The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLII-2/W13
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W13, 857–863, 2019
https://doi.org/10.5194/isprs-archives-XLII-2-W13-857-2019
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W13, 857–863, 2019
https://doi.org/10.5194/isprs-archives-XLII-2-W13-857-2019

  05 Jun 2019

05 Jun 2019

TOWARDS CONTINUOUS CONTROL FOR MOBILE ROBOT NAVIGATION: A REINFORCEMENT LEARNING AND SLAM BASED APPROACH

K. A. A. Mustafa1, N. Botteghi1, B. Sirmacek1, M. Poel2, and S. Stramigioli1 K. A. A. Mustafa et al.
  • 1Robotics and Mechatronics, Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, The Netherlands
  • 2Data Science, Faculty of Electric Engineering, Mathematics and Computer Science, University of Twente, The Netherlands

Keywords: SLAM, Deep Reinforcement Learning, Artificial Intelligence, Online Path Planning, Unknown environments

Abstract. We introduce a new autonomous path planning algorithm for mobile robots for reaching target locations in an unknown environment where the robot relies on its on-board sensors. In particular, we describe the design and evaluation of a deep reinforcement learning motion planner with continuous linear and angular velocities to navigate to a desired target location based on deep deterministic policy gradient (DDPG). Additionally, the algorithm is enhanced by making use of the available knowledge of the environment provided by a grid-based SLAM with Rao-Blackwellized particle filter algorithm in order to shape the reward function in an attempt to improve the convergence rate, escape local optima and reduce the number of collisions with the obstacles. A comparison is made between a reward function shaped based on the map provided by the SLAM algorithm and a reward function when no knowledge of the map is available. Results show that the required learning time has been decreased in terms of number of episodes required to converge, which is 560 episodes compared to 1450 episodes in the standard RL algorithm, after adopting the proposed approach and the number of obstacle collision is reduced as well with a success ratio of 83% compared to 56% in the standard RL algorithm. The results are validated in a simulated experiment on a skid-steering mobile robot.