Minimizing incorrect sensor data associations for autonomous vehicles

Patent metadata

Field	Value
Publication number	US-10054678-B2
Application number	US-201514813429-A
Country	US
Kind code	B2
Filing date	Jul 30, 2015
Priority date	Jul 30, 2015
Publication date	Aug 21, 2018
Grant date	Aug 21, 2018

Abstract

Minimizing incorrect associations of sensor data for an autonomous vehicle are described. A driving environment of the autonomous vehicle includes a stationary object and a dynamic object. Such objects can be detected by radar sensors and/or lidar sensors. In one example, a history of radar observation can be used to minimize incorrect sensor data associations. In such case, the location of a stationary object in the driving environment can be determined. When a dynamic object passes by the stationary object, lidar data of the dynamic object is prevented from being associated with radar data obtained substantially at the determined location of the stationary object. In another example, identifiers assigned to radar data can be used to minimize incorrect sensor data associations. In such case, lidar data of an object can be associated with radar data having a particular identifier.

First claim

What is claimed is:

1. A method of minimizing incorrect associations of sensor data for an autonomous vehicle, the autonomous vehicle operating in a driving environment, a stationary object and a dynamic object being located in a forward portion of the driving environment, the method comprising:
acquiring, using at least a radar sensor, a first sensor observation of the forward portion of the driving environment in which the dynamic object is located away from the stationary object, the first sensor observation including radar data for the dynamic object and the stationary object, acquiring the first sensor observation including:
transmitting one or more radar signals into the forward portion of the driving environment;
receiving one or more reflections of the one or more transmitted radar signals, whereby the one or more radar signals are reflected off of objects in the driving environment;

determining the location of the stationary object in the driving environment based on the radar data;
acquiring, using at least the radar sensor and a lidar sensor, a second sensor observation of the forward portion of the driving environment in which the dynamic object is located substantially near the determined location of the stationary object, the second sensor observation including radar data and lidar data for the dynamic object and the stationary object, the second sensor observation being subsequent to the first sensor observation, acquiring the second sensor observation including:
transmitting one or more radar signals into the forward portion of the driving environment;
receiving one or more reflections of the one or more transmitted radar signals, whereby the one or more radar signals are reflected off of objects in the driving environment;
transmitting one or more lidar signals into the forward portion of the driving environment;
receiving one or more reflections of the one or more transmitted lidar signals, whereby the one or more lidar signals are reflected off of objects in the driving environment; and

for the second sensor observation, preventing the lidar data of the dynamic object from being associated with radar data obtained substantially at the determined location of the stationary object.

2. The method of claim 1 , wherein acquiring a first sensor observation of the forward portion of the driving environment in which the dynamic object is located away from the stationary object includes:
acquiring a plurality of sensor observations of the forward portion of the driving environment in which the dynamic object is located away from the stationary object; wherein the plurality of sensor observations includes radar data for the dynamic object and the stationary object; and
for the plurality of sensor observations, determining the location of the stationary object in the driving environment based at least in part on the radar data.

3. The method of claim 1 , wherein the radar data includes speed data and location data, and wherein preventing the lidar data of the dynamic object from being associated with radar data obtained substantially at the determined location of the stationary object includes preventing the lidar data of the dynamic object from being associated with at least the speed data from the radar data obtained near the determined location of the stationary object.

4. The method of claim 1 , further including:
determining a driving maneuver for the autonomous vehicle based at least partially on the lidar data of the dynamic object that is prevented from being associated with radar data obtained substantially at the determined location of the stationary object.

5. A method of minimizing incorrect associations of sensor data for an autonomous vehicle, the autonomous vehicle operating in a driving environment, a stationary object and a dynamic object being located in a forward portion of the driving environment, the method comprising:
acquiring a first sensor observation of the forward portion of the driving environment in which the dynamic object is located away from the stationary object, the first sensor observation including radar data for the dynamic object and the stationary object;
determining the location of the stationary object in the driving environment based on the radar data;
acquiring a second sensor observation of the forward portion of the driving environment in which the dynamic object is located substantially near the determined location of the stationary object, the second sensor observation including radar data and lidar data for the dynamic object and the stationary object, the second sensor observation being subsequent to the first sensor observation;
for the second sensor observation, preventing the lidar data of the dynamic object from being associated with radar data obtained substantially at the determined location of the stationary object;
determining a driving maneuver for the autonomous vehicle based at least partially on the lidar data of the dynamic object that is prevented from being associated with radar data obtained substantially at the determined location of the stationary object; and
causing the autonomous vehicle to implement the determined driving maneuver.

6. The method of claim 5 , wherein acquiring the first sensor observation of the forward portion of the driving environment is performed using at least a radar sensor, and wherein acquiring the second sensor observation of the forward portion of the driving environment is performed using at least a radar sensor and a lidar sensor.

7. A system for minimizing incorrect associations of sensor data for an autonomous vehicle, the autonomous vehicle operating in a driving environment, a stationary object and a dynamic object being located in a forward portion of the driving environment, the system comprising:
a sensor system including a radar sensor and a lidar sensor, the sensor system being configured to:
acquire, using at least the radar sensor, a first sensor observation of a forward portion of the driving environment in which the dynamic object is located away from the stationary object, the first sensor observation including radar data for the dynamic object and the stationary object, acquiring the first sensor observation including:
transmitting one or more radar signals into the forward portion of the driving environment;
receiving one or more reflections of the one or more transmitted radar signals, whereby the one or more radar signals are reflected off of objects in the driving environment; and

acquire, using at least the radar sensor and the lidar sensor, a second sensor observation of the forward portion of the driving environment in which the dynamic object is located substantially near the stationary object, the second sensor observation including radar data and lidar data for the dynamic object and the stationary object, the second sensor observation being subsequent to the first sensor observation, acquiring the second sensor observation including:
transmitting one or more radar signals into the forward portion of the driving environment;
receiving one or more reflections of the one or more transmitted radar signals, whereby the one or more radar signals are reflected off of objects in the driving environment;

transmitting one or more lidar signals into the forward portion of the driving environment;
receiving one or more reflections of the one or more transmitted lidar signals, whereby the one or more lidar signals are reflected off of objects in the driving environment; and

a processor operatively connected to the sensor system, the processor being programmed to initiate executable operations including:
for the first sensor observation, determining the location of the stationary object in the driving environment based on the radar

Assignees

• Toyota Eng & Mfg North America

Inventors

• Mei Xue
• Nagasaka Naoki
• Okumura Bunyo

Classifications

• G01S13/58

  Velocity or trajectory determination systems; Sense-of-movement determination systems · CPC title

• G01S17/931

  of land vehicles · CPC title

• B60W30/0956

  the prediction being responsive to traffic or environmental parameters · CPC title

• G01S13/42

  Simultaneous measurement of distance and other co-ordinates (indirect measurement G01S13/46) · CPC title

• G01S13/865 Primary

  Combination of radar systems with lidar systems · CPC title