Method and apparatus for optimized resource allocation during autonomous driving based on reinforcement learning using data from lidar, radar and camera sensors

摘要

PROBLEM TO BE SOLVED: To reduce power consumption of an autonomous vehicle by efficiently allocating resources during autonomous traveling by reinforcement learning. In a method for efficiently allocating resources during autonomous traveling by reinforcement learning, (a) a computing device obtains at least one attention sensor data and calculates one or more attention scores. And (b) the computing device obtains at least one video data and generates at least one determination data for autonomous driving, (c) the computing device has a drive network, and refers to the determination data. And driving the autonomous vehicle to acquire at least one situation data indicating a change in the surrounding situation, (d) the computing device at least one of the one or more parameters used for the neural network operation. Partly adjusting. [Selection diagram] Figure 1