TRAVELING ENVIRONMENT RECOGNITION DEVICE AND METHOD

• US 20120053755A1
• Filed: 08/25/2011
• Published: 03/01/2012
• Est. Priority Date: 08/30/2010
• Status: Active Grant

• Current Assignee: DENSO Corporation
• Original Assignee: DENSO Corporation
• Inventors: TAKAGI, Kiyokazu
• Granted Patent: US 8,744,744 B2
• Time in Patent Office: Days
• US Class Current: 701/1
• CPC Class Codes: B60W 2520/06 Direction of travel
• CPC Class Codes: B60W 2552/20 Road profile, i.e. the change in elevation or curvature of a plurality of continuous road segments
• CPC Class Codes: B60W 2554/00 Input parameters relating to objects
• CPC Class Codes: B60W 2556/50 of positioning data, e.g. GPS [Global Positioning System] data
• CPC Class Codes: B60W 2556/65 Data transmitted between vehicles
• CPC Class Codes: B60W 40/04 Traffic conditions
• CPC Class Codes: B60W 40/06 Road conditions
• CPC Class Codes: G01S 13/89 for mapping or imaging
• CPC Class Codes: G01S 13/931 of land vehicles
• CPC Class Codes: G01S 17/89 for mapping or imaging
• CPC Class Codes: G01S 17/931 of land vehicles
• CPC Class Codes: G01S 2013/9323 Alternative operation using light waves
• CPC Class Codes: G01S 2013/9324 Alternative operation using ultrasonic waves
• CPC Class Codes: G01S 7/4808 Evaluating distance, position or velocity data

Abstract

A traveling environment recognition device capable of accurately recognizing a traveling environment of a vehicle. An occupancy grid map that stores an occupancy probability of each obstacle to traveling of the own vehicle for each cell of the occupancy grid map is generated, and the occupancy probability for each cell is updated according to Bayesian inference. More specifically, for each cell of the occupancy grid map, the occupancy probability calculated from information from a radar device, the occupancy probability calculated from information from a communication device, and the occupancy probability calculated from information from a storage device that stores map data are blended to provide an occupancy probability of the obstacles to traveling of the own vehicle, which leads to more accurate traveling environment recognition.

Claims

1. A traveling environment recognition device that recognizes a traveling environment of one'"'"'s own vehicle, the device comprising:

own vehicle position determining means for determining a position and a traveling direction of the own vehicle in an absolute coordinate system with its origin at an arbitrary point on the basis of information from one or more sensors for detecting a quantity of motion of the own vehicle; and

occupancy grid map generating means for dividing the absolute coordinate system into a grid of equal cells, and generating an occupancy grid map that stores an occupancy probability of each obstacle to traveling of the own vehicle for each cell of the grid, and updating the occupancy probability according to Bayesian inference, wherein the occupancy grid map generating means comprises;

object occupancy probability calculating means for calculating, on the basis of information from a radar device that detects a forward object of the own vehicle, which is an obstacle, the occupancy probability of the forward object for each cell of the occupancy grid map;

other vehicle occupancy probability calculating means for calculating, on the basis of information from a communication device that receives positional information transmitted from another vehicle around the own vehicle, which is an obstacle, the occupancy probability of the other vehicle for each cell of the occupancy grid map;

traffic lane line occupancy probability calculating means for calculating, on the basis of information from a storage device that stores map data which allows a position to be specified of a traffic lane line which is an obstacle, the occupancy probability of the traffic lane line for each cell of the occupancy grid map; and

occupancy probability blending means for blending, for each cell of the occupancy grid map, the occupancy probability calculated by the object occupancy probability calculating means, the occupancy probability calculated by the other vehicle occupancy probability calculating means, and the occupancy probability calculated by the traffic lane line occupancy probability calculating means to provide a blended occupancy probability of the obstacles to traveling of the own vehicle.

2. The device of claim 1, wherein the occupancy probability blending means blends the occupancy probability calculated by the object occupancy probability calculating means, the occupancy probability calculated by the other vehicle occupancy probability calculating means, and the occupancy probability calculated by the traffic lane line occupancy probability calculating means so as to minimize an influence degree of the occupancy probability calculated by the traffic lane line occupancy probability calculating means.

3. The device of claim 1, wherein the radar device is capable of detecting a three-dimensional object as the forward object,

the object occupancy probability calculating means calculates the occupancy probability of the three-dimensional object according to a sensor model that defines the occupancy probability of the three-dimensional object as a function of a direct distance from a detection wave emitting point of the radar device along a straight line through the detection wave emitting point and an observed point of the three-dimensional object.

