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

• URL: http://arxiv.org/abs/2506.17601v1
• Date: Sat, 21 Jun 2025 05:39:04 GMT
• Title: Risk-Guided Diffusion: Toward Deploying Robot Foundation Models in Space, Where Failure Is Not An Option
• Authors: Rohan Thakker, Adarsh Patnaik, Vince Kurtz, Jonas Frey, Jonathan Becktor, Sangwoo Moon, Rob Royce, Marcel Kaufmann, Georgios Georgakis, Pascal Roth, Joel Burdick, Marco Hutter, Shehryar Khattak,
• Abstract summary: Recent generative-AI methods learn semantically aware navigation policies from large, cross-embodiment datasets.<n>Inspired by human cognitive science, we propose a risk-guided diffusion framework that fuses a fast, learned "System-1" with a slow, physics-based "System-2"
• Score: 14.217389097651573
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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, 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 $4\times$ while matching the goal-reaching performance of learning-based robotic models by leveraging inference-time compute without any additional training.

Related papers

• You Only Crash Once v2: Perceptually Consistent Strong Features for One-Stage Domain Adaptive Detection of Space Terrain [4.339510167603377]
  In-situ detection of planetary, lunar, and small-body surface terrain is crucial for autonomous spacecraft applications.<n>Unsupervised Domain Adaptation (UDA) offers a promising solution by facilitating model training with disparate data sources.<n>We propose novel additions to the VSA scheme that enhance terrain detection capabilities under UDA.
  arXiv  Detail & Related papers  (2025-01-23T14:58:49Z)
• ReGentS: Real-World Safety-Critical Driving Scenario Generation Made Stable [88.08120417169971]
  Machine learning based autonomous driving systems often face challenges with safety-critical scenarios that are rare in real-world data. This work explores generating safety-critical driving scenarios by modifying complex real-world regular scenarios through trajectory optimization. Our approach addresses unrealistic diverging trajectories and unavoidable collision scenarios that are not useful for training robust planner.
  arXiv  Detail & Related papers  (2024-09-12T08:26:33Z)
• SoNIC: Safe Social Navigation with Adaptive Conformal Inference and Constrained Reinforcement Learning [26.554847852013737]
  SoNIC is the first algorithm that integrates adaptive conformal inference and constrained reinforcement learning.<n>Our method achieves a success rate of 96.93%, which is 11.67% higher than the previous state-of-the-art RL method.<n>Our experiments demonstrate that the system can generate robust and socially polite decision-making when interacting with both sparse and dense crowds.
  arXiv  Detail & Related papers  (2024-07-24T17:57:21Z)
• Efficient Real-time Smoke Filtration with 3D LiDAR for Search and Rescue with Autonomous Heterogeneous Robotic Systems [56.838297900091426]
  Smoke and dust affect the performance of any mobile robotic platform due to their reliance on onboard perception systems. This paper proposes a novel modular computation filtration pipeline based on intensity and spatial information.
  arXiv  Detail & Related papers  (2023-08-14T16:48:57Z)
• Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robot Navigation [72.24964965882783]
  Reinforcement learning (RL) is a promising approach for robotic navigation, allowing robots to learn through trial and error.<n>Real-world robotic tasks often suffer from sparse rewards, leading to inefficient exploration and suboptimal policies.<n>We introduce Confidence-Controlled Exploration (CCE), a novel method that improves sample efficiency in RL-based robotic navigation without modifying the reward function.
  arXiv  Detail & Related papers  (2023-06-09T18:45:15Z)
• Incremental 3D Scene Completion for Safe and Efficient Exploration Mapping and Planning [60.599223456298915]
  We propose a novel way to integrate deep learning into exploration by leveraging 3D scene completion for informed, safe, and interpretable mapping and planning. We show that our method can speed up coverage of an environment by 73% compared to the baselines with only minimal reduction in map accuracy. Even if scene completions are not included in the final map, we show that they can be used to guide the robot to choose more informative paths, speeding up the measurement of the scene with the robot's sensors by 35%.
  arXiv  Detail & Related papers  (2022-08-17T14:19:33Z)
• MLNav: Learning to Safely Navigate on Martian Terrains [25.42849032622348]
  We present MLNav, a learning-enhanced path planning framework for safety-critical and resource-limited systems. MLNav makes judicious use of machine learning to enhance the efficiency of path planning while fully respecting safety constraints. We validate in high-fidelity simulations using both real Martian terrain data and a suite of challenging synthetic terrains.
  arXiv  Detail & Related papers  (2022-03-09T07:53:15Z)
• Fail-Safe Human Detection for Drones Using a Multi-Modal Curriculum Learning Approach [1.094245191265935]
  We present KUL-UAVSAFE, a first-of-its-kind dataset for the study of safety-critical people detection by drones. We propose a CNN architecture with cross-fusion highways and introduce a curriculum learning strategy for multi-modal data.
  arXiv  Detail & Related papers  (2021-09-28T12:34:13Z)
• Towards Robust Monocular Visual Odometry for Flying Robots on Planetary Missions [49.79068659889639]
  Ingenuity, that just landed on Mars, will mark the beginning of a new era of exploration unhindered by traversability. We present an advanced robust monocular odometry algorithm that uses efficient optical flow tracking. We also present a novel approach to estimate the current risk of scale drift based on a principal component analysis of the relative translation information matrix.
  arXiv  Detail & Related papers  (2021-09-12T12:52:20Z)
• SABER: Data-Driven Motion Planner for Autonomously Navigating Heterogeneous Robots [112.2491765424719]
  We present an end-to-end online motion planning framework that uses a data-driven approach to navigate a heterogeneous robot team towards a global goal. We use model predictive control (SMPC) to calculate control inputs that satisfy robot dynamics, and consider uncertainty during obstacle avoidance with chance constraints. recurrent neural networks are used to provide a quick estimate of future state uncertainty considered in the SMPC finite-time horizon solution. A Deep Q-learning agent is employed to serve as a high-level path planner, providing the SMPC with target positions that move the robots towards a desired global goal.
  arXiv  Detail & Related papers  (2021-08-03T02:56:21Z)
• Rule-Based Reinforcement Learning for Efficient Robot Navigation with Space Reduction [8.279526727422288]
  In this paper, we focus on efficient navigation with the reinforcement learning (RL) technique. We employ a reduction rule to shrink the trajectory, which in turn effectively reduces the redundant exploration space. Experiments conducted on real robot navigation problems in hex-grid environments demonstrate that RuRL can achieve improved navigation performance.
  arXiv  Detail & Related papers  (2021-04-15T07:40:27Z)
• Learning to be Safe: Deep RL with a Safety Critic [72.00568333130391]
  A natural first approach toward safe RL is to manually specify constraints on the policy's behavior. We propose to learn how to be safe in one set of tasks and environments, and then use that learned intuition to constrain future behaviors.
  arXiv  Detail & Related papers  (2020-10-27T20:53:20Z)
• Learning-to-Fly: Learning-based Collision Avoidance for Scalable Urban Air Mobility [2.117421588033177]
  We present Learning-to-Fly (L2F), a decentralized on-demand airborne collision avoidance framework for multiple UAS. L2F is a two-stage collision avoidance method that consists of: 1) a learning-based decision-making scheme and 2) a distributed, linear programming-based UAS control algorithm. We show the real-time applicability of our method which is $approx!6000times$ faster than the MILP approach and can resolve $100%$ of collisions when there is ample room to maneuver.
  arXiv  Detail & Related papers  (2020-06-23T18:46:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.