Method, program, storage medium and assistance system for assisting an operator of an ego-agent

A program comprising program-code means for executing a method for assisting an operator of an ego-agent, when the program is executed on a computer or digital signal processor, wherein the method comprises:

• applying a behavior planning algorithm using at least a first value of a parameter value and a second value of the parameter in a cost function of the behavior planning algorithm to determine at least a first and a second planned behavior of the ego-agent;
• determining a current state of the ego-agent to determine an actual behavior of the ego-agent;
• estimating a personalized parameter value for the parameter in the cost function based on a relation of the at least first and second planned behavior and an actual behavior of the ego-agent;
• determining a parameter correction value at least based on the personalized parameter value and a target parameter value for the parameter in the cost function, wherein the parameter correction value shifts the personalized parameter value towards the target parameter value;
• generating an adapted parameter value for the parameter in the cost function by correcting the personalized parameter value using the parameter correction value;
• applying the behavior planning algorithm based on the adapted parameter value and estimating a future risk using the adapted parameter value in the behavior planning algorithm;
• and
• generating an output signal for communicating the estimated future risk to the operator via a human machine interface or adjusting semi-autonomously a control input from the operator via the human machine interface.

A non-transitory computer-readable storage medium embodying a program of machine-readable instructions executable by a digital processing apparatus, which cause the digital processing apparatus to perform:

• applying a behavior planning algorithm using at least a first value of a parameter and a second value of the parameter in a cost function of the behavior planning algorithm to determine at least a first and a second planned behavior of the ego-agent;
• determining a current state of the ego-agent to determine an actual behavior of the ego-agent;
• estimating a personalized parameter value for the parameter in the cost function based on a relation of the at least first and second planned behavior and an actual behavior of the ego-agent;
• determining a parameter correction value at least based on the personalized parameter value and a target parameter value for the parameter in the cost function, wherein the parameter correction value shifts the personalized parameter value towards the target parameter value;
• generate an adapted parameter value for the parameter in the cost function by correcting the personalized parameter value using the parameter correction value;
• applying the behavior planning algorithm based on the adapted parameter value and estimating a future risk using the adapted parameter value in the behavior planning algorithm;
• and
• generating an output signal for communicating the estimated future risk to the operator via a human machine interface or adjusting semi-autonomously a control input from the operator via the human machine interface.

An assistance system for assisting an ego-agent, the system comprises a processor configured to

• apply a behavior planning algorithm using at least a first value of a parameter and a second value of the parameter in a cost function of the behavior planning algorithm to determine at least a first and a second planned behavior of the ego-agent;
• determine a current state of the ego-agent to determine an actual behavior of the ego-agent;
• estimate a personalized parameter value for the parameter in the cost function based on a relation of the at least first and second planned behavior and an actual behavior of the ego-agent;
• determine a parameter correction value at least based on the personalized parameter value and a target parameter value for the parameter in the cost function, wherein the parameter correction value shifts the personalized parameter value towards the target parameter value;
• generate an adapted parameter value for the parameter in the cost function by correcting the personalized parameter value using the parameter correction value;
• apply the behavior planning algorithm based on the adapted parameter value and estimate a future risk using the adapted parameter value in the behavior planning algorithm;
• and
• communicate the estimated future risk to the operator via a human machine interface or adjusting semi-autonomously a control input from the operator via the human machine interface.