DRQN-based 3D Obstacle Avoidance with a Limited Field of View

08/12/2021
by   Yu'an Chen, et al.
0

In this paper, we propose a map-based end-to-end DRL approach for three-dimensional (3D) obstacle avoidance in a partially observed environment, which is applied to achieve autonomous navigation for an indoor mobile robot using a depth camera with a narrow field of view. We first train a neural network with LSTM units in a 3D simulator of mobile robots to approximate the Q-value function in double DRQN. We also use a curriculum learning strategy to accelerate and stabilize the training process. Then we deploy the trained model to a real robot to perform 3D obstacle avoidance in its navigation. We evaluate the proposed approach both in the simulated environment and on a robot in the real world. The experimental results show that the approach is efficient and easy to be deployed, and it performs well for 3D obstacle avoidance with a narrow observation angle, which outperforms other existing DRL-based models by 15.5

READ FULL TEXT

page 5

page 7

research
02/11/2020

Robot Navigation with Map-Based Deep Reinforcement Learning

This paper proposes an end-to-end deep reinforcement learning approach f...
research
03/23/2019

HouseExpo: A Large-scale 2D Indoor Layout Dataset for Learning-based Algorithms on Mobile Robots

As one of the most promising areas, mobile robots draw much attention th...
research
07/19/2023

Nonlinear Model Predictive Control with Obstacle Avoidance Constraints for Autonomous Navigation in a Canal Environment

In this paper, we describe the development process of autonomous navigat...
research
12/15/2017

Visual Based Navigation of Mobile Robots

We have developed an algorithm to generate a complete map of the travers...
research
02/25/2021

FAITH: Fast iterative half-plane focus of expansion estimation using event-based optic flow

Course estimation is a key component for the development of autonomous n...
research
11/24/2021

Autonomous bot with ML-based reactive navigation for indoor environment

Local or reactive navigation is essential for autonomous mobile robots w...
research
09/16/2021

End-to-End Partially Observable Visual Navigation in a Diverse Environment

How can a robot navigate successfully in a rich and diverse environment,...

Please sign up or login with your details

Forgot password? Click here to reset