Tracking on-road vehicles with sensors of different modalities

Patent metadata

Field	Value
Publication number	US-9255989-B2
Application number	US-201213556802-A
Country	US
Kind code	B2
Filing date	Jul 24, 2012
Priority date	Jul 24, 2012
Publication date	Feb 9, 2016
Grant date	Feb 9, 2016

Abstract

A vehicle system includes a first sensor and a second sensor, each having, respectively, different first and second modalities. A controller includes a processor configured to: receive a first sensor input from the first sensor and a second sensor input from the second sensor; detect, synchronously, first and second observations from, respectively, the first and second sensor inputs; project the detected first and second observations onto a graph network; associate the first and second observations with a target on the graph network, the target having a trajectory on the graph network; select either the first or the second observation as a best observation based on characteristics of the first and second sensors; and estimate a current position of the target by performing a prediction based on the best observation and a current timestamp.

First claim

The invention claimed is:

1. A controller for a vehicle, comprising a processor configured to:
receive a first sensor input from a first sensor and a second sensor input from a second sensor, the first and second sensors having, respectively, different first and second modalities and the first and second sensors being local to the vehicle;
detect, synchronously, first and second observations of a target from, respectively, the first and second sensor inputs, the first and second observations being from a perspective of the vehicle;
generate a graph network from a road map of a road network of an area in which the vehicle is present and an acquired position of the vehicle, wherein the graph network includes one dimensional lanes as links between nodes;
project the detected first and second observations of the target onto the graph network;
associate the first and second observations with the target on the graph network, the target having a trajectory on the graph network, wherein the trajectory of the target is based on one of the one dimensional lanes;
select either the first or the second observation of the target as a best observation of the target based on characteristics of the first and second sensors; and
estimate a current position of the target by performing a prediction based on the best observation and a current timestamp.

2. The controller according to claim 1 , wherein the first and second observations are associated with the target by generating a new target on the graph network when the first and second observations are not within a predefined distance of a currently tracked target.

3. The controller according to claim 1 , wherein the first sensor is a lidar sensor, and the second sensor is a radar sensor.

4. The controller according to claim 1 , wherein the current position of the target is estimated by performing a Kalman filter prediction process.

5. The controller according to claim 1 , wherein the characteristics of the first and second sensors include a time delay for processing the sensor data and an accuracy in detecting valid obstacles by the processing of the sensor data.

6. The controller according to claim 1 , wherein the target is tracked, by current position updates, through successive observations by the first and second sensors, and the target is removed from being tracked when no observation is observed for the target for a defined time period.

7. The controller according to claim 1 , wherein the detected first and second observations are projected onto the graph network by transforming respective coordinate systems of the first and second sensor inputs into a common coordinate system of the vehicle.

8. The controller according to claim 1 , wherein the controller stores a list of targets in a target list in a memory of the controller, and the target list is queried to associate observations with the targets.

9. The controller according to claim 1 , wherein synchronous detection of observations is restricted to points on or within a margin of error from a lane of the graph network.

10. The controller according to claim 1 , wherein tracking of targets is restricted to points on or within a margin of error from a lane of the graph network.

11. The controller according to claim 1 , wherein the detected first and second observations are projected onto the graph network by correcting the detected first and second observations to reflect a current timestamp, adjusting a position of the first and second observations on the graph network to account for a time delay between acquiring respective sensor data and projecting resulting observations onto the graph network.

12. A vehicle system, comprising:
a first sensor and a second sensor, each having, respectively, different first and second modalities, the first and second sensors being local to the vehicle; and
a controller including a processor configured to:
receive a first sensor input from the first sensor and a second sensor input from the second sensor;
detect, synchronously, first and second observations of a target from, respectively, the first and second sensor inputs, the first and second observations being from a perspective of the vehicle;
generate a graph network from a road map of a road network of an area in which the vehicle is present and an acquired position of the vehicle, wherein the graph network includes one dimensional lanes as links between nodes;
project the detected first and second observations onto the graph network;
associate the first and second observations with the target on the graph network, the target having a trajectory on the graph network, wherein the trajectory of the target is based on one of the one dimensional lanes;
select either the first or the second observation of the target as a best observation of the target based on characteristics of the first and second sensors; and
estimate a current position of the target by performing a prediction based on the best observation and a current timestamp.

13. A method, comprising:
receiving a first sensor input from a first sensor and a second sensor input from a second sensor, the first and second sensors having, respectively, different first and second modalities and the first and second sensors being local to a vehicle;
detecting, synchronously, first and second observations of a target from, respectively, the first and second sensor inputs, the first and second observations being from a perspective of the vehicle;
generating a graph network from a road map of a road network of an area in which the vehicle is present and an acquired position of the vehicle, wherein the graph network includes one dimensional lanes as links between nodes;
projecting the detected first and second observations onto a graph network;
associating the first and second observations with the target on the graph network, the target having a trajectory on the graph network, wherein the trajectory of the target is based on one of the one dimensional lanes;
selecting either the first or the second observation of the target as a best observation of the target based on characteristics of the first and second sensors; and
estimating a current position of the target by performing a prediction based on the best observation and a current timestamp.

Assignees

• Joshi Avdhut S
• James Michael R
• Samples Michael E
• Toyota Eng & Mfg North America

Inventors

• Joshi Avdhut S
• James Michael R
• Samples Michael E

Classifications

• G01S13/931 Primary

  of land vehicles · CPC title

• G05D2201/0213

  Physics · mapped topic

• G08G1/166

  for active traffic, e.g. moving vehicles, pedestrians, bikes · CPC title

• G05D1/0274

  using mapping information stored in a memory device (navigation using map-matching G01C21/30) · CPC title

• G05D1/0257

  using a radar (radar systems designed for anti-collision purposes between land vehicles or between land vehicle and fixed obstacles G01S13/931) · CPC title