Safety filtering of robotic manipulation under environment uncertainty: a computational approach

2025-09-16

AI Summary

Safety filters often fail in dynamic, unstructured environments due to uncertainty in physical parameters—e.g., object mass and friction coefficients—leading to unsafe control actions. Method: We propose a safety-filtering framework grounded in high-fidelity physics simulation. It innovatively combines dense rollout with parallel sparse re-evaluation at critical state transitions; introduces a generalized safety factor unifying grasp stability and actuator constraints; and employs exploratory actions to actively reduce key parameter uncertainties. Contribution/Results: Evaluated in dual-arm manipulation simulations, the framework efficiently identifies and filters unsafe trajectories induced by parametric uncertainty. It significantly improves control safety and system scalability while providing a robust, formally verifiable safety assurance mechanism for real-world robotic manipulation.

Technology Category

• Natural Language Processing: Safety and Robustness
• Intelligent Robots: Manipulation
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Security and Privacy: Large-scale security measurements
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Robotic manipulation in dynamic and unstructured environments requires safety mechanisms that exploit what is known and what is uncertain about the world. Existing safety filters often assume full observability, limiting their applicability in real-world tasks. We propose a physics-based safety filtering scheme that leverages high-fidelity simulation to assess control policies under uncertainty in world parameters. The method combines dense rollout with nominal parameters and parallelizable sparse re-evaluation at critical state-transitions, quantified through generalized factors of safety for stable grasping and actuator limits, and targeted uncertainty reduction through probing actions. We demonstrate the approach in a simulated bimanual manipulation task with uncertain object mass and friction, showing that unsafe trajectories can be identified and filtered efficiently. Our results highlight physics-based sparse safety evaluation as a scalable strategy for safe robotic manipulation under uncertainty.

Problem

• Develops safety filters for robotic manipulation under environmental uncertainty
• Addresses limitations of full observability assumptions in existing methods
• Proposes physics-based evaluation for safe control under parameter uncertainty

Innovation

• Physics-based safety filtering scheme
• High-fidelity simulation under uncertainty
• Sparse re-evaluation with safety factors