Gameplay Filters：通过对抗式想象实现鲁棒的零样本安全性
Gameplay Filters: Robust Zero-Shot Safety through Adversarial Imagination
AI总结：
针对现有腿式机器人安全过滤器依赖降阶模型、鲁棒性不足的问题，本文提出gameplay filter，通过与虚拟对手的对抗推演预判风险，实现了36自由度四足机器人的全阶安全过滤，在大扰动下零样本安全性更优。
摘要：
尽管近年来基于学习的机器人控制取得了显著进展，但确保对分布外条件的鲁棒性仍是一个未解决的挑战。安全过滤器原则上可以通过覆写不安全动作，防止任意控制策略发生灾难性故障，但针对复杂（如腿式）机器人动力学的现有解决方案并未覆盖完整运动范围，而是依赖局部的降阶模型。这类过滤器往往过度限制了敏捷性，且在偏离标称条件受到扰动时仍可能失效。本文提出了gameplay filter（博弈式过滤器），这是一类新型预测性安全过滤器，它持续推演其经仿真训练的安全策略与一个协同训练的虚拟对手之间的假设对抗——该虚拟对手被训练以触发最坏情况事件和 sim-to-real（仿真到现实）误差——并排除后续会导致故障的动作。我们通过首个面向36自由度四足动力学的全阶安全过滤器，验证了该方法的可扩展性和鲁棒性。在两种不同四足平台上的实物实验表明，gameplay filter在拉扯、未建模地形等大扰动下具有更优的零样本效能。实验视频和开源软件可在线获取：https://saferobotics.org/research/gameplay-filter
英文摘要：
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
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
