Method and system for impact-based operation of an autonomous agent
A system for impact-based operation of an autonomous agent (equivalently referred to herein as an ego agent and autonomous vehicle) includes and/or interfaces with a computing subsystem (equivalently referred to herein as a computer and/or set of computers). A method for impact-based operation of an autonomous agent includes: receiving a set of inputs; predicting a set of future scenarios; and determining a set of metrics based on the set of future scenarios. Additionally or alternatively, the method can include operating the autonomous agent based on the set of metrics and/or any other processes.
1. A method for impact-based operation of an autonomous vehicle, the method comprising:
collecting data from a set of sensors associated with the autonomous vehicle;
detecting a set of environmental objects in an environment of the autonomous vehicle based on the data;
performing a set of forward simulations comprising representations of the set of environmental objects, the set of forward simulations comprising:
a 1 st subset of simulations, comprising multiple simulations, wherein in the 1 st subset of simulations, a representation of the autonomous vehicle is present;
a 2 nd subset of simulations, comprising multiple simulations, wherein the multiple simulations of the 2 nd subset differ in an estimated intent assigned to the set of environmental objects represented in the multiple simulations, wherein in each of the 2 nd subset of simulations, the representation of the autonomous vehicle is absent;
determining an impact score of the ego vehicle on the environment, comprising:
calculating a 1 st set of metric values based on the 1 st subset of simulations;
calculating a 2 nd set of second metric values based on the 2 nd subset of simulations;
comparing the 1 st set of metric values with the 2 nd set of metric values; and
determining the impact score based on the comparison;
operating the ego vehicle based on the impact score.
2. The method of claim 1 , wherein comparing the 1 st set of metric values with the 2 nd set of metric values comprises calculating a difference between the 1 st set of metric values and the 2 nd set of metric values, wherein the difference represents a quantified impedance of progress of the environmental objects as caused by the autonomous vehicle.
3. The method of claim 2 , wherein each of the 1 st and 2 nd sets of metric values is determined based on a derivative of velocity of the environmental objects in the set of forward simulations.
4. The method of claim 2 , wherein each of the 1 st and 2 nd sets of metric values is determined based on a distance traveled by the environmental objects in the set of forward simulations.
5. The method of claim 2 , further comprising applying a scaling factor to the difference based on a set of features associated with the set of environmental objects.
6. The method of claim 5 , wherein the set of features comprises at least one of: a determination an environmental object of the set of environmental objects does not have a right-of-way privilege in a scenario present in the set of forward simulations; a determination that the environmental object is arranged behind the autonomous vehicle; and a determination that the environmental vehicle is located above a predetermined distance threshold from the autonomous vehicle.
7. The method of claim 6 , wherein the scaling factor decreases the value of the difference.
8. The method of claim 1 , further comprising determining a set of multiple impact scores, wherein the set of multiple impact scores comprises the impact score, wherein operating the autonomous vehicle based on the impact score comprises selecting a policy from a set of multiple policy options for the autonomous vehicle based on the set of multiple impact scores.
9. The method of claim 8 , wherein the policy is further selected based on a reward score associated with the autonomous vehicle, wherein the reward score represents the progress of the autonomous vehicle relative to an autonomous vehicle goal.
10. The method of claim 9 , wherein the autonomous vehicle goal comprises a distance to a destination of the autonomous vehicle.
11. The method of claim 9 , wherein the autonomous vehicle goal comprises an amount of work exerted by the autonomous vehicle to reach a destination associated with the autonomous vehicle.
12. The method of claim 1 , wherein the environmental objects comprise a set of vehicles and a set of pedestrians located in a field-of-view of the set of sensors.
13. A system for impact-based operation of an autonomous vehicle, the system comprising:
a data collection subsystem comprising a set of sensors;
a computing subsystem comprising a memory and a processor in communication with the data collection subsystem, wherein the computing subsystem:
collects data from the data collection subsystem;
processes the data to detect a set of environmental objects in an environment on the autonomous vehicle;
a simulator that performs a set of forward simulations, the set of forward simulations comprising:
a 1 st subset of simulations, comprising multiple simulations, wherein in the 1 st subset of simulations, a representation of the autonomous vehicle is present;
a 2 nd subset of simulations, comprising multiple simulations, wherein the multiple simulations of the 2 nd subset differ in an estimated intent assigned to the set of environmental objects represented in the multiple simulations, wherein in each of the 2 nd subset of simulations, the representation of the autonomous vehicle is absent;
a controller configured to maneuver the autonomous vehicle based on a set of instructions received from the computing subsystem, wherein the computing subsystem:
determines the set of instructions based on an impact of the autonomous vehicle on the set of environmental objects, wherein determining the impact comprises:
calculating a 1 st set of metric values based on the 1 st subset of simulations;
calculating a 2 nd set of second metric values based on the 2 nd subset of simulations;
comparing the 1 st set of metric values with the 2 nd set of metric values; and
determining the impact based on the comparison.
14. The system of claim 13 , wherein the simulator is part of the computing subsystem.
15. The system of claim 14 , wherein the computing subsystem is located onboard the autonomous vehicle.
16. The system of claim 13 , wherein the simulator performs the set of forward simulations throughout a trip of the autonomous vehicle.
17. The system of claim 16 , wherein simulations of the set of forward simulations are performed according to a predetermined frequency.
18. The system of claim 13 , wherein comparing the 1 st set of metric values with the 2 nd set of metric values comprises calculating a difference between the 1 st set of metric values and the 2 nd set of metric values, wherein the difference represents a quantified impedance of progress of the environmental objects as caused by the autonomous vehicle.
19. The system of claim 18 , wherein each of the 1 st and 2 nd sets of metric values is determined based on a derivative of velocity of the environmental objects in the set of forward simulations.
20. The system of claim 18 , wherein each of the 1 st and 2 nd sets of metric values is determined based on a distance traveled by the environmental objects in the set of forward simulations.