4. The device of claim 3, wherein when the radar device detects two three-dimensional objects at their observed points along a straight line through the two observed points and the detection wave emitting point of the radar device, the object occupancy probability calculating means calculates the occupancy probability of the two three-dimensional objects according to a sensor model that defines the occupancy probability of the three-dimensional objects as a function of a direct distance from the detection wave emitting point of the radar device along the straight line such that the occupancy probability at the observed point closer to the own vehicle is set smaller than the occupancy probability at the observed point further away from the own vehicle.

5. The device of claim 3, wherein the radar device is also capable of detecting a traffic lane line as the forward object,

the object occupancy probability calculating means calculates the occupancy probability of the traffic lane line according to a sensor model such that the occupancy probability of the traffic lane line is set smaller than the occupancy probability of the three-dimensional object.

6. The device of claim 1, wherein the communication device receives information about a position and a traveling direction of the other vehicle as the positional information,

the other vehicle occupancy probability calculating means calculates the occupancy probability of the other vehicle according to a sensor model that defines a correspondence relation between a position with reference to a contour of the other vehicle and the occupancy probability of the other vehicle.

7. The device of claim 1, wherein the traffic lane line occupancy probability calculating means calculates the occupancy probability of the traffic lane line according to a sensor model such that that the occupancy probability for the cell that intersects with one of two adjacent traffic lane lines is set larger than 0.5 and the occupancy probability for the cell that is included in a road-width portion of the road on which the own vehicle is traveling is set smaller than 0.5, the road-width portion being between the two adjacent traffic lane lines and not including the two lane lines.

8. The device of claim 1, wherein the occupancy probability blending means calculates, for each cell of the occupancy grid map, a weighted average of the occupancy probability calculated by the object occupancy probability calculating means, the occupancy probability calculated by the other vehicle occupancy probability calculating means, and the occupancy probability calculated by the traffic lane line occupancy probability calculating means.

9. The device of claim 8, wherein weights used in calculating the weighted average are such that a weight for the occupancy probability calculated by the object occupancy probability calculating means is larger than a weight for the occupancy probability calculated by the other vehicle occupancy probability calculating means, and the weight for the occupancy probability calculated by the other vehicle occupancy probability calculating means is larger than a weight for the occupancy probability calculated by the traffic lane line occupancy probability calculating means.

10. The device of claim 1, wherein the radar device is a laser radar.

11. The device of claim 1, wherein the origin of the absolute coordinate system is set to a position of the own vehicle at a certain time.

12. The device of claim 1, further comprising:

low-resolution occupancy grid map generating means for grouping a predetermined number of mutually adjacent cells of the grid into a larger cell of a low-resolution grid over the grid, and generating a low-resolution occupancy grid map that stores a low-resolution occupancy probability of each obstacle to traveling of the own vehicle for each cell of the low-resolution grid, and updating the low-resolution occupancy probability according to the Bayesian inference, wherein the low-resolution occupancy grid map generating means comprises;

low-resolution object occupancy probability calculating means for calculating, on the basis of the information from the radar device, the low-resolution occupancy probability of the forward object for each cell of the low-resolution occupancy grid map;

low-resolution other vehicle occupancy probability calculating means for calculating, on the basis of the information from the communication device, the low-resolution occupancy probability of the other vehicle for each cell of the low-resolution occupancy grid map;

low-resolution traffic lane line occupancy probability calculating means for calculating, on the basis of the information from the storage device that stores the map data, the low-resolution occupancy probability of the traffic lane line for each cell of the low-resolution occupancy grid map; and

low-resolution occupancy probability blending means for blending, for each cell of the low-resolution occupancy grid map, the low-resolution occupancy probability calculated by the low-resolution object occupancy probability calculating means, the low-resolution occupancy probability calculated by the low-resolution other vehicle occupancy probability calculating means, and the low-resolution occupancy probability calculated by the low-resolution traffic lane line occupancy probability calculating means to provide a low-resolution blended occupancy probability of the obstacles to traveling of the own vehicle,

the device still further comprising;

low-resolution grid cell selecting means for selecting, from the equal larger cells of the low-resolution occupancy grid map, a cell that has the low-resolution blended occupancy probability of the obstacles calculated by the low-resolution occupancy probability blending means that is larger than a predetermined threshold,

wherein the object occupancy probability calculating means calculates, on the basis of the information from the radar device, the occupancy probability of the forward object for each cell of each larger cell of the low-resolution occupancy grid map that is selected by the low-resolution grid cell selecting means,

the other vehicle occupancy probability calculating means calculates, on the basis of the information from the communication device, the occupancy probability of the other vehicle for each cell of each larger cell of the low-resolution occupancy grid map that is selected by the low-resolution grid cell selecting means;

the traffic lane line occupancy probability calculating means calculates, on the basis of the information from the storage device that stores map data, the occupancy probability of the traffic lane line for each cell of each larger cell of the low-resolution occupancy grid map that is selected by the low-resolution grid cell selecting means; and

the occupancy probability blending means blends, for each cell of each larger cell of the low-resolution occupancy grid map that is selected by the low-resolution grid cell selecting means, the occupancy probability calculated by the object occupancy probability calculating means, the occupancy probability calculated by the other vehicle occupancy probability calculating means, and the occupancy probability calculated by the traffic lane line occupancy probability calculating means to provide the blended occupancy probability of the obstacles to traveling of the own vehicle.

