Abstract
Inspection and maintenance are two crucial aspects of industrial pipeline plants. While robotics has made tremendous progress in the mechanic design of in-pipe inspection robots, the autonomous control of such robots is still a big open challenge due to the high number of actuators and the complex manoeuvres required. To address this problem, we investigate the usage of Deep Reinforcement Learning for achieving autonomous navigation of in-pipe robots in pipeline networks with complex topologies. We introduce a hierarchical policy decomposition based on Hierarchical Reinforcement Learning to learn robust high-level navigation skills. We show that the hierarchical structure introduced in the policy is fundamental for solving the navigation task through pipes and necessary for achieving navigation performances superior to human-level control. A video of our experiments can be found at: https://youtu.be/uyjSHulpGoI.
Original language | English |
---|---|
Title of host publication | Robot Intelligence Technology and Applications 6 - Results from the 9th International Conference on Robot Intelligence Technology and Applications |
Editors | Jinwhan Kim, Brendan Englot, Hae-Won Park, Han-Lim Choi, Hyun Myung, Junmo Kim, Jong-Hwan Kim |
Publisher | Springer |
Pages | 259-271 |
Number of pages | 13 |
ISBN (Print) | 9783030976712 |
DOIs | |
Publication status | Published - 2022 |
Event | 9th International Conference on Robot Intelligence Technology and Applications, RiTA 2021 - Daejeon, Korea, Republic of Duration: 16 Dec 2021 → 17 Dec 2021 Conference number: 9 |
Publication series
Name | Lecture Notes in Networks and Systems |
---|---|
Volume | 429 LNNS |
ISSN (Print) | 2367-3370 |
ISSN (Electronic) | 2367-3389 |
Conference
Conference | 9th International Conference on Robot Intelligence Technology and Applications, RiTA 2021 |
---|---|
Abbreviated title | RiTA 2021 |
Country/Territory | Korea, Republic of |
City | Daejeon |
Period | 16/12/21 → 17/12/21 |
Keywords
- In-pipe inspection robotics
- Reinforcement learning