Reachability Verification Based Reliability Assessment for Deep Reinforcement Learning Controlled Robotics and Autonomous Systems
Deep Reinforcement Learning (DRL) has achieved impressive performance in robotics and autonomous systems (RAS). A key challenge to its deployment in real-life operations is the presence of spuriously unsafe DRL policies. Unexplored states may lead the agent to make wrong decisions that could result in hazards, especially in applications where DRL-trained end-to-end controllers govern the behaviour of RAS. This paper proposes a novel quantitative reliability assessment framework for DRL-controlled RAS, leveraging verification evidence generated from formal reliability analysis of neural networks. A two-level verification framework is introduced to check the safety property with respect to inaccurate observations that are due to, e.g., environmental noise and state changes. Reachability verification tools are leveraged locally to generate safety evidence of trajectories. In contrast, at the global level, we quantify the overall reliability as an aggregated metric of local safety evidence, corresponding to a set of distinct tasks and their occurrence probabilities. The effectiveness of the proposed verification framework is demonstrated and validated via experiments on real RAS.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep Reinforcement LearningSimilar Papers 제목 키워드 기반
Unifying Qualitative and Quantitative Safety Verification of DNN-Controlled Systems
The rapid advance of deep reinforcement learning techniques enables the oversight of safety-critical systems through the utilization of Deep Neural Networks (DNNs). This underscores the pressing need to promptly establis…
Deep Reinforcement LearningvalidNeuro-Reachability of Networked Microgrids
A neural ordinary differential equations network (ODE-Net)-enabled reachability method (Neuro-Reachability) is devised for the dynamic verification of networked microgrids (NMs) with unidentified subsystems and heterogen…
Model DiscoverySafety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation
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 safet…
Reinforcement LearningRobot NavigationSolving reachability problems on data-aware workflows
Recent advances in the field of Business Process Management have brought about several suites able to model complex data objects along with the traditional control flow perspective. Nonetheless, when it comes to formal v…
ManagementA New Strategy for Verifying Reach-Avoid Specifications in Neural Feedback Systems
Forward reachability analysis is the predominant approach for verifying reach-avoid properties in neural feedback systems (dynamical systems controlled by neural networks). This dominance stems from the limited scalabili…