Laser Based Navigation in Asymmetry and Complex Environment

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.

Cognitive Enhancement of Robot Path Planning and Environmental Perception Based on Gmapping Algorithm Optimization

“…To achieve efficient logistics sorting, automation technology and sorting robots are widely used in the field of logistics warehousing [4]. Automated sorting systems can significantly improve sorting speed and accuracy [5], thereby reducing labor costs and sorting error rates [6]. However, in the process of automatic sorting, the robot must have the ability to identify and avoid various obstacles to ensure safe and efficient operation [7].…”

INVys: Indoor Navigation System for Persons with Visual Impairment Using RGB-D Camera

“…Judging from that ability, these tools are better than the conventional white cane because they can automatically detect obstacles and actively give feedback to the users. However, laser and ultrasonic provide poor information about the environment [10] and they only support micronavigation function.…”