Towards Fully Autonomous Negative Obstacle Traversal via Imitation Learning Based Control
| dc.contributor.author | César-Tondreau, Brian | en |
| dc.contributor.author | Warnell, Garrett | en |
| dc.contributor.author | Kochersberger, Kevin | en |
| dc.contributor.author | Waytowich, Nicholas R. | en |
| dc.date.accessioned | 2022-06-23T18:52:45Z | en |
| dc.date.available | 2022-06-23T18:52:45Z | en |
| dc.date.issued | 2022-06-22 | en |
| dc.date.updated | 2022-06-23T12:12:32Z | en |
| dc.description.abstract | Current research in experimental robotics has had a focus on traditional, cost-based, navigation methods. These methods ascribe a value of utility for occupying certain locations in the environment. A path planning algorithm then uses this cost function to compute an optimal path relative to obstacle positions based on proximity, visibility, and work efficiency. However, tuning this function to induce more complex navigation behaviors in the robot is not straightforward. For example, this cost-based scheme tends to be pessimistic when assigning traversal cost to negative obstacles. Its often simpler to ascribe high traversal costs to costmap cells based on elevation. This forces the planning algorithm to plan around uneven terrain rather than exploring techniques that understand if and how to safely traverse through them. In this paper, imitation learning is applied to the task of negative obstacle traversal with Unmanned Ground Vehicles (UGVs). Specifically, this work introduces a novel point cloud-based state representation of the local terrain shape and employs imitation learning to train a reactive motion controller for negative obstacle detection and traversal. This method is compared to a classical motion planner that uses the dynamic window approach (DWA) to assign traversal cost based on the terrain slope local to the robots current pose. | en |
| dc.description.version | Published version | en |
| dc.format.mimetype | application/pdf | en |
| dc.identifier.citation | César-Tondreau, B.; Warnell, G.; Kochersberger, K.; Waytowich, N.R. Towards Fully Autonomous Negative Obstacle Traversal via Imitation Learning Based Control. Robotics 2022, 11, 67. | en |
| dc.identifier.doi | https://doi.org/10.3390/robotics11040067 | en |
| dc.identifier.uri | http://hdl.handle.net/10919/110912 | en |
| dc.language.iso | en | en |
| dc.publisher | MDPI | en |
| dc.rights | Creative Commons Attribution 4.0 International | en |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | en |
| dc.subject | autonomous navigation | en |
| dc.subject | learning from demonstration | en |
| dc.subject | imitation learning | en |
| dc.title | Towards Fully Autonomous Negative Obstacle Traversal via Imitation Learning Based Control | en |
| dc.title.serial | Robotics | en |
| dc.type | Article - Refereed | en |
| dc.type.dcmitype | Text | en |