Gameplay Filters: Robust Zero-Shot Safety through Adversarial Imagination

• URL: http://arxiv.org/abs/2405.00846v3
• Date: Thu, 29 Aug 2024 15:53:29 GMT
• Title: Gameplay Filters: Robust Zero-Shot Safety through Adversarial Imagination
• Authors: Duy P. Nguyen, Kai-Chieh Hsu, Wenhao Yu, Jie Tan, Jaime F. Fisac,
• Abstract summary: This paper presents a new class of predictive safety filter that continually plays out hypothetical matches between its simulation-trained safety strategy and a virtual adversary. We demonstrate the scalability and robustness of the approach with a first-of-its-kind full-order safety filter for (36-D) quadrupedal dynamics.
• Score: 12.548355269509882
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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 it to fail 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.

Related papers

• Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysis [6.267574471145217]
  Hamilton-Jacobi (H) reachability is a rigorous framework that enables robots to simultaneously detect unsafe states and generate actions. We propose La Safety Filters, a latent-space reachability that operates directly on raw observation data.
  arXiv  Detail & Related papers  (2025-02-02T22:00:20Z)
• Pre-Trained Vision Models as Perception Backbones for Safety Filters in Autonomous Driving [2.4381063627159523]
  Safety remains a major concern in end-to-end vision-based autonomous driving. We use frozen pre-trained vision representation models as perception backbones to design vision-based safety filters. We empirically evaluate the offline performance of four common pre-trained vision models in this context.
  arXiv  Detail & Related papers  (2024-10-29T22:59:23Z)
• ReGentS: Real-World Safety-Critical Driving Scenario Generation Made Stable [88.08120417169971]
  Machine learning based autonomous driving systems often face challenges with safety-critical scenarios that are rare in real-world data. This work explores generating safety-critical driving scenarios by modifying complex real-world regular scenarios through trajectory optimization. Our approach addresses unrealistic diverging trajectories and unavoidable collision scenarios that are not useful for training robust planner.
  arXiv  Detail & Related papers  (2024-09-12T08:26:33Z)
• SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systems [15.782203322922017]
  We propose SAFE-GIL, a design-time method to learn safety-aware behavior cloning policies. We inject adversarial disturbance in the system during data collection to guide the expert towards safety-critical states. This disturbance injection simulates potential policy errors that the system might encounter during the test time.
  arXiv  Detail & Related papers  (2024-04-08T07:25:25Z)
• Uniformly Safe RL with Objective Suppression for Multi-Constraint Safety-Critical Applications [73.58451824894568]
  The widely adopted CMDP model constrains the risks in expectation, which makes room for dangerous behaviors in long-tail states. In safety-critical domains, such behaviors could lead to disastrous outcomes. We propose Objective Suppression, a novel method that adaptively suppresses the task reward maximizing objectives according to a safety critic.
  arXiv  Detail & Related papers  (2024-02-23T23:22:06Z)
• SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries [94.84458417662407]
  We introduce SAFE-SIM, a controllable closed-loop safety-critical simulation framework. Our approach yields two distinct advantages: 1) generating realistic long-tail safety-critical scenarios that closely reflect real-world conditions, and 2) providing controllable adversarial behavior for more comprehensive and interactive evaluations. We validate our framework empirically using the nuScenes and nuPlan datasets across multiple planners, demonstrating improvements in both realism and controllability.
  arXiv  Detail & Related papers  (2023-12-31T04:14:43Z)
• Modular Control Architecture for Safe Marine Navigation: Reinforcement Learning and Predictive Safety Filters [0.0]
  Reinforcement learning is increasingly used to adapt to complex scenarios, but standard frameworks ensuring safety and stability are lacking. Predictive Safety Filters (PSF) offer a promising solution, ensuring constraint satisfaction in learning-based control without explicit constraint handling. We apply this approach to marine navigation, combining RL with PSF on a simulated Cybership II model. Results demonstrate the PSF's effectiveness in maintaining safety without hindering the RL agent's learning rate and performance, evaluated against a standard RL agent without PSF.
  arXiv  Detail & Related papers  (2023-12-04T12:37:54Z)
• Safe Deep Policy Adaptation [7.2747306035142225]
