DUnE: A Versatile Dynamic Unstructured Environment for Off-Road Navigation
Navigating uneven, unstructured terrain with dynamic obstacles remains a challenge for autonomous mobile robots. This article introduces <b>D</b>ynamic <b>Un</b>structured <b>E</b>nvironment (DUnE) for evaluating the performance of off-road navigation systems in s...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Robotics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-6581/14/4/35 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850155122869403648 |
|---|---|
| author | Jack M. Vice Gita Sukthankar |
| author_facet | Jack M. Vice Gita Sukthankar |
| author_sort | Jack M. Vice |
| collection | DOAJ |
| description | Navigating uneven, unstructured terrain with dynamic obstacles remains a challenge for autonomous mobile robots. This article introduces <b>D</b>ynamic <b>Un</b>structured <b>E</b>nvironment (DUnE) for evaluating the performance of off-road navigation systems in simulation. DUnE is a versatile software framework that implements the Gymnasium reinforcement learning (RL) interface for ROS 2, incorporating unstructured Gazebo simulation environments and dynamic obstacle integration to advance off-road navigation research. The testbed automates key performance metric logging and provides semi-automated trajectory generation for dynamic obstacles including simulated human actors. It supports multiple robot platforms and five distinct unstructured environments, ranging from forests to rocky terrains. A baseline reinforcement learning agent demonstrates the framework’s effectiveness by performing pointgoal navigation with obstacle avoidance across various terrains. By providing an RL interface, dynamic obstacle integration, specialized navigation tasks, and comprehensive metric tracking, DUnE addresses significant gaps in existing simulation tools. |
| format | Article |
| id | doaj-art-8fb6861c55db4c12af2ce4e8d7f47d1d |
| institution | OA Journals |
| issn | 2218-6581 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Robotics |
| spelling | doaj-art-8fb6861c55db4c12af2ce4e8d7f47d1d2025-08-20T02:25:02ZengMDPI AGRobotics2218-65812025-03-011443510.3390/robotics14040035DUnE: A Versatile Dynamic Unstructured Environment for Off-Road NavigationJack M. Vice0Gita Sukthankar1Department of Computer Science, University of Central Florida, Orlando, FL 32816, USADepartment of Computer Science, University of Central Florida, Orlando, FL 32816, USANavigating uneven, unstructured terrain with dynamic obstacles remains a challenge for autonomous mobile robots. This article introduces <b>D</b>ynamic <b>Un</b>structured <b>E</b>nvironment (DUnE) for evaluating the performance of off-road navigation systems in simulation. DUnE is a versatile software framework that implements the Gymnasium reinforcement learning (RL) interface for ROS 2, incorporating unstructured Gazebo simulation environments and dynamic obstacle integration to advance off-road navigation research. The testbed automates key performance metric logging and provides semi-automated trajectory generation for dynamic obstacles including simulated human actors. It supports multiple robot platforms and five distinct unstructured environments, ranging from forests to rocky terrains. A baseline reinforcement learning agent demonstrates the framework’s effectiveness by performing pointgoal navigation with obstacle avoidance across various terrains. By providing an RL interface, dynamic obstacle integration, specialized navigation tasks, and comprehensive metric tracking, DUnE addresses significant gaps in existing simulation tools.https://www.mdpi.com/2218-6581/14/4/35off-road navigationunstructured terrainrobotic simulatorsreinforcement learning benchmarks |
| spellingShingle | Jack M. Vice Gita Sukthankar DUnE: A Versatile Dynamic Unstructured Environment for Off-Road Navigation Robotics off-road navigation unstructured terrain robotic simulators reinforcement learning benchmarks |
| title | DUnE: A Versatile Dynamic Unstructured Environment for Off-Road Navigation |
| title_full | DUnE: A Versatile Dynamic Unstructured Environment for Off-Road Navigation |
| title_fullStr | DUnE: A Versatile Dynamic Unstructured Environment for Off-Road Navigation |
| title_full_unstemmed | DUnE: A Versatile Dynamic Unstructured Environment for Off-Road Navigation |
| title_short | DUnE: A Versatile Dynamic Unstructured Environment for Off-Road Navigation |
| title_sort | dune a versatile dynamic unstructured environment for off road navigation |
| topic | off-road navigation unstructured terrain robotic simulators reinforcement learning benchmarks |
| url | https://www.mdpi.com/2218-6581/14/4/35 |
| work_keys_str_mv | AT jackmvice duneaversatiledynamicunstructuredenvironmentforoffroadnavigation AT gitasukthankar duneaversatiledynamicunstructuredenvironmentforoffroadnavigation |