RoboRAN: A Unified Robotics Framework for Reinforcement Learning-Based Autonomous Navigation

Matteo El-Hariry, Antoine Richard, Ricard Marsal, Luis Felipe Wolf Batista, Matthieu Geist, Cédric Pradalier, Miguel Olivares-Mendez

Abstract: Autonomous robots must navigate and operate in diverse environments, from terrestrial and aquatic settings to aerial and space domains. While Reinforcement Learning (RL) has shown promise in training policies for specific autonomous robots, existing frameworks and benchmarks are often constrained to unique platforms, limiting generalization and fair comparisons across different mobility systems. In this paper, we present a multi-domain framework for training, evaluating and deploying RL-based navigation policies across diverse robotic platforms and operational environments. Our work presents four key contributions: (1) a scalable and modular framework, facilitating seamless robot-task interchangeability and reproducible training pipelines; (2) sim-to-real transfer demonstrated through real- world experiments with multiple robots, including a satellite robotic simulator, an unmanned surface vessel, and a wheeled ground vehicle; (3) the release of the first open-source API for deploying IsaacLab-trained policies to real robots, enabling lightweight inference and rapid field validation; and (4) uniform tasks and metrics for cross-medium evaluation, through a unified evaluation testbed to assess performance of navigation tasks in diverse operational conditions (aquatic, terrestrial and space). By ensuring consistency between simulation and real-world deployment, RoboRAN lowers the barrier to developing adaptable RL-based navigation strategies. Its modular design enables straightforward integration of new robots and tasks through predefined templates, fostering reproducibility and extension to diverse domains. To support the community, we release RoboRAN as open-source.

Submission Length: Regular submission (no more than 12 pages of main content)

Changes Since Last Submission:

### Summary of Changes Addressing Reviews
- Added a future work paragraph on multi-task and transfer learning possibilities (in the **Conclusions** section).
- Included implementation details and examples to show integration simplicity (**Appendix A7**).
- Replaced the claim with a more precise statement about modularity in the list of contributions (**Section 1 – Introduction**).
- Rephrased the robustness claim throughout the paper (**Sections 3.4 and Appendix A3**).

All changes to the original paper are highlighted in **blue**.

-------

## Camera ready additions - minor revision required by Editor
- We added a paragraph (3.7) titled "Relation to Isaac Lab" to answer the Editor's request to provide a clear distinction between our framework and the Isaac Lab baseline.

Assigned Action Editor: ~Christopher_Mutschler1

Submission Number: 5685