mlsanityData to 14 Oct 2026

Reachability Verification Based Reliability Assessment for Deep Reinforcement Learning Controlled Robotics and Autonomous Systems

arXiv 2210.14991 ↗First posted 26 Oct 2022cs.RO cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 20 of its 43 references that are in the map. First posted on arXiv 26 Oct 2022.

Builds on

20 of 43 references.

References · 20

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2015Continuous control with deep reinforcement learningcited by 3,407
  3. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  4. 2015End-to-End Training of Deep Visuomotor Policiescited by 875
  5. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 807
  6. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 721
  7. 2017Safe Reinforcement Learning via Shieldingcited by 449
  8. 2018Safe Exploration in Continuous Action Spacescited by 247
  9. 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 154
  10. 2020Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learningcited by 103
  11. 2018Reachability Analysis of Deep Neural Networks with Provable Guaranteescited by 93
  12. 2018Verisig: verifying safety properties of hybrid systems with neural network controllerscited by 84
8 more
  1. 2018A Statistical Approach to Assessing Neural Network Robustnesscited by 54
  2. 2021POLAR: A Polynomial Arithmetic Framework for Verifying Neural-Network Controlled Systemscited by 39
  3. 2021Towards Scalable Verification of Deep Reinforcement Learningcited by 33
  4. 2019Statistically Robust Neural Network Classificationcited by 16
  5. 2021Reliability Assessment and Safety Arguments for Machine Learning Components in System Assurancecited by 16
  6. 2019Assessing the Safety and Reliability of Autonomous Vehicles from Road Testingcited by 15
  7. 2021Assessing the Reliability of Deep Learning Classifiers Through Robustness Evaluation and Operational Profilescited by 11
  8. 2021A Survey of Deep Reinforcement Learning Algorithms for Motion Planning and Control of Autonomous Vehiclescited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Probabilistic Robustness in Deep Learning: A Concise yet Comprehensive Guidecited by 6
  2. 2025TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learningcited by 3
  3. 2026Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigationcited by 0