动态循环一致性控制的跨域对应学习
Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency
摘要：
许多机器人问题的核心是跨领域学习对应关系的挑战。例如，模仿学习需要获得人类和机器人之间的对应关系;模拟到真实需要物理模拟器和现实世界之间的对应关系;迁移学习需要不同机器人环境之间的对应关系。本文旨在学习不同领域的对应关系，这些领域在表示（视觉与内部状态），物理参数（质量和摩擦力）和形态（肢体数量）方面有所不同。重要的是，使用来自两个域的未配对和随机收集的数据来学习对应关系。我们提出了\textit{dynamics cycles}，调整动态机器人的行为在两个域使用周期一致性约束。一旦找到这种对应关系，我们就可以直接将在一个域上训练的策略转移到另一个域，而不需要在第二个域上进行任何额外的微调。我们在各种问题域进行实验，无论是在模拟和真实的机器人。我们的框架是能够调整一个真正的机器人手臂的未校准的单眼视频的动态状态动作轨迹的模拟手臂没有配对的数据。我们的结果的视频演示可在：https://sjtuzq.github.io/cycle_dynamics.html。
英文摘要：
At the heart of many robotics problems is the challenge of learning correspondences across domains. For instance, imitation learning requires obtaining correspondence between humans and robots; sim-to-real requires correspondence between physics simulators and the real world; transfer learning requires correspondences between different robotics environments. This paper aims to learn correspondence across domains differing in representation (vision vs. internal state), physics parameters (mass and friction), and morphology (number of limbs). Importantly, correspondences are learned using unpaired and randomly collected data from the two domains. We propose \textit{dynamics cycles} that align dynamic robot behavior across two domains using a cycle-consistency constraint. Once this correspondence is found, we can directly transfer the policy trained on one domain to the other, without needing any additional fine-tuning on the second domain. We perform experiments across a variety of problem domains, both in simulation and on real robot. Our framework is able to align uncalibrated monocular video of a real robot arm to dynamic state-action trajectories of a simulated arm without paired data. Video demonstrations of our results are available at: https://sjtuzq.github.io/cycle_dynamics.html .
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。
