Connecting Deep-Reinforcement-Learning-based Obstacle Avoidance with Conventional Global Planners using Waypoint Generators

04/08/2021
by   Linh Kästner, et al.
0

Deep Reinforcement Learning has emerged as an efficient dynamic obstacle avoidance method in highly dynamic environments. It has the potential to replace overly conservative or inefficient navigation approaches. However, the integration of Deep Reinforcement Learning into existing navigation systems is still an open frontier due to the myopic nature of Deep-Reinforcement-Learning-based navigation, which hinders its widespread integration into current navigation systems. In this paper, we propose the concept of an intermediate planner to interconnect novel Deep-Reinforcement-Learning-based obstacle avoidance with conventional global planning methods using waypoint generation. Therefore, we integrate different waypoint generators into existing navigation systems and compare the joint system against traditional ones. We found an increased performance in terms of safety, efficiency and path smoothness especially in highly dynamic environments.

READ FULL TEXT

page 1

page 8

research
04/08/2021

Towards Deployment of Deep-Reinforcement-Learning-Based Obstacle Avoidance into Conventional Autonomous Navigation Systems

Recently, mobile robots have become important tools in various industrie...
research
09/23/2021

Enhancing Navigational Safety in Crowded Environments using Semantic-Deep-Reinforcement-Learning-based Navigation

Intelligent navigation among social crowds is an essential aspect of mob...
research
09/23/2021

All-in-One: A DRL-based Control Switch Combining State-of-the-art Navigation Planners

Autonomous navigation of mobile robots is an essential aspect in use cas...
research
03/08/2021

Vision-Based Mobile Robotics Obstacle Avoidance With Deep Reinforcement Learning

Obstacle avoidance is a fundamental and challenging problem for autonomo...
research
09/23/2021

Obstacle-aware Waypoint Generation for Long-range Guidance of Deep-Reinforcement-Learning-based Navigation Approaches

Navigation of mobile robots within crowded environments is an essential ...
research
02/06/2023

Holistic Deep-Reinforcement-Learning-based Training of Autonomous Navigation Systems

In recent years, Deep Reinforcement Learning emerged as a promising appr...
research
12/23/2021

Missing Velocity in Dynamic Obstacle Avoidance based on Deep Reinforcement Learning

We introduce a novel approach to dynamic obstacle avoidance based on Dee...

Please sign up or login with your details

Forgot password? Click here to reset