System and methods to support autonomous vehicles via environmental perception and sensor calibration and verification

Patent metadata

Field	Value
Publication number	US-10534370-B2
Application number	US-201515301600-A
Country	US
Kind code	B2
Filing date	Apr 2, 2015
Priority date	Apr 4, 2014
Publication date	Jan 14, 2020
Grant date	Jan 14, 2020

Abstract

An autonomous vehicle support system, including a lighting network ( 100 ) having, a plurality of light units ( 106 - 1, . . . , 106 -N) wherein at least one light unit includes at least one sensor type ( 110 - 1, . . . , 110 -N), and a centralized or distributed controller ( 102, 105 - 1, . . . , 105 -N), wherein a first light unit ( 106 - 1, . . . , 106 -N) receives sensor data from its sensor type ( 110 - 1, . . . , 110 -N), wherein the controller ( 105 - 1, . . . , 105 - 1 ) forms a local environmental perception of an area local to the first light unit ( 106 - 1, . . . , 106 -N), using the received sensor data from light unit, and receives sensor measurement data from an autonomous vehicle relating to at least a portion of the area, and cross-validates the local environmental perception of the area and the sensor measurement data from the autonomous vehicle.

First claim

What is claimed is:

1. A self-driving autonomous vehicle sensor support system, comprising:
a lighting network having:
a plurality of light units wherein at least one light unit includes at least one sensor; and
a controller, wherein the controller,
forms, based on data from the at least one sensor, a sensor map of an area local to one or more of the plurality of light units;
receives sensor measurement data from an autonomous vehicle relating to at least a portion of the area,
determines a difference in sensor data between the sensor map of the area and the sensor measurement data from the autonomous vehicle,
cross-validates the portion of the area of the sensor map and sensor measurement data and provide the difference in sensor data to the autonomous vehicle, and
determines an event based on the difference in the sensor map and the sensor measurement data from the autonomous vehicle, wherein the event is evaluated based upon sensor data from the lighting network that is outside a sensor detection range of the autonomous vehicle; and
communicates an action related to the event or the cross validated portion of area to the autonomous vehicle, wherein the action is an alert/emergency action or an update/calibration action to the vehicle measurement system.

2. The self-driving autonomous vehicle sensor support system of claim 1 , wherein the controller forms the sensor map, using received sensor data from a first light unit and at least one of a second light unit, connected devices and resource servers that obtain information from additional sources.

3. The self-driving autonomous vehicle sensor support system of claim 2 , wherein the controller determines a ground truth, wherein the ground truth is determined by continuously monitoring the sensor data from the lighting units of the road condition and/or other devices and resource servers.

4. The self-driving autonomous vehicle sensor support system of claim 1 , wherein the cross-validation includes comparing the light unit's sensor map of the area and the sensor measurement data from the autonomous vehicle.

5. The self-driving autonomous vehicle sensor support system of claim 1 , wherein the system transmits cross-validation sensor information to the autonomous vehicle or broadcasts cross-validation sensor information to any other autonomous vehicles.

6. The self-driving autonomous vehicle sensor validation system of claim 1 , wherein the controller stores changes to the perception, when sensors send new sensor data, to update the sensor map and form a history of perceptions.

7. The self-driving autonomous vehicle sensor support system of claim 6 , wherein the controller generates a prioritized list of events relating to the changes to the perception, and determines which events should be sent to the autonomous vehicle or broadcasted to other autonomous vehicles.

8. A method of supporting a self-driving autonomous vehicle's sensor system using a lighting network, the lighting network having a plurality of light units wherein at least one light unit includes at least one sensor type and a centralized or distributed controller; in communication with the light units, the method comprising the steps of:
receiving, in a first light unit, sensor data from a first sensor;
forming, in the controller and based on data from the at least one sensor, a local environmental sensor map of an area local to one or more of the plurality of light units;
receiving sensor measurement data from an autonomous vehicle relating to at least a portion of the area;
determining a difference in sensor data between the local environmental sensor map and the sensor measurement data from the autonomous vehicle;
cross-validating the portion of the area of the local environmental sensor map and the sensor measurement data; and
determining an event based on the difference in sensor data, wherein the event is evaluated based upon sensor data from the lighting network that is outside a sensor detection range of the autonomous vehicle; and
communicating and action based on the event or cross-validated the portion of the area, wherein the action is an alert/emergency action or an update/calibration action to the vehicle measurement system.

9. The method of claim 8 , further including the step of, determining, in the controller a ground truth, wherein the ground truth is determined by continuously monitoring the sensor data from the lighting units of the road condition and/or other devices and resource servers.

10. The method of claim 8 , wherein the step of cross-validating includes comparing the light unit's sensor map of the area and the sensor measurement data from the autonomous vehicle.

11. The method of claim 8 , further including the step of transmitting cross-validation sensor information to the autonomous vehicle or broadcasting cross-validation sensor information to any autonomous vehicle in range.

12. The method of claim 8 , further including the step, changing the sensor map, in the controller when sensor send new sensor data, and updating the sensor map and forming a history of sensor maps.

13. The method of claim 12 , wherein the step of changing the sensor map includes generating a prioritized list of events relating to the changes to the sensor map, and determining which events should be sent to the autonomous vehicle or broadcasted to other autonomous vehicles or sent to third parties.

14. The method of claim 1 , wherein the event includes one or more of traffic or weather conditions, detection of a road emergency situation/safety issue, and detection of vehicle malfunctions.

Assignees

• Signify Holding Bv

Inventors

• Cavalcanti Dave Alberto Tavares
• Szczodrak Marcin Krzysztof
• De Oliveira Talmai Brandão
• Yang Yong

Classifications

• B60W2555/00

  Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00 · CPC title

• G08G1/0116 Primary

  from roadside infrastructure, e.g. beacons · CPC title

• G08G1/091

  Traffic information broadcasting (broadcasting communication H04H) · CPC title

• H05B47/19

  via wireless transmission · CPC title

• G08G1/0141

  for traffic information dissemination · CPC title