threshold number of vehicles, wherein the determining comprises comparing locations of the real-time traffic condition, similarity of driving environments, and an overlap of detection times from multiple reports of traffic conditions information;
in response to the real-time traffic condition being determined to be unknown, transmitting data concerning the real-time traffic condition of the driving environment to a remote server over a network, wherein the transmitted data includes the unknown real-time traffic condition including an ID of a reporting ADV, a location for the real-time traffic condition, a type of the real-time traffic condition, and a time of detection of the real-time traffic condition, wherein the transmitted data associated with the ADV are authenticated by the remote server, wherein the remote server is to modify a map section of a map associated with a road segment to generate and broadcast the modified map section an updated map to ADVs operating within a predetermined area associated with a portion of the updated map having real-time traffic information based on the transmitted unknown real-time traffic condition, the server communicating with the remote server via a map service application programming interface (API) to update the map; and
in response to receiving the updated map, planning and controlling the ADV based on real-time traffic information obtained from the updated map.

2. The method of claim 1 , wherein the remote server is configured to receive data concerning the unknown real-time traffic condition from at least one of a plurality of vehicles, examine weather condition and each of the received unknown real-time traffic conditions with traffic conditions information reported by other vehicles in a surrounding vicinity, determine whether a confidence score for each of the weather condition and the real-time traffic conditions is greater than a predetermined threshold, wherein the predetermined threshold is calculated based on a number of reporting vehicles, to update the map based on the unknown real-time traffic condition from the plurality of the vehicles via an application programming interface (API), and to transmit the updated map back to a set of the plurality of the vehicles interested in the real-time traffic conditions, the set of the plurality of the vehicles being within proximity of the weather condition and the real-time traffic conditions.

3. The method of claim 2 , wherein the map to be updated comprises one or more map layers to store real-time traffic conditions.

4. The method of claim 1 , further comprising prompting a user of the ADV to confirm a rerouting of the ADV based on the real-time traffic information obtained from the updated map.

5. The method of claim 1 , further comprising transmitting data concerning a disappearance of a real-time traffic condition of the driving environment to a remote server over a network wherein the transmitting, by the remote server, to generate an updated map having real-time traffic information, in response to determining the real-time traffic condition is known but disappearing, the disappearance of the real-time traffic condition include obstacles which were previously perceived, but no longer perceived, by the ADV, wherein map update communication protocols between the remote server and the ADVs are updated using trained predictive models based on driving statistics.

6. The method of claim 5 , wherein the remote server is configured to receive data concerning the disappearance of known real-time traffic condition from at least one of a plurality of vehicles, to update the map based on the disappearance of known real-time traffic condition from the plurality of the vehicles, and to transmit the updated map back to the plurality of the vehicles.

7. The method of claim 1 , wherein the state change includes stopping, slowing down, speeding up, and changing lanes.

8. A non-transitory machine-readable medium having instructions stored therein, which when executed by one or more processors, cause the one or more processors to perform operations, the operations comprising:
monitoring a state change of an autonomous driving vehicle (ADV) using a plurality of sensors mounted on the ADV;
detecting a driving environment surrounding the ADV using at least a portion of the sensors;
analyzing causes for the state change of the ADV in view of the driving environment surrounding the ADV to determine a real-time traffic condition of the driving environment at a point in time;
determining whether the real-time traffic condition of the driving environment is unknown by matching the real-time traffic condition with at least one of a plurality of predetermined traffic conditions, wherein the plurality of predetermined traffic conditions comprise slow traffic on highway moving less than a predetermined threshold, slow traffic on highway moving between about a predetermined range, road construction, and temporary detour;
in response to the real-time traffic condition being determined to be unknown, determining whether the real-time traffic condition is reported by more than a threshold number of vehicles, wherein the determining comprises comparing locations of the real-time traffic condition, similarity of driving environments, and an overlap of detection times from multiple reports of traffic conditions information;
in response to the real-time traffic condition being determined to be unknown, transmitting data concerning the real-time traffic condition of the driving environment to a remote server over a network, wherein the transmitted data includes the unknown real-time traffic condition including an ID of a reporting ADV, a location for the real-time traffic condition, a type of the real-time traffic condition, and a time of detection of the real-time traffic condition, wherein the transmitted data associated with the ADV are authenticated by the remote server, wherein the remote server is to modify a map section of a map associated with a road segment to generate and broadcast an updated map to ADVs operating within a predetermined area associated with a portion of the updated map having real-time traffic information based on the transmitted unknown real-time traffic condition, the server communicating with the remote server via a map service application programming interface (API) to update the map; and
in response to receiving the updated map, planning and controlling the ADV based on real-time traffic information obtained from the updated map.

9. The non-transitory machine-readable medium of claim 8 , wherein the remote server is configured to receive da

Assignees

• Baidu Usa Llc

Inventors

• Tao Jiaming
• Li Dong
• Jiang Yifei
• Zhang Liangliang
• Hu Jiangtao

Classifications

• G01C21/3878

  Hierarchical structures, e.g. layering · CPC title

• G01C21/3848

  Data obtained from both position sensors and additional sensors · CPC title

• G08G1/0112 Primary

  from the vehicle, e.g. floating car data [FCD] · CPC title

• G08G1/0145

  for active traffic flow control · CPC title

• G08G1/0969

  having a display in the form of a map · CPC title