Institution profile

Naval Research Laboratory

Academic institutionnorthamerica · us
Official website
Research library62linked papers
Opportunities0open roles
Selected work

Representative Papers

Crossing the Sim2Real Gap Between Simulation and Ground Testing to Space Deployment of Autonomous Free-flyer Control

Dec 03, 2025

To address the Sim2Real gap hindering reinforcement learning (RL) policy deployment in space autonomous control, this paper proposes an end-to-end simulation-to-reality transfer framework. We build a high-fidelity microgravity physics simulator using NVIDIA Omniverse, integrate curriculum learning with Monte Carlo random sampling for robust policy training, and design a lightweight neural controller that replaces NASA’s Astrobee standard controller. Our approach achieves, for the first time, zero-shot, on-orbit deployment of a deep RL policy—from ground-based simulation directly to the International Space Station—successfully completing free-flying navigation tasks without fine-tuning. The core contribution is the first GPU-accelerated Sim2Real training pipeline tailored for space operations, significantly enhancing policy generalization and deployment reliability. This establishes a scalable, online-tuning-free autonomous control paradigm for in-space servicing, assembly, and manufacturing (ISAM) missions.

2 citationsRead paper

Autonomous Planning In-space Assembly Reinforcement-learning free-flYer (APIARY) International Space Station Astrobee Testing

Dec 03, 2025

This work addresses the challenge of autonomous control for free-flying robots in microgravity space environments. We propose an end-to-end, six-degree-of-freedom motion control framework based on reinforcement learning (RL), specifically leveraging the Proximal Policy Optimization (PPO) algorithm within an actor-critic architecture. Training is conducted in NVIDIA Isaac Lab under randomized target poses and robot mass parameters. The learned policy is rigorously validated through ground-based testing and, critically, via on-orbit experiments aboard the International Space Station (ISS) using the Astrobee robot—marking the first deployment of an RL policy for real-space operation. Our approach enables rapid, minute-scale customization of mission-specific behaviors, achieving centimeter-level positional accuracy and sub-degree attitude error. It significantly improves responsiveness and environmental adaptability compared to conventional methods. This work establishes a scalable, simulation-to-reality transferable intelligent control paradigm for future autonomous space operations, on-orbit servicing, and agile orbital logistics.

2 citationsRead paper

On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning

Jan 11, 2026arXiv.org

This work proposes TT-VLA, a novel framework that introduces test-time reinforcement learning to vision-language-action (VLA) models, enabling online adaptation during deployment without requiring retraining. Existing VLA models lack the ability to adapt at test time, limiting their robustness in dynamic environments. TT-VLA addresses this by fine-tuning policies at inference using task-progress signals, integrating a dense reward mechanism with prior-preserving techniques to maintain stable and effective behavior. Experiments demonstrate that the method significantly improves task success rates, policy stability, and adaptability to unseen environmental dynamics in both simulated and real-world settings, thereby enhancing the practical deployability of VLA models.

1 citationsRead paper
Recent publications

Latest Papers