COLLISION PROBABILITY CALCULATION APPARATUS FOR VEHICLE AND COLLISION AVOIDANCE SYSTEM USING THE SAME

• US 20120283895A1
• Filed: 05/01/2012
• Published: 11/08/2012
• Est. Priority Date: 05/02/2011
• Status: Active Grant

• Current Assignee: DENSO Corporation
• Original Assignee: DENSO Corporation
• Inventors: Noda, Kazuhiro
• Granted Patent: US 8,838,372 B2
• Time in Patent Office: Days
• US Class Current: 701/1
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2520/10 Longitudinal speed
• CPC Class Codes: B60W 30/09 Taking automatic action to avoid collision, e.g. braking and steering
• CPC Class Codes: B60W 30/0953 the prediction being responsive to vehicle dynamic parameters
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: B60W 30/12 Lane keeping
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes

Abstract

A collision probability calculation apparatus capable of accurately calculating a collision probability that one'"'"'s own vehicle will collide with an object around the own vehicle (referred to as a nearby object). In the apparatus, a position of the nearby object and a traveling speed and a traveling direction of the own vehicle are acquired. A collision probability map is generated on the basis of the traveling speed and traveling direction of the own vehicle. A width of a traveling lane of the own vehicle is acquired and the map is corrected in response to the width of the traveling lane. Thereafter, a collision probability associated with the position of the nearby object is corrected in response to the position of the nearby object. The corrected collision probability is outputted as a more accurate collision probability that the own vehicle will collide with the nearby object.

Claims

1. A collision probability calculation apparatus for a vehicle, comprising:

object information acquisition means for acquiring object information including a position of an object around one'"'"'s own vehicle, the object being referred to as a nearby object;

vehicle state information acquisition means for acquiring vehicle state information including a traveling speed and a traveling direction of the own vehicle;

collision probability map generation means for generating a collision probability map that indicates a collision probability that the own vehicle will collide with a nearby object at each point of a region around the own vehicle, on the basis of the acquired vehicle state information;

lane width acquisition means for acquiring a width of a traffic lane in which the own vehicle is traveling, the traffic lane being referred to as a traveling lane;

collision probability distribution correction means for correcting a collision probability distribution in the collision probability map to produce a corrected collision probability map, in response to the acquired width of the traveling lane;

collision probability correction means for reading a collision probability associated with the position of the nearby object from the corrected collision probability map and correcting the read collision probability in response to the acquired object information; and

collision probability output means for outputting the collision probability corrected by the collision probability correction means as a more accurate collision probability that the own vehicle will collide with the nearby object.

2. The apparatus of claim 1, wherein

the collision probability distribution correction means sets a width of a region on which the collision probability is constant (referred to as a constant collision probability region) so that the width of the constant collision probability region decreases with a decreasing width of the traveling lane.

3. The apparatus of claim 1, further comprising:

captured image acquisition means for acquiring a captured image of surroundings of the own vehicle;

lane-edge detection means for detecting an edge of the traveling lane of the own vehicle from the captured image;

surrounding-region extraction means for extracting a region surrounding and in the vicinity of the nearby object from the captured image; and

lane-edge presence determination means for determining whether or not there exists an edge of the traveling lane of the own vehicle in the extracted region,

wherein the collision probability correction means corrects the read collision probability to a higher value when it is determined by the lane-edge presence determination means that there exists an edge of the traveling lane of the own vehicle in the extracted region in the vicinity of the nearby object.

4. The apparatus of claim 3, further comprising:

vulnerable road user determination means for determining whether or not the nearby object is a vulnerable road user that is likely to be harmed by the own vehicle,

wherein the collision probability correction means corrects the read collision probability to a first higher value when it is determined by the lane-edge presence determination means that there exists an edge of the traveling lane of the own vehicle in the extracted region in the vicinity of the nearby object and it is determined by the vulnerable road user determination means that the nearby object is a vulnerable road user that is likely to be harmed by the own vehicle and corrects the read collision probability to a second higher value lower than the first higher value when it is determined by the lane-edge presence determination means that there exists an edge of the traveling lane of the own vehicle in the extracted region in the vicinity of the nearby object and it is determined by the vulnerable road user determination means that the nearby object is not a vulnerable road user that is likely to be harmed by the own vehicle.

5. The apparatus of claim 3, further comprising:

movement speed detection means for detecting a movement speed of the nearby object, the movement speed of the nearby object being included in the object information of the nearby object,

wherein the surrounding-region extraction means alters dimensions of a region to be extracted from the captured image (referred to as an extraction region) as a function of the movement speed of the nearby object.

6. The apparatus of claim 1, further comprising:

vehicle control means for controlling the own vehicle to avoid a possible collision with the nearby object in response to the collision probability outputted by the collision probability output means.

7. The apparatus of claim 6, further comprising:

delay control means for delaying the start of the collision avoidance control in response to the collision probability outputted by the collision probability output means.

8. The apparatus of claim 3, wherein the lane width acquisition means acquires the width of the traveling lane on the basis of locations of edges detected by the lane-edge detection means.

9. A collision avoidance system for a vehicle, comprising:

a collision probability calculation apparatus for a vehicle, comprising;

object information acquisition means for acquiring object information including a position of an object around one'"'"'s own vehicle, the object being referred to as a nearby object;

vehicle state information acquisition means for acquiring vehicle state information including a traveling speed and a traveling direction of the own vehicle;

collision probability map generation means for generating a collision probability map that indicates a collision probability that the own vehicle will collide with a nearby object at each point of a region around the own vehicle, on the basis of the acquired vehicle state information;

lane width acquisition means for acquiring a width of a traffic lane in which the own vehicle is traveling, the traffic lane being referred to as a traveling lane;

collision probability distribution correction means for correcting a collision probability distribution in the collision probability map to produce a corrected collision probability map, in response to the acquired width of the traveling lane;

collision probability correction means for reading a collision probability associated with the position of the nearby object from the corrected collision probability map and correcting the read collision probability in response to the acquired object information;

collision probability output means for outputting the collision probability corrected by the collision probability correction means as a more accurate collision probability that the own vehicle will collide with the nearby object, and vehicle control means for controlling the own vehicle to avoid a possible collision with the nearby object in response to the collision probability outputted by the collision probability output means, wherein the vehicle control means controls the own vehicle by outputting an instruction for collision avoidance control in response to the collision probability outputted by the collision probability output means;

a nearby-object detector that detects at least a position of an object around the own vehicle (referred to as a nearby object) and outputs the detected position of the nearby object to the apparatus;

a vehicle state detector that detects at least a traveling speed and a traveling direction of the own vehicle and outputs the detected traveling speed and traveling direction of the own vehicle to the apparatus; and

a collision avoidance control executor that implements collision avoidance control upon reception of the instruction for collision avoidance control from the apparatus.

10. The system of claim 9, wherein the vehicle control means further outputs an instruction for alert in response to the collision probability outputted by the collision probability output means, the system further comprising:

an alert annunciator that alerts a vehicle'"'"'s driver of a possible collision with the nearby object upon reception of the instruction for alert from the apparatus.