Laser Based Navigation in Asymmetry and Complex Environment
Open Access
- 27 January 2022
- Vol. 14 (2), 253
- https://doi.org/10.3390/sym14020253
Abstract
For collision-free navigation in unstructured and cluttered environments, deep reinforcement learning (DRL) has gained extensive successes for being capable of adapting to new environments without much human effort. However, due to its asymmetry, the problems related to its lack of data efficiency and robustness remain as challenges. In this paper, we present a new laser-based navigation system for mobile robots, which combines a global planner with reinforcement learning-based local trajectory re-planning. The proposed method uses Proximal Policy Optimization to learn an efficient and robust local planning policy with asynchronous data generation and training. Extensive experiments have been presented, showing that the proposed system achieves better performance than previous methods including end-to-end DRL, and it can improve the asymmetrical performance. Our analysis show that the proposed method can efficiently avoid deadlock points and achieves a higher success rate. Moreover, we show that our system can generalize to unseen environments and obstacles with only a few shots. The model enables the warehouse to realize automatic management through intelligent sorting and handling, and it is suitable for various customized application scenarios.Keywords
Funding Information
- National Natural Science Foundation of China (61902037, 11902350)
- Fundamental Research Funds for the Central Universities (500419804)
- Key De- 384 ployment Projects of Chinese Academy of Sciences (KJZD-EW-G20-03, BILSCIC-2018KF-09)
This publication has 14 references indexed in Scilit:
- Integrating a Path Planner and an Adaptive Motion Controller for Navigation in Dynamic EnvironmentsApplied Sciences, 2019
- Towards Goal-Directed Navigation Through Combining Learning Based Global and Local PlannersSensors, 2019
- Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language NavigationPublished by Springer Science and Business Media LLC ,2018
- A 3D Rotating Laser-Based Navigation Solution for Micro Aerial Vehicles in Dynamic EnvironmentsUnmanned Systems, 2018
- LiDAR-only based navigation algorithm for an autonomous agricultural robotComputers and Electronics in Agriculture, 2018
- A Real-Time 3D Path Planning Solution for Collision-Free Navigation of Multirotor Aerial Robots in Dynamic EnvironmentsJournal of Intelligent & Robotic Systems, 2018
- Mastering the game of Go with deep neural networks and tree searchNature, 2016
- Socially Adaptive Path Planning in Human Environments Using Inverse Reinforcement LearningInternational Journal of Social Robotics, 2015
- Human-level control through deep reinforcement learningNature, 2015
- Reinforcement learning in robotics: A surveyThe International Journal of Robotics Research, 2013