On Reward Shaping for Mobile Robot Navigation: A Reinforcement Learning and SLAM Based Approach
This is an incremental improvement for mobile robot navigation, enhancing obstacle awareness and transferability to real robots.
They tackled mobile robot navigation in unknown environments using a deep reinforcement learning approach with a reward function shaped by online map knowledge, resulting in a 36.9% reduction in iteration steps and up to 45% improvement in unseen environments.
We present a map-less path planning algorithm based on Deep Reinforcement Learning (DRL) for mobile robots navigating in unknown environment that only relies on 40-dimensional raw laser data and odometry information. The planner is trained using a reward function shaped based on the online knowledge of the map of the training environment, obtained using grid-based Rao-Blackwellized particle filter, in an attempt to enhance the obstacle awareness of the agent. The agent is trained in a complex simulated environment and evaluated in two unseen ones. We show that the policy trained using the introduced reward function not only outperforms standard reward functions in terms of convergence speed, by a reduction of 36.9\% of the iteration steps, and reduction of the collision samples, but it also drastically improves the behaviour of the agent in unseen environments, respectively by 23\% in a simpler workspace and by 45\% in a more clustered one. Furthermore, the policy trained in the simulation environment can be directly and successfully transferred to the real robot. A video of our experiments can be found at: https://youtu.be/UEV7W6e6ZqI