Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Localisation-safe reinforcement learning for mapless navigation

Lin, Feiqiang, Ji, Ze ORCID:, Wei, Changyun and Grech, Raphael 2022. Localisation-safe reinforcement learning for mapless navigation. Presented at: IEEE International Conference on Robotics and Biomimetics (IEEE ROBIO 2022), Jinghong, China, 5-9 December 2022. IEEE International Conference on Robotics and Biomimetics (ROBIO). IEEE, pp. 1327-1334. 10.1109/ROBIO55434.2022.10011937

[thumbnail of Ji Z - Robio 2022.pdf] PDF - Accepted Post-Print Version
Download (1MB)


Most reinforcement learning (RL)-based works for mapless point goal navigation tasks assume the availability of the robot ground-truth poses, which is unrealistic for real world applications. In this work, we remove such an assumption and deploy observation-based localisation algorithms, such as Lidar-based or visual odometry, for robot self-pose estimation. These algorithms, despite having widely achieved promising performance and being robust to various harsh environments, may fail to track robot locations under many scenarios, where observations perceived along robot trajectories are insufficient or ambiguous. Hence, using such localisation algorithms will introduce new unstudied problems for mapless navigation tasks. This work will propose a new RL-based algorithm, with which robots learn to navigate in a way that prevents localisation failures or getting trapped in local minimum regions. This ability can be learned by deploying two techniques suggested in this work: a reward metric to decide punishment on behaviours resulting in localisation failures; and a reconfigured state representation that consists of current observation and history trajectory information to transfer the problem from a partially observable Markov decision process (POMDP) to a Markov Decision Process (MDP) model to avoid local minimum.

Item Type: Conference or Workshop Item (Paper)
Date Type: Publication
Status: Published
Schools: Engineering
Publisher: IEEE
ISBN: 9781665481106
Date of First Compliant Deposit: 17 October 2022
Date of Acceptance: 15 October 2022
Last Modified: 21 Feb 2023 12:27

Actions (repository staff only)

Edit Item Edit Item


Downloads per month over past year

View more statistics