Method for assisting a driver in driving an ego vehicle and corresponding driver assistance system

• US 9,708,004 B2
• Filed: 01/08/2016
• Issued: 07/18/2017
• Est. Priority Date: 01/23/2015
• Status: Active Grant

• Current Assignee: Honda Research Institute Europe GmbH (Honda Motor Company)
• Original Assignee: Honda Research Institute Europe GmbH (Honda Motor Company)
• Inventors: Weisswange, Thomas, Fritsch, Jannik, Goerick, Christian, Casapietra, Edoardo
• Primary Examiner(s): Melton, Todd
• Application Number:
  US14/990,982
• Publication Number:
  US 20160214647A1
• Time in Patent Office: 557 Days
• CPC Class Codes: B60W 30/095 Predicting travel path or likelihood of collision
• CPC Class Codes: B60W 30/10 Path keeping cruise control for automatically following a preceding vehicle B60W30/165
• CPC Class Codes: B60W 40/04 Traffic conditions
• CPC Class Codes: B60W 40/06 Road conditions
• CPC Class Codes: B62D 15/025 Active steering aids, e.g. helping the driver by actively influencing the steering system after environment evaluation B62D1/28 takes precedence
• CPC Class Codes: B62D 15/029 Steering assistants using warnings or proposing actions to the driver without influencing the steering system
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: G08G 1/0965 responding to signals from another vehicle, e.g. emergency vehicle

Abstract

An environment of an ego vehicle is physically sensed and sensor data is produced. A representation of the environment is generated. The representation includes a plurality of representation segments each of which corresponds to a limited area of the environment. Characteristic information is generated for at least a part of the limited areas of the environment and the characteristic information is assigned to the representation segment which corresponds to the respective area of the environment. Furthermore, future or past movement behavior for a traffic object is estimated and characteristic information for at least one limited area of the environment is inferred based upon the estimated movement behavior. This characteristic information is assigned to the representation segment corresponding to the respective area of the environment and an evaluation is performed for determining a preferred path for the ego vehicle. An assistance signal based on the determined path is output.

Claims

1. Method for assisting a driver in driving an ego-vehicle, comprising the steps of:

physically sensing an environment of the ego-vehicle and producing sensor data;

generating a representation of the environment, the representation comprising a plurality of representation segments each of which corresponds to a limited area of the environment;

analyzing the sensor data for generating structural characteristic information of the environment for at least a part of the limited areas of the environment;

assigning the structural characteristic information to the representation segment corresponding to the respective area of the environment;

determining for which of the limited areas of the environment no structural characteristic information is generated from the sensor data or structural characteristic information is to be supplemented;

estimating a future or past movement behavior for a traffic object sensed by the physical sensing;

inferring structural characteristics of the environment for at least one determined limited area of the environment on the basis of the estimated movement behavior;

assigning at least part of the structural characteristic information inferred on the basis of the estimated movement behavior to the representation segment corresponding the respective area of the environment;

evaluating the resulting representation comprising the representation segments including all assigned structural characteristics for determining a preferred path for the ego-vehicle; and

generating and outputting an assistance signal based on the determined path.

2. Method according to claim 1, wherein

as movement behavior for the traffic object a most likely trajectory is calculated.

3. Method according to claim 1, wherein

as a movement behavior for the traffic object a position probability distribution is calculated.

4. Method according to claim 1, wherein

the representation is a metric top-down view.

5. Method according to claim 4, wherein

the representation segments define a regular grid.

6. Method according to claim 1, wherein inferring structural characteristic information on the basis of estimated movement behavior is performed only for limited areas of the environment corresponding to representation segments that do not have assigned structural characteristic information derived by analyzing the sensor data.

7. Method according to claim 1, wherein

the preferred path is determined by generating plurality of possible paths through the representation connecting a current position of the ego-vehicle with a predetermined waypoint and evaluating on the basis of their quality which is determined as a measure taking into account quality values that describe the usability of each of the representation segments for driving along the respective path.

8. Method according to claim 1, wherein

the preferred path is determined by selecting representation segments step by step starting from the ego-vehicles current position.

9. Method according to claim 1, wherein

future or past movement behavior is estimated for every traffic object that can be recognized on the basis of the sensor data.

10. Method according to claim 1, wherein

the resulting representation is evaluated for determining at least one possible path for at least on traffic object other than the ego vehicle.

11. Driver assistance system comprising:

sensor means for physically sensing an environment of an ego-vehicle,

a representation generation unit, for generating a representation of the environment, comprising a plurality of representation segments and configured to assign characteristic information derived from the sensor data to representation segments,

traffic object future or past movement behavior estimation unit,

inference unit configured to determine for which of the limited areas of the environment no structural characteristic information is generated from the sensor data or structural characteristic information is to be supplemented, to infer structural characteristics for at least one determined limited area of the environment on the basis of the output of the movement behavior estimation unit and assign the structural characteristic information to the representation segment of the representation inferred on the basis of the estimated movement behavior, and

a path evaluation unit for evaluating the resulting representation including all assigned structural characteristics and configured to generate and output an assistance signal.

12. Driver assistance system according to claim 11, wherein

the inference unit is configured to perform inference of structural characteristic information on the basis of the estimated movement behavior only for limited areas of the environment corresponding to representation segments that do not have assigned structural characteristic information derived by analyzing the sensor data.

13. Driver assistance system according to claim 11, wherein

the path evaluation unit is configured to determine the preferred path by generating a plurality of possible paths through the representation connecting a current position of the ego-vehicle with a predetermined waypoint and evaluating on the basis of their quality which is determined as a measure taking into account quality values that describe the usability of each of the representation segments for driving along the respective path.

14. Driver assistance system according to claim 11, wherein

the path evaluation unit is configured to determine the preferred path by selecting representation segments step by step starting from the ego-vehicles current position.

15. Driver assistance system according to claim 11, wherein

the path evaluation unit is configured to estimate the future or past movement behavior for every traffic object that can be recognized on the basis of the sensor data.

16. Driver assistance system according to claim 11, wherein

the path evaluation unit is configured to evaluate the resulting representation to determine at least one possible path for at least one traffic object other than the ego vehicle.