13. A traveling environment recognition device that recognizes a traveling environment of one'"'"'s own vehicle, the device comprising:

own vehicle position determining means for determining a position and a traveling direction of the own vehicle in an absolute coordinate system with its origin at an arbitrary point on the basis of information from one or more sensors for detecting a quantity of motion of the own vehicle; and

occupancy grid map generating means for dividing the absolute coordinate system into a grid of equal cells, and generating an occupancy grid map that stores an occupancy probability of each obstacle to traveling of the own vehicle for each cell of the grid, and updating the occupancy probability according to Bayesian inference, wherein the occupancy grid map generating means comprises;

object occupancy probability calculating means for calculating, on the basis of information from a radar device that detects a forward object of the own vehicle, which is an obstacle, the occupancy probability of the forward object for each cell of the occupancy grid map;

other vehicle occupancy probability calculating means for calculating, on the basis of information from a communication device that receives positional information transmitted from another vehicle around the own vehicle, which is an obstacle, the occupancy probability of the other vehicle for each cell of the occupancy grid map; and

occupancy probability blending means for blending, for each cell of the occupancy grid map, the occupancy probability calculated by the object occupancy probability calculating means, and the occupancy probability calculated by the other vehicle occupancy probability calculating means to provide a blended occupancy probability of the obstacles to traveling of the own vehicle.

14. A traveling environment recognition device that recognizes a traveling environment of one'"'"'s own vehicle, the device comprising:

own vehicle position determining means for determining a position and a traveling direction of the own vehicle in an absolute coordinate system with its origin at an arbitrary point on the basis of information from one or more sensors for detecting a quantity of motion of the own vehicle; and

occupancy grid map generating means for dividing the absolute coordinate system into a grid of equal cells, and generating an occupancy grid map that stores an occupancy probability of each obstacle to traveling of the own vehicle for each cell of the grid, and updating the occupancy probability according to Bayesian inference, wherein the occupancy grid map generating means comprises;

object occupancy probability calculating means for calculating, on the basis of information from a radar device that detects a forward object of the own vehicle, which is an obstacle, the occupancy probability of the forward object for each cell of the occupancy grid map;

traffic lane line occupancy probability calculating means for calculating, on the basis of information from a storage device that stores map data which allows a position to be specified of a traffic lane line which is an obstacle, the occupancy probability of the traffic lane line for each cell of the occupancy grid map; and

occupancy probability blending means for blending, for each cell of the occupancy grid map, the occupancy probability calculated by the object occupancy probability calculating means, and the occupancy probability calculated by the traffic lane line occupancy probability calculating means to provide a blended occupancy probability of the obstacles to traveling of the own vehicle.

15. A method of recognizing a traveling environment of one'"'"'s own vehicle, the method comprising the steps of:

determining a position and a traveling direction of the own vehicle in an absolute coordinate system with its origin at an arbitrary point on the basis of information from one or more sensors for detecting a quantity of motion of the own vehicle; and

dividing the absolute coordinate system into a grid of equal cells, and generating an occupancy grid map that stores an occupancy probability of each obstacle to traveling of the own vehicle for each cell of the grid, and updating the occupancy probability according to Bayesian inference, wherein the occupancy grid map generating step comprises;

calculating, on the basis of information from a radar device that detects a forward object of the own vehicle, which is an obstacle, the occupancy probability of the forward object for each cell of the occupancy grid map;

calculating, on the basis of information from a communication device that receives positional information transmitted from another vehicle around the own vehicle, which is an obstacle, the occupancy probability of the other vehicle for each cell of the occupancy grid map;

calculating, on the basis of information from a storage device that stores map data which allows a position to be specified of a traffic lane line which is an obstacle, the occupancy probability of the traffic lane line for each cell of the occupancy grid map; and

blending, for each cell of the occupancy grid map, the occupancy probability calculated in the object occupancy probability calculating step, the occupancy probability calculated in the other vehicle occupancy probability calculating step, and the occupancy probability calculated in the traffic lane line occupancy probability calculating step to provide a blended occupancy probability of the obstacles to traveling of the own vehicle.

16. The method of claim 15, wherein the occupancy probability blending step includes calculating, for each cell of the occupancy grid map, a weighted average of the occupancy probability calculated in the object occupancy probability calculating step, the occupancy probability calculated in the other vehicle occupancy probability calculating step, and the occupancy probability calculated in the traffic lane line occupancy probability calculating step.