Confidence estimation for predictive driver assistance systems based on plausibility rules

1. A method for a prediction subsystem in a driving assistance system of a vehicle implemented by an electronic control unit, the method comprising the following steps:

accepting an environment representation representing at least one entity, wherein the at least one entity comprises at least one of a static or a moving object, or a structural element which is detected by one or more sensors in an environment of the vehicle;

applying one or more plausibility rules on the environment representation;

calculating a confidence estimate related to the environment representation according to a result of the application of one or more plausibility rules on the environment representation, wherein each plausibility rule comprises a plausible relation between the at least one entity and at least one another entity; and

providing the confidence estimate as input for an evaluation of a prediction based on the environment representation,

wherein the confidence estimate is an estimate of a degree of influence by the detected entity on the prediction, and

wherein the driving assistance system is configured to perform at least one of an active control and passive control of the vehicle based on the prediction.

2. The method according to claim 1 ,

wherein a plausibility rule comprises a condition which returns a binary value representing either true or false when applied to the environment representation.

3. The method according to claim 1 ,

wherein a plausibility rule comprises a numerical expression which returns a numerical value when applied to the environment representation.

4. The method according to claim 1 ,

wherein the confidence estimate is assigned a numerical value representing a confidence of the associated environment representation.

5. The method according to claim 4 ,

wherein the confidence is expressed as a probability value.

6. The method according to claim 1 ,

wherein applying one of the plausibility rules comprises computing a confidence estimate as one of:

setting a predefined value (c_start) for the confidence estimate indicating a plausible detection of the environment representation,

setting a predefined value (c_low) for the confidence estimate indicating an implausible detection of the environment representation, and

increasing or decreasing a value of the confidence estimate by a predefined amount (Δc).

7. The method according to claim 1 ,

wherein calculating the confidence estimate comprises calculating a combination of multiple confidence estimates, resulting from applying multiple plausibility rules, based on at least one of a summation, weighted summation, product, weighted product, and selecting a minimum or maximum.

8. The method according to claim 1 ,

wherein the evaluation comprises deciding on whether or not the environment representation is used for a prediction by comparing a numerical value of the confidence estimate with a numerical value of at least one of a predefined threshold value and numerical values of one or more other confidence estimates.

9. The method according to claim 1 ,

wherein the driving assistance system is adapted to perform a cruise control functionality.

10. A non-transitory computer readable medium comprising program code portions for performing the method according to claim 1 when the computer program is executed by a computing device.

11. A driving assistance system for a vehicle, the driving assistance system including a prediction subsystem and comprising:

a component adapted to accept an environment representation representing at least one entity, wherein the at least one entity comprises at least one of a static or a moving object, or a structural element which is detected by one or more sensors in an environment of the vehicle;

a component adapted to apply one or more plausibility rules on the environment representation;

a component adapted to calculate a confidence estimate related to the environment representation according to a result of the application of one or more plausibility rules on the environment representation, wherein each plausibility rule comprises a plausible relation between the at least one entity and at least one another entity; and

a component adapted to provide the confidence estimate as input for an evaluation of a prediction based on the environment representation,

wherein the confidence estimate is an estimate of a degree of influence by the detected entity on the prediction, and

wherein the driving assistance system is configured to perform at least one of an active control and passive control of the vehicle based on the prediction.

12. The system according to claim 11 ,

wherein the prediction subsystem is adapted to perform a context based prediction and a physical prediction.

13. A vehicle comprising a system according to claim 11 .