mlsanityData to 14 Oct 2026

Gameplay Filters: Robust Zero-Shot Safety through Adversarial Imagination

arXiv 2405.00846 ↗First posted 1 May 2024cs.RO cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

Despite the impressive recent advances in learning-based robot control, ensuring robustness to out-of-distribution conditions remains an open challenge. Safety filters can, in principle, keep arbitrary control policies from incurring catastrophic failures by overriding unsafe actions, but existing solutions for complex (e.g., legged) robot dynamics do not span the full motion envelope and instead rely on local, reduced-order models. These filters tend to overly restrict agility and can still fail when perturbed away from nominal conditions. This paper presents the gameplay filter, a new class of predictive safety filter that continually plays out hypothetical matches between its simulation-trained safety strategy and a virtual adversary co-trained to invoke worst-case events and sim-to-real error, and precludes actions that would cause failures down the line. We demonstrate the scalability and robustness of the approach with a first-of-its-kind full-order safety filter for (36-D) quadrupedal dynamics. Physical experiments on two different quadruped platforms demonstrate the superior zero-shot effectiveness of the gameplay filter under large perturbations such as tugging and unmodeled terrain. Experiment videos and open-source software are available online: https://saferobotics.org/research/gameplay-filter

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 40 of its 52 references that are in the map. First posted on arXiv 1 May 2024.

Builds on

40 of 52 references.

References · 40

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 508
  3. 2019Control Barrier Functions: Theory and Applicationscited by 372
  4. 2023Robots That Ask For Help: Uncertainty Alignment for Large Language Model Plannerscited by 308
  5. 2017Hamilton-Jacobi Reachability: A Brief Overview and Recent Advancescited by 201
  6. 2020Recovery RL: Safe Reinforcement Learning with Learned Recovery Zonescited by 175
  7. 2022Rapid Locomotion via Reinforcement Learningcited by 168
  8. 2023Robot Parkour Learningcited by 149
  9. 2018A predictive safety filter for learning-based control of constrained nonlinear dynamical systemscited by 118
  10. 2020Conservative Safety Critics for Explorationcited by 113
  11. 2020Learning Control Barrier Functions from Expert Demonstrationscited by 92
  12. 2020DeepReach: A Deep Learning Approach to High-Dimensional Reachabilitycited by 91
28 more
  1. 2023The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systemscited by 88
  2. 2024Agile But Safe: Learning Collision-Free High-Speed Legged Locomotioncited by 73
  3. 2021Robust Control Barrier-Value Functions for Safety-Critical Controlcited by 51
  4. 2021Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learningcited by 49
  5. 2014Reach-Avoid Problems with Time-Varying Dynamics, Targets and Constraintscited by 44
  6. 2020Reach-SDP: Reachability Analysis of Closed-Loop Systems with Neural Network Controllers via Semidefinite Programmingcited by 43
  7. 2018Linear model predictive safety certification for learning-based controlcited by 37
  8. 2022Safe Reinforcement Learning for Legged Locomotioncited by 35
  9. 2016Robustness of Control Barrier Functions for Safety Critical Controlcited by 30
  10. 2022ISAACS: Iterative Soft Adversarial Actor-Critic for Safetycited by 28
  11. 2021Run Time Assurance for Safety-Critical Systems: An Introduction to Safety Filtering Approaches for Complex Control Systemscited by 27
  12. 2022Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guaranteescited by 27
  13. 2020Learning Hybrid Control Barrier Functions from Datacited by 24
  14. 2021Safe Occlusion-aware Autonomous Driving via Game-Theoretic Active Perceptioncited by 23
  15. 2022Learning and Deploying Robust Locomotion Policies with Minimal Dynamics Randomizationcited by 17
  16. 2018Permissive Barrier Certificates for Safe Stabilization Using Sum-of-squarescited by 15
  17. 2021Learning Robust Hybrid Control Barrier Functions for Uncertain Systemscited by 14
  18. 2022Sim-to-Real Transfer for Quadrupedal Locomotion via Terrain Transformercited by 14
  19. 2023Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomycited by 10
  20. 2021Model-Free Safety-Critical Control for Robotic Systemscited by 8
  21. 2024Robust-Locomotion-by-Logic: Perturbation-Resilient Bipedal Locomotion via Signal Temporal Logic Guided Model Predictive Controlcited by 8
  22. 2016Correctness Guarantees for the Composition of Lane Keeping and Adaptive Cruise Controlcited by 7
  23. 2021Hybrid zonotopes: a new set representation for reachability analysis of mixed logical dynamical systemscited by 7
  24. 2022Predictive safety filter using system level synthesiscited by 7
  25. 2023Fast, Smooth, and Safe: Implicit Control Barrier Functions through Reach-Avoid Differential Dynamic Programmingcited by 5
  26. 2020Dynamic Walking: Toward Agile and Efficient Bipedal Robotscited by 3
  27. 2015An Iterative Abstraction Algorithm for Reactive Correct-by-Construction Controller Synthesiscited by 2
  28. 2020Eyes-Closed Safety Kernels: Safety for Autonomous Systems Under Loss of Observabilitycited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 12.

16 papers.

Sort:

By area:

  1. 2025Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failurescited by 33
  2. 2026Synthesis and Deployment of Maximal Robust Control Barrier Functions through Adversarial Reinforcement Learningcited by 5
  3. 2025Provably Optimal Reinforcement Learning under Safety Filteringcited by 3
  4. 2025Neural Fidelity Calibration for Informative Sim-to-Real Adaptationcited by 1
  5. 2025Safety-Aware Imitation Learning via MPC-Guided Disturbance Injectioncited by 1
  6. 2026Permissive Safety Through Trusted Inference: Verifiable Belief-Space Neural Safety Filters for Assured Interactive Roboticscited by 1
  7. 2026Selective Agentic Recovery for UAV Autonomy with a Persistent Mission Runtimecited by 1
  8. 2026Efficient Coordination with the System-Level Shared State: An Embodied-AI Native Modular Frameworkcited by 0
  9. 2026Solving Parameter-Robust Avoid Problems with Unknown Feasibility using Reinforcement Learningcited by 0
  10. 2026Shield-Loco: Shielding Locomotion Policies with Predictive Safety Filteringcited by 0
  11. 2026Directional Constraints for Efficient Exploration in Safe Reinforcement Learningcited by 0
  12. 2026No Free Checker: A Survey of Verifiers for Robot Policiescited by 0
4 more
  1. 2026ResSafe: Learning Safety Filtering with Residual Reinforcement Learning for Humanoidscited by 0
  2. 2026Turning Safety into Competence: Minimally Exploitable Robot Policies via Safety-Filtered Reinforcement Learningcited by 0
  3. 2026LEAP-CBF: A Safety Filter for Uncertain Systems with Least-Effort Adversarial Potentialscited by 0
  4. 2026ORACLE: Optimizer-Relative Alignment for Constrained LEarningcited by 0