Risk-Guided Diffusion: Toward Deploying Robot Foundation Models In Space, Where Failure Is Not An Option

Rohan Thakker, Adarsh Patnaik, Vince Kurtz, Jonas Frey, Jonathan Becktor, Sangwoo Moon, Rob Royce, Marcel Kaufmann, Georgios Georgakis, Pascal Roth, Joel W. Burdick, Marco Hutter, Shehryar Khattak

Keywords: Embodied AI, Autonomous Robotic Space Exploration, Diffusion, Risk-aware Planning

TL;DR: Used physics-based risk assesment to increase safety of robot navigation foundation models using inference time compute.

Abstract: Safe, reliable navigation in extreme, unfamiliar terrain is required for future robotic space exploration missions. Recent generative-AI methods learn semantically aware navigation policies from large, cross-embodiment datasets, but offer limited safety guarantees. Inspired by human cognitive science [1], we propose a risk-guided diffusion framework that fuses a fast, learned “System-1” with a slow, physics-based “System-2,” sharing computation at both training and inference to couple adaptability with formal safety. Hardware experiments conducted at the NASA JPL’s Mars-analog facility, Mars Yard, show that our approach reduces failure rates by up to 4× while matching the goal-reaching performance of learning-based robotic models by leveraging inference-time compute without any additional training.

Submission Number: 9