mlsanityData to 7 Oct 2026

Approximating Safety Feedback Without a Safety Oracle via Model Predictive Control

arXiv 2510.20955 ↗First posted 23 Oct 2025cs.LG cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Safe decision-making algorithms for control of mobile robots often require the existence of feedback to verify the safety of proposed actions. This feedback is assumed to be directly available during the development or deployment of the control system. It can take the form of either an explicit constraint formulation or a set of hand-labeled safety data, both of which can be inaccurate or time consuming to produce. Many recently developed simulators can handle complex interactions and varied environments. These environments have implicit safety constraints that may be hard to model. By leveraging one of these simulators, we can construct a proxy for a safety function that bypasses the need for hand designed feedback in capturing these constraints. We present an algorithm that approximates safety by using reversibility and a positive-invariance assumption on the unsafe state space. This method employs the Model-Predictive Path Integral algorithm (MPPI) to establish this reversibility and verify a proposed action. First the action is projected via the simulator to a future state. Then if MPPI can find a path back to a previous state in the trajectory, that state is guaranteed to be outside the unsafe (positive invariant) set. Experimental results demonstrate that the proposed algorithm can approximate the performance of a safety oracle while avoiding classification of unsafe states as safe.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 25 references that are in the map. First posted on arXiv 23 Oct 2025.

Builds on

16 of 25 references.

References · 16

  1. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,777
  2. 2017Safe Reinforcement Learning via Shieldingcited by 427
  3. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
  4. 2019Control Barrier Functions: Theory and Applicationscited by 332
  5. 2017Hamilton-Jacobi Reachability: A Brief Overview and Recent Advancescited by 186
  6. 2020Safe Reinforcement Learning in Constrained Markov Decision Processescited by 109
  7. 2020Learning to be Safe: Deep RL with a Safety Criticcited by 109
  8. 2020Conservative Safety Critics for Explorationcited by 107
  9. 2017Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learningcited by 86
  10. 2016Safe Exploration in Finite Markov Decision Processes with Gaussian Processescited by 72
  11. 2019Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamicscited by 45
  12. 2022When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learningcited by 20
4 more
  1. 2021There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learningcited by 17
  2. 2024Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learningcited by 11
  3. 2022Provable Safe Reinforcement Learning with Binary Feedbackcited by 7
  4. 2024Long-term Safe Reinforcement Learning with Binary Feedbackcited by 4

Built on by

Not cited yet.