Learning Robot Exploration Strategy with 4D Point-Clouds-like Information as Observations

06/17/2021
by   Zhaoting Li, et al.
0

Being able to explore unknown environments is a requirement for fully autonomous robots. Many learning-based methods have been proposed to learn an exploration strategy. In the frontier-based exploration, learning algorithms tend to learn the optimal or near-optimal frontier to explore. Most of these methods represent the environments as fixed size images and take these as inputs to neural networks. However, the size of environments is usually unknown, which makes these methods fail to generalize to real world scenarios. To address this issue, we present a novel state representation method based on 4D point-clouds-like information, including the locations, frontier, and distance information. We also design a neural network that can process these 4D point-clouds-like information and generate the estimated value for each frontier. Then this neural network is trained using the typical reinforcement learning framework. We test the performance of our proposed method by comparing it with other five methods and test its scalability on a map that is much larger than maps in the training set. The experiment results demonstrate that our proposed method needs shorter average traveling distances to explore whole environments and can be adopted in maps with arbitrarily sizes.

READ FULL TEXT

page 1

page 3

page 4

page 7

research
04/08/2019

3D mapping for multi hybrid robot cooperation

This paper presents a novel approach to build consistent 3D maps for mul...
research
05/08/2023

An Enhanced Sampling-Based Method With Modified Next-Best View Strategy For 2D Autonomous Robot Exploration

Autonomous exploration is a new technology in the field of robotics that...
research
03/29/2011

Planning to Be Surprised: Optimal Bayesian Exploration in Dynamic Environments

To maximize its success, an AGI typically needs to explore its initially...
research
07/21/2017

3DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-scale 3D Point Clouds

Semantic parsing of large-scale 3D point clouds is an important research...
research
11/18/2022

LiSnowNet: Real-time Snow Removal for LiDAR Point Cloud

LiDARs have been widely adopted to modern self-driving vehicles, providi...
research
02/26/2019

Learning to See the Wood for the Trees: Deep Laser Localization in Urban and Natural Environments on a CPU

Localization in challenging, natural environments such as forests or woo...

Please sign up or login with your details

Forgot password? Click here to reset