Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation

• URL: http://arxiv.org/abs/2605.14174v1
• Date: Wed, 13 May 2026 22:53:47 GMT
• Title: Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation
• Abstract summary: We propose a framework that trains risk-sensitive policies through Conditional Value-at-Risk (CVaR) constrained optimization on an off-policy TD3 backbone.<n>During training, the policy is optimized under CVaR constraints on cumulative costs, promoting sensitivity to high-cost tail outcomes.<n>A key finding is that policies trained with CVaR constraints maintain larger safety margins from obstacles across evaluated states.
• Score: 13.151825012034886
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Safe navigation for mobile robots demands policies that remain reliable under the high-consequence perception uncertainty of cluttered environments. Yet most existing safe reinforcement learning (RL) methods assess safety through average cumulative cost. Such metrics can mask dangerous tail-risk behaviors. To address this, we propose a framework that trains risk-sensitive policies through Conditional Value-at-Risk (CVaR) constrained optimization on an off-policy TD3 backbone and evaluates their safety margins post-training through neural network reachability verification. During training, the policy is optimized under CVaR constraints on cumulative costs, promoting sensitivity to high-cost tail outcomes rather than average behavior alone. After training, we compute action reachable sets under bounded observation uncertainty using Taylor Model analysis, yielding a safety rate metric that quantifies the proportion of evaluated states at which the policy's reachable action set remains within prescribed safety margins. A key finding is that policies trained with CVaR constraints maintain larger safety margins from obstacles across evaluated states. This makes them significantly more amenable to formal reachability verification. Experiments across ten navigation scenarios and six baselines show that our method achieves a 98.3\% success rate, the highest safety verification rate among all compared methods, while revealing that average cost rankings and reachability-based safety rankings can diverge. This indicates that reachability verification captures risks which are missed by empirical cost metrics alone. We further validate our approach on a physical Clearpath Jackal robot, demonstrating successful sim-to-real transfer.

Related papers

• Self-Aware Active Learning Enables Continual Improvement in Autonomous Driving [12.669051115615176]
  Self-aware guided exploration (SAGE) is an active learning framework for post-training adaptation in autonomous driving.<n>Curiosity adaptively calibrates the intervention threshold for fear, allowing the agent to regulate risk in a context-dependent manner.<n>Fear is integrated into policy optimization and evaluation as a safety-oriented constraint to reduce performance regressions.
  arXiv  Detail & Related papers  (2026-08-30T13:01:32Z)
• Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability [79.08785366532287]
  We propose a lightweight risk-gated reinforcement learning approximation for risk-sensitive control under partial observability.<n>We evaluate the approach in two safety-critical partially observable domains: automated glucose regulation and safety-constrained navigation.
  arXiv  Detail & Related papers  (2026-05-14T01:23:09Z)
• SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning [30.037309138373754]
  Vision-language-action models (VLAs) show potential as generalist robot policies.<n>These models pose extreme safety challenges during real-world deployment, including the risk of harm to the environment, the robot itself, and humans.<n>We address this by exploring an integrated safety approach (ISA), systematically modeling safety requirements, then actively eliciting diverse unsafe behaviors.
  arXiv  Detail & Related papers  (2025-03-05T13:16:55Z)
• TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning [16.176812250762666]
  We propose a trust region-based safe RL method with CVaR constraints, called TRC. We first derive the upper bound on CVaR and then approximate the upper bound in a differentiable form in a trust region. Compared to other safe RL methods, the performance is improved by 1.93 times while the constraints are satisfied in all experiments.
  arXiv  Detail & Related papers  (2023-12-01T04:40:47Z)
• Safety Margins for Reinforcement Learning [53.10194953873209]
  We show how to leverage proxy criticality metrics to generate safety margins. We evaluate our approach on learned policies from APE-X and A3C within an Atari environment.
  arXiv  Detail & Related papers  (2023-07-25T16:49:54Z)
• Safe Deep Reinforcement Learning by Verifying Task-Level Properties [84.64203221849648]
  Cost functions are commonly employed in Safe Deep Reinforcement Learning (DRL) The cost is typically encoded as an indicator function due to the difficulty of quantifying the risk of policy decisions in the state space. In this paper, we investigate an alternative approach that uses domain knowledge to quantify the risk in the proximity of such states by defining a violation metric.
  arXiv  Detail & Related papers  (2023-02-20T15:24:06Z)
• Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning [64.11013095004786]
  We propose a dual-agent safe reinforcement learning strategy consisting of a baseline and a safe agent. Such a decoupled framework enables high flexibility, data efficiency and risk-awareness for RL-based control. The proposed method outperforms the state-of-the-art safe RL algorithms on difficult robot locomotion and manipulation tasks.
  arXiv  Detail & Related papers  (2022-12-14T03:11:25Z)
• Safe Reinforcement Learning via Confidence-Based Filters [78.39359694273575]
  We develop a control-theoretic approach for certifying state safety constraints for nominal policies learned via standard reinforcement learning techniques. We provide formal safety guarantees, and empirically demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2022-07-04T11:43:23Z)
• Conservative Safety Critics for Exploration [120.73241848565449]
  We study the problem of safe exploration in reinforcement learning (RL) We learn a conservative safety estimate of environment states through a critic. We show that the proposed approach can achieve competitive task performance while incurring significantly lower catastrophic failure rates.
  arXiv  Detail & Related papers  (2020-10-27T17:54:25Z)
• Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach [2.741266294612776]
  We propose a model-free safety specification method that learns the maximal probability of safe operation. Our approach constructs a Lyapunov function with respect to a safe policy to restrain each policy improvement stage. It yields a sequence of safe policies that determine the range of safe operation, called the safe set.
  arXiv  Detail & Related papers  (2020-02-24T09:20:03Z)

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.