学习行动的同时学习观察：机器人模仿中的主动感知扩散模型
Learning to See While Learning to Act: Diffusion Models for Active Perception in Robot Imitation
AI总结：
提出See2Act模仿学习方法，通过耦合动作去噪与视角优化，在测试时基于主动推断的视角序列预测动作，解决遮挡下的部分可观测问题，在Ravens和RLBench任务上性能提升达34%。
摘要：
大多数模仿学习方法假设桌面环境完全可观测。实际上，物体经常被遮挡，要求机器人同时搜索和行动，而从有限的示范中学习这种耦合行为仍然具有挑战性。我们提出See2Act，一种模仿学习方法，通过将动作去噪与视角优化相结合，在测试时基于主动推断的视角序列来条件化动作预测。该策略使用锚定于离线示范中关键帧动作的相机位姿进行训练，从而在学习如何行动的同时隐式学习观察位置。我们实验证明，在Ravens中，该策略在严重遮挡下恢复信息丰富的视角，在RLBench任务上，相比先前方法性能提升高达34%。在真实世界中，我们在数字孪生中收集了50个示范，并在使用深度观测的拾取和放置任务上实现了零样本的仿真到现实迁移。该策略处理了显著的遮挡，表明学习到的视角推理能够在部分可观测性下实现鲁棒的操作。
英文摘要：
Most imitation learning methods assume full observability in table-top settings. In practice, objects are often occluded, requiring robots to both search and act, and learning this coupled behavior from limited demonstrations remains challenging. We propose See2Act, an imitation learning approach that conditions action prediction on a sequence of actively inferred viewpoints at test time, by coupling action denoising with viewpoint refinement. The policy is trained using camera poses anchored to keyframe actions from offline demonstrations, enabling implicit learning of where to see, while learning how to act. We empirically demonstrate that in Ravens the policy recovers informative viewpoints under severe occlusions, and on RLBench tasks it improves performance by up to 33% points over prior methods. In the real world, we collect 50 demonstrations in a digital twin and achieve zero-shot sim-to- real transfer on pick-and-place tasks using depth observations. The policy handles significant occlusions, showing that learned viewpoint reasoning enables robust manipulation under partial observability.
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。
