File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/IROS45743.2020.9341805
- Scopus: eid_2-s2.0-85102405139
- WOS: WOS:000724145801078
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: DeepMNavigate: Deep reinforced multi-robot navigation unifying local & global collision avoidance
Title | DeepMNavigate: Deep reinforced multi-robot navigation unifying local & global collision avoidance |
---|---|
Authors | |
Keywords | Motion and Path Planning Collision Avoidance Reinforcement learning Robot sensing systems Intelligent robots |
Issue Date | 2020 |
Publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000393 |
Citation | IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS): Consumer Robots and Our Future, Virtual Conference, Las Vegas, USA, 25 October 2020 - 24 January 2021, p. 6952-6959 How to Cite? |
Abstract | We present a novel algorithm (DeepMNavigate) for global multi-agent navigation in dense scenarios using deep reinforcement learning (DRL). Our approach uses local and global information for each robot from motion information maps. We use a three-layer CNN that takes these maps as input to generate a suitable action to drive each robot to its goal position. Our approach is general, learns an optimal policy using a multi-scenario, multi-state training algorithm, and can directly handle raw sensor measurements for local observations. We demonstrate the performance on dense, complex benchmarks with narrow passages and environments with tens of agents. We highlight the algorithm’s benefits over prior learning methods and geometric decentralized algorithms in complex scenarios. |
Description | TuCT19 Learning in Motion Planning - Paper TuCT19.6 |
Persistent Identifier | http://hdl.handle.net/10722/285032 |
ISSN | 2023 SCImago Journal Rankings: 1.094 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Tan, Q | - |
dc.contributor.author | Fan, T | - |
dc.contributor.author | Pan, J | - |
dc.contributor.author | Manocha, D | - |
dc.date.accessioned | 2020-08-07T09:05:51Z | - |
dc.date.available | 2020-08-07T09:05:51Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS): Consumer Robots and Our Future, Virtual Conference, Las Vegas, USA, 25 October 2020 - 24 January 2021, p. 6952-6959 | - |
dc.identifier.issn | 2153-0858 | - |
dc.identifier.uri | http://hdl.handle.net/10722/285032 | - |
dc.description | TuCT19 Learning in Motion Planning - Paper TuCT19.6 | - |
dc.description.abstract | We present a novel algorithm (DeepMNavigate) for global multi-agent navigation in dense scenarios using deep reinforcement learning (DRL). Our approach uses local and global information for each robot from motion information maps. We use a three-layer CNN that takes these maps as input to generate a suitable action to drive each robot to its goal position. Our approach is general, learns an optimal policy using a multi-scenario, multi-state training algorithm, and can directly handle raw sensor measurements for local observations. We demonstrate the performance on dense, complex benchmarks with narrow passages and environments with tens of agents. We highlight the algorithm’s benefits over prior learning methods and geometric decentralized algorithms in complex scenarios. | - |
dc.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000393 | - |
dc.relation.ispartof | IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Proceedings | - |
dc.subject | Motion and Path Planning | - |
dc.subject | Collision Avoidance | - |
dc.subject | Reinforcement learning | - |
dc.subject | Robot sensing systems | - |
dc.subject | Intelligent robots | - |
dc.title | DeepMNavigate: Deep reinforced multi-robot navigation unifying local & global collision avoidance | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Pan, J: jpan@cs.hku.hk | - |
dc.identifier.authority | Pan, J=rp01984 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/IROS45743.2020.9341805 | - |
dc.identifier.scopus | eid_2-s2.0-85102405139 | - |
dc.identifier.hkuros | 312223 | - |
dc.identifier.spage | 6952 | - |
dc.identifier.epage | 6959 | - |
dc.identifier.isi | WOS:000724145801078 | - |
dc.publisher.place | United States | - |
dc.identifier.issnl | 2153-0858 | - |