Zhang, Bingqing;
(2023)
Understanding Interactions in Shared-control Wheelchair Use in Crowds.
Doctoral thesis (Ph.D), UCL (University College London).
Preview |
Text
PhD_Thesis___Pat_final.pdf - Accepted Version Download (39MB) | Preview |
Abstract
Navigating through human crowds is a challenging task for robots. Classic approaches treat people as obstacles while ignoring the potential interaction and cooperation between the human and the robot. These approaches are typically limited to low crowd density and usually fail when the density increases. This is known as the “freezing robot” problem. In order to deal with this issue, interaction that happens during robot navigation needs to be captured so as to provide a safe and social navigation strategy. This is a new field of research that has begun to receive attention in recent years. This PhD work is a part of the EU H2020 CrowdBot project, with the aim to explore the crowd navigation problem for an important but overlooked use case: A shared-controlled wheelchair -- which is designed for increasing independent mobility of people with mobility impairment and are having difficulty using standard power wheelchairs. Different from an autonomous robot, the presence of a human driver who controls the wheelchair jointly with a path planner completely changes the social aspect of navigation and poses a new challenge by adding more potential interactions into the system. In order to explore interactions in the shared-control navigation in crowds, this research has been carried out through following steps: Firstly, the requirement and design recommendations were identified through stakeholder engagement. Then, existing navigation strategies that are either model-based or learning-based approaches have been explored, implemented by taking shared-control and user-wheelchair-crowds interaction into account. The proposed methods have been tested in simulation and the real world crowds.
Type: | Thesis (Doctoral) |
---|---|
Qualification: | Ph.D |
Title: | Understanding Interactions in Shared-control Wheelchair Use in Crowds |
Open access status: | An open access version is available from UCL Discovery |
Language: | English |
Additional information: | Copyright © The Author 2022. Original content in this thesis is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) Licence (https://creativecommons.org/licenses/by-nc/4.0/). Any third-party copyright material present remains the property of its respective owner(s) and is licensed under its existing terms. Access may initially be restricted at the author’s request. |
Keywords: | Shared-control, Robotics, Wheelchair, Navigation |
UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
URI: | https://discovery-pp.ucl.ac.uk/id/eprint/10167711 |
Archive Staff Only
![]() |
View Item |