mlsanityData to 7 Oct 2026

Online Safety Property Collection and Refinement for Safe Deep Reinforcement Learning in Mapless Navigation

arXiv 2302.06695 ↗First posted 13 Feb 2023cs.AI cs.ROcited by 7

Not on the map. Why?

Abstract (arXiv)

Safety is essential for deploying Deep Reinforcement Learning (DRL) algorithms in real-world scenarios. Recently, verification approaches have been proposed to allow quantifying the number of violations of a DRL policy over input-output relationships, called properties. However, such properties are hard-coded and require task-level knowledge, making their application intractable in challenging safety-critical tasks. To this end, we introduce the Collection and Refinement of Online Properties (CROP) framework to design properties at training time. CROP employs a cost signal to identify unsafe interactions and use them to shape safety properties. Hence, we propose a refinement strategy to combine properties that model similar unsafe interactions. Our evaluation compares the benefits of computing the number of violations using standard hard-coded properties and the ones generated with CROP. We evaluate our approach in several robotic mapless navigation tasks and demonstrate that the violation metric computed with CROP allows higher returns and lower violations over previous Safe DRL approaches.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 17 of its 34 references that are in the map. First posted on arXiv 13 Feb 2023.

Builds on

17 of 34 references.

References · 17

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  4. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  5. 2018Reward Constrained Policy Optimizationcited by 397
  6. 2020Responsive Safety in Reinforcement Learning by PID Lagrangian Methodscited by 302
  7. 2019Algorithms for Verifying Deep Neural Networkscited by 221
  8. 2019IPO: Interior-point Policy Optimization under Constraintscited by 119
  9. 2016Deep Reinforcement Learning with Successor Features for Navigation across Similar Environmentscited by 50
  10. 2022Verifying Learning-Based Robotic Navigation Systemscited by 33
  11. 2021Direct Behavior Specification via Constrained Reinforcement Learningcited by 30
  12. 2021Safe Reinforcement Learning using Formal Verification for Tissue Retraction in Autonomous Robotic-Assisted Surgerycited by 22
5 more
  1. 2023The #DNN-Verification Problem: Counting Unsafe Inputs for Deep Neural Networkscited by 19
  2. 2021Towards Hierarchical Task Decomposition using Deep Reinforcement Learning for Pick and Place Subtaskscited by 13
  3. 2021Centralizing State-Values in Dueling Networks for Multi-Robot Reinforcement Learning Mapless Navigationcited by 13
  4. 2021Curriculum Learning for Safe Mapless Navigationcited by 11
  5. 2021Benchmarking Safe Deep Reinforcement Learning in Aquatic Navigationcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 1; 2025: 2; 2026: 1.

7 papers.

  1. 2023Enumerating Safe Regions in Deep Neural Networks with Provable Probabilistic Guaranteescited by 19
  2. 2023Safe Deep Reinforcement Learning by Verifying Task-Level Propertiescited by 9
  3. 2024Improving Policy Optimization via varepsilon-Retraincited by 5
  4. 2025Online inductive learning from answer sets for efficient reinforcement learning explorationcited by 4
  5. 2025Designing Control Barrier Function via Probabilistic Enumeration for Safe Reinforcement Learning Navigationcited by 3
  6. 2023Scaling #DNN-Verification Tools with Efficient Bound Propagation and Parallel Computingcited by 1
  7. 2026Probabilistic Verification of Recurrent Neural Networks for Single and Multi-Agent Reinforcement Learningcited by 0