  Policy adaptation based on reinforcement learning (RL) offers versatility and generalizability but presents safety and robustness challenges. We propose SafeDPA, a novel RL and control framework that simultaneously tackles the problems of policy adaptation and safe reinforcement learning. We provide theoretical safety guarantees of SafeDPA and show the robustness of SafeDPA against learning errors and extra perturbations.
  arXiv  Detail & Related papers  (2023-10-08T00:32:59Z)
• Learning Vision-based Pursuit-Evasion Robot Policies [54.52536214251999]
  We develop a fully-observable robot policy that generates supervision for a partially-observable one. We deploy our policy on a physical quadruped robot with an RGB-D camera on pursuit-evasion interactions in the wild.
  arXiv  Detail & Related papers  (2023-08-30T17:59:05Z)
• Nonprehensile Planar Manipulation through Reinforcement Learning with Multimodal Categorical Exploration [8.343657309038285]
  Reinforcement Learning is a powerful framework for developing such robot controllers. We propose a multimodal exploration approach through categorical distributions, which enables us to train planar pushing RL policies. We show that the learned policies are robust to external disturbances and observation noise, and scale to tasks with multiple pushers.
  arXiv  Detail & Related papers  (2023-08-04T16:55:00Z)
• A Multiplicative Value Function for Safe and Efficient Reinforcement Learning [131.96501469927733]
  We propose a safe model-free RL algorithm with a novel multiplicative value function consisting of a safety critic and a reward critic. The safety critic predicts the probability of constraint violation and discounts the reward critic that only estimates constraint-free returns. We evaluate our method in four safety-focused environments, including classical RL benchmarks augmented with safety constraints and robot navigation tasks with images and raw Lidar scans as observations.
  arXiv  Detail & Related papers  (2023-03-07T18:29:15Z)
• Modular Safety-Critical Control of Legged Robots [0.0]
  Safety concerns during the operation of legged robots must be addressed to enable their widespread use. This study presents a modular safety filter to improve the safety of a legged robot, i.e., reduce the chance of a fall.
  arXiv  Detail & Related papers  (2023-03-04T11:36:21Z)
• In-Distribution Barrier Functions: Self-Supervised Policy Filters that Avoid Out-of-Distribution States [84.24300005271185]
  We propose a control filter that wraps any reference policy and effectively encourages the system to stay in-distribution with respect to offline-collected safe demonstrations. Our method is effective for two different visuomotor control tasks in simulation environments, including both top-down and egocentric view settings.
  arXiv  Detail & Related papers  (2023-01-27T22:28:19Z)
• ISAACS: Iterative Soft Adversarial Actor-Critic for Safety [0.9217021281095907]
  This work introduces a novel approach enabling scalable synthesis of robust safety-preserving controllers for robotic systems. A safety-seeking fallback policy is co-trained with an adversarial "disturbance" agent that aims to invoke the worst-case realization of model error. While the learned control policy does not intrinsically guarantee safety, it is used to construct a real-time safety filter.
  arXiv  Detail & Related papers  (2022-12-06T18:53:34Z)
• DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality [64.51295032956118]
  We train a policy that can perform robust dexterous manipulation on an anthropomorphic robot hand. Our work reaffirms the possibilities of sim-to-real transfer for dexterous manipulation in diverse kinds of hardware and simulator setups.
  arXiv  Detail & Related papers  (2022-10-25T01:51:36Z)
• Safe Reinforcement Learning Using Black-Box Reachability Analysis [20.875010584486812]
  Reinforcement learning (RL) is capable of sophisticated motion planning and control for robots in uncertain environments. To justify widespread deployment, robots must respect safety constraints without sacrificing performance. We propose a Black-box Reachability-based Safety Layer (BRSL) with three main components.
  arXiv  Detail & Related papers  (2022-04-15T10:51:09Z)
• Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attacks [62.87459235819762]
  In a real-world scenario like autonomous driving, more attention should be devoted to real-world adversarial examples (RWAEs) This paper presents an in-depth evaluation of the robustness of popular SS models by testing the effects of both digital and real-world adversarial patches.
  arXiv  Detail & Related papers  (2021-08-13T11:49:09Z)
• Adaptive Feature Alignment for Adversarial Training [56.17654691470554]
  CNNs are typically vulnerable to adversarial attacks, which pose a threat to security-sensitive applications. We propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths. Our method is trained to automatically align features of arbitrary attacking strength.
  arXiv  Detail & Related papers  (2021-05-31T17:01:05Z)

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.