Loading patent…
AssigneesHuawei Technologies Co., Ltd., The Royal Institution for the Advancement of Learning/Mcgill University
InventorsFlorian Shkurti, Gregory Dudek, Yasasa Abeysirigoonawardena, Elmira Amirloo Abolfathi, Jun Luo
Estimating the term…
A method and apparatus for generating adversarial scenarios and training an autonomous driving agent for an autonomous vehicle, using one or more sets of parameters, each set of parameters defining a respective driving scenario. A new set of parameters is generated by changing one or more parameters of one of the sets of parameters to define a new driving scenario, and performance of the autonomous driving agent is evaluated on the new driving scenario. The generating and evaluating is repeated until the autonomous driving agent fails to satisfy a predefined performance threshold for the new driving scenario. Each instance of changing the one or more parameters is based on a prior evaluated performance of the autonomous driving agent. The autonomous driving agent is trained to update a learned policy of the autonomous driving agent using at least one set of parameters, including the new set of parameters.
A method for training an autonomous driving agent for an autonomous vehicle using one or more sets of parameters, each set of parameters defining a respective driving scenario for the autonomous vehicle, the method comprising:
A processing unit comprising:
Dependencies are inferred from the claim text.