Abstract:
Deep Learning has led us to newer possibilities in solving complex control and
navigation related tasks. The paper presents Deep Learning with back propagation
autonomous navigation and obstacle avoidance of self-driving cars, applied with
Deep Q Network to a simulated car an urban environment. The approach uses two
types of sensor data as input: camera sensor and laser sensor in front of the car.
It also designs a cost-efcient high-speed car prototype capable of running the same
algorithm in real-time. The design uses a camera and a Hokuyo Lidar sensor in the
car front. It uses embedded GPU (Nvidia-TX2) or CPU for running deep-learning
algorithms based on sensor inputs.
