Orientation sensitive traffic collision warning system

• US 9,524,643 B2
• Filed: 04/16/2013
• Issued: 12/20/2016
• Est. Priority Date: 04/20/2012
• Status: Active Grant

• Current Assignee: Honda Research Institute Europe GmbH (Honda Motor Company)
• Original Assignee: Honda Research Institute Europe GmbH (Honda Motor Company)
• Inventors: Goerick, Christian, Bolder, Bram, Dittes, Benjamin
• Primary Examiner(s): Black, Thomas G
• Assistant Examiner(s): Nolan, Peter D
• Application Number:
  US13/863,563
• Publication Number:
  US 20130282268A1
• Time in Patent Office: 1,344 Days
• Field of Search: 701/300, 701/301, 348/148, 348/169, 340/436
• US Class Current: 1/1
• CPC Class Codes: B60W 30/095 Predicting travel path or likelihood of collision
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G08G 1/16 Anti-collision systems road vehicle drive control systems for predicting or avoiding probable or impending collision otherwise than by control of a particular sub-unit B60W30/08
• CPC Class Codes: G08G 1/165 for passive traffic, e.g. including static obstacles, trees
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes

Abstract

The present invention provides an Advanced Driver Assistant System (ADAS) 10 and an operating method thereof, which work on long time scales, and guide an ego vehicle 20 away from upcoming risks, rather than only reacting to risks to mitigate the consequences of a crash. To this end, information comprising the orientation of other traffic participants 30, 40, 50, 60, a free driving area of the ego vehicle 20, and/or a driving trajectory of the vehicle 20 as intended by the driver is taken into account, in order to determine potential risks.

Claims

1. An advanced driver assistant system for an ego vehicle, the system comprising:

at least one sensor configured to detect one or more traffic participants;

a computing unit configured to receive a sensor signal from the at least one sensor, to determine from the sensor signal an orientation of each of the detected traffic participants in respect to the ego vehicle,

wherein the computing unit is configured to determine whether the traffic participant is a vehicle or pedestrian, based on extracted visual features of the traffic participant, and if it determines that the traffic participant is a vehicle, to distinguish between front side and back side of the vehicle and to determine as the orientation a direction pointing from said back side to said front side;

the computing unit is configured to calculate a distance between the traffic participant and a driving area, in which the ego vehicle is expected to drive and which the ego vehicle will reach in the future, and to consider the traffic participant as relevant, if the determined distance is below a predetermined threshold and the determined orientation of the traffic participant is relevant to the driving area; and

the computing unit is configured to determine information concerning the driving area, and to predict the potential risks for the ego vehicle by taking only said relevant traffic participants into account.

2. The advanced driver assistant system according to claim 1, wherein the computing unit is configured to extract from the sensor signal visual features of a traffic participant, and to determine the orientation of the traffic participant based on an analysis of the extracted visual features.

3. The advanced driver assistant system according to claim 2, wherein the computing unit is configured to analyze the extracted visual features by comparing them to visual features stored in a memory of the advanced driver assistant system.

4. The advanced driver assistant system according to claim 2, wherein the computing unit is configured to continuously determine an angle between the orientation of the traffic participant and the current driving direction of the ego vehicle.

5. The advanced driver assistant system according to claim 1, wherein the computing unit is further configured to determine an intended driving trajectory of the ego vehicle.

6. The advanced driver assistant system according to claim 5, wherein the computing unit is configured to monitor vehicle parameters concerning the actions and intentions of a driver of the ego vehicle, and to determine the driving trajectory based on a past trajectory of the ego vehicle and/or the monitored vehicle parameters.

7. The advanced driver assistant system according to claim 6, wherein the computing unit is configured to output a warning signal if it determines that the determined driving trajectory of the ego vehicle is not sufficient to avoid the predicted potential risk.

8. The advanced driver assistant system according to claim 5, wherein the computing unit is configured to compute whether the driving trajectory of the ego vehicle is sufficient to avoid the predicted potential risks.

9. The advanced driver assistant system according to claim 1, wherein the computing unit is configured to extract from the sensor signal a moving direction of a traffic participant, and to determine the orientation of the traffic participant based on the moving direction.

10. The advanced driver assistant system according to claim 1, wherein the computing unit is configured to rank all determined potential risks, and to issue a warning signal only for a potential risk that is ranked above a predetermined threshold rank.

11. A method for operating an advanced driver assistant system for an ego vehicle, the method comprising:

detecting one or more traffic participants with at least one sensor;

determining, from a sensor signal of the at least one sensor, an orientation of each of the traffic participants in respect to the ego vehicle;

determining whether the traffic participant is a vehicle or pedestrian, based on extracted visual features of a traffic participant; and

if it is determined that a traffic participant is a vehicle, distinguishing between front side and back side of the vehicle and determining as the orientation a direction pointing from said back side to said front side,

wherein the detecting further comprises calculating a distance between the traffic participant and a driving area, in which the ego vehicle is expected to drive and which the ego vehicle will reach in the future, and to consider the traffic participant as relevant, if the determined distance is below a predetermined threshold and the determined orientation of the traffic participant is relevant to the driving area; and

determining information concerning the driving area, and to predict the potential risks for the ego vehicle by taking only said relevant traffic participants into account.