Dynamic Obstacle Avoidance Technique for Mobile Robot Navigation Using Deep Reinforcement Learning
Journal: International Journal of Emerging Trends in Engineering Research (IJETER) (Vol.11, No. 9)Publication Date: 2023-09-25
Authors : Ravi Raj Andrzej Kos;
Page : 307-314
Keywords : artificial intelligence (AI); dynamic obstacles; deep reinforcement learning (DRL); dynamic policy; mobile robot (MR); navigation;
Abstract
N the realm of mobile robotics, navigating around obstacles is a fundamental task, particularly in constantly changing situations. Although deep reinforcement learning (DRL) techniques exist that utilize the positional information of robot's, environmental states, and input dataset for neural networks. Although, the positional information alone does not provide sufficient insights into the motion trends of obstacles. To solve this issue, this paper presents a dynamic obstacle mobility pattern approach for mobile robots (MRs) that rely on DRL. This method employs the positional details of dynamic obstacles dependent upon time for establishing a movement trend vector. This vector, in conjunction with another mobility state attribute, forms the MR mobility guidance matrix, that essentially conveys the pattern variation of dynamic obstacles trend over a specified interval. Using this matrix, the robot can choose its avoidance action. Also, this methodology uses the DRL-based dynamic policy algorithm for the testing and validation of the proposed technique through Python programming. The experimental outcomes demonstrate that this technique substantially improves the safety of avoiding dynamic obstacles.
Other Latest Articles
- A Brief Review of Rehabilitation Wearable Robots for the Upper and Lower Limbs
- A Secure Deduplication Technique for Data in the Cloud
- CHRONIC DISEASE MANAGEMENT THROUGH PERSONALIZED CONTENT: A CMS APPROACH
- AIRCRAFT GAS TURBINE ENGINE TEST BED & MODULE CHANGE WORKSHOP: REVIEW FOR EDUCATION & RESEARCH
- FUELING THE NEXT ERA OF AR/VR ADVANCEMENTS THROUGH EDGEAI
Last modified: 2023-09-25 23:12:19