End-to-end human inspired learning based system for dynamic obstacle avoidance

As a first, the paper proposes modelling and learning of specific behaviors for dynamic obstacle avoidance in end-to-end motion planning. In the literature many end-to-end methods have been used in simulators to drive a car and to apply the learnt strategies to avoid the obstacles using the lane changing, following the vehicle as per the traffic rules, driving in-between the lane boundaries, and many more behaviors. The proposed method is designed to avoid obstacles in the scenarios where a dynamic obstacle is headed directly towards the robot from different directions. To avoid the critical encounter of the dynamic obstacles, we trained a novel deep neural network (DNN) with two specific behavioral obstacle avoidance strategies, namely "head-on collision avoidance" and "stop and move". These two strategies of obstacle avoidance come from the human behavior of obstacle avoidance. Looking at the current frame only, for a very similar visual display of the scenario, the two strategies have contrasting outputs and overall outcomes that makes learning very difficult. A random data recording over general simulations is unlikely to record the corner cases of both behaviors that rarely occur, and a behavior-specific training used in this paper intensifies the same cases for a better learning of the robot in such corner cases. We calculate the intention of the obstacle, whether it will move or not. This proposed method is compared with three state-of-the-art methods of motion planning, namely Timed-Elastic Band, Dynamic Window Approach and Nonlinear Probabilistic Velocity Obstacle. The proposed method beats all the state-of-the-art methods used for comparisons.