发表机构
College of Engineering, Carnegie Mellon University; Dartmouth College（卡内基梅隆大学工程学院; 达特茅斯学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对机器人预测失败却无法阻止的问题，提出混合学习-分析框架RAYA，在控制器内嵌入可恢复性裕度并动态调整任务权重，显著提升四旋翼和自动驾驶基准的生存率，并零样本迁移至新场景，硬件实验验证其有效性。
AI 中文摘要
机器人能够预测失败，却仍可能无法阻止失败的发生。当安全机制做出反应时，名义计划可能已经耗尽了恢复所需的控制权限，而固定的任务优先级可能会阻碍任何剩余的响应。我们的关键见解是，这两个方面都是在控制器内部决定的。可恢复性必须在选择动作时告知动作，而不是事后否决它们，并且任务目标必须随着可恢复性的缩减而调整。基于此，我们提出了RAYA，一个混合学习-分析框架，它将一个学习到的有限时域可恢复性裕度置于具有硬约束的最优控制器内，并将其与一个有界的学习调度器配对，该调度器调整任务权重以促进恢复。在跨越四旋翼飞行器和自动驾驶车辆基准的每个控制器的7,200次模拟回合中，RAYA不仅提高了生存率，还将学习到的组件零样本迁移到未见过的轨迹、扰动、模型变化和摩擦布局中。我们开发了RAYA的嵌入式实现，并将其部署在一架35克的Crazyflie四旋翼飞行器上。在40次组合硬件飞行中，在存在风且伴有气动失配或未建模的40%电机指令损失的情况下，三个基线中的每一个在所有试验中都失败，而RAYA完成了10/10的六周期任务。项目网站：此https URL。
英文摘要
A robot can predict failure and still be unable to prevent it. By the time a safety mechanism reacts, the nominal plan may already have spent the control authority that recovery requires, and fixed task priorities may block whatever response remains. Our key insight is that both aspects are decided inside the controller. Recoverability must inform actions while they are chosen rather than veto them afterward, and task objectives must be adapted as recoverability shrinks. Building on this, we present RAYA, a hybrid learned-analytic framework that places a learned finite-horizon recoverability margin inside an optimal controller with hard constraints and pairs it with a bounded learned scheduler that shifts task weights to facilitate recovery. Across 7,200 simulation episodes per controller spanning quadrotor and autonomous-vehicle benchmarks, RAYA not only improves survival rates, but also transfers the learned components zero-shot to unseen trajectories, disturbances, plant shifts, and friction layouts. We developed an embedded realization of RAYA and deployed it on-board a 35g Crazyflie quadrotor. Across 40 combined hardware flights under wind with either aerodynamic mismatch or an unmodeled 40% motor-command loss, each of three baselines fails in all trials, while RAYA completes 10/10 six-cycle missions. Project Website: https://raya-control.github.io/.
Comments8 pages, 4 figures
