arXiv 1909.069932019-09cs.CVcs.RO

使用跨模态表示学习空中导航的视觉运动策略

Learning Visuomotor Policies for Aerial Navigation Using Cross-Modal Representations

Microsoft Corporation（微软公司）；Carnegie Mellon University（卡内基梅隆大学）

Rogerio Bonatti, Ratnesh Madaan, Vibhav Vineet, Sebastian Scherer, Ashish Kapoor

摘要：

机器距离强大地解决开放世界的感知控制任务还有很长的路要走，比如第一人称视角（FPV）空中导航。虽然最近在端到端机器学习方面的进展，特别是模仿和强化学习似乎很有前途，但它们受到大量难以收集的标记真实世界数据的限制。另一方面，模拟数据很容易生成，但通常不会在各种现实生活场景中呈现安全行为。在这项工作中，我们提出了一种新的方法来学习强大的可视化策略，用于现实世界的部署，可以纯粹用模拟数据进行训练。我们开发了丰富的状态表示，结合了监督和无监督的环境数据。我们的方法采用了跨模态的视角，其中单独的模态对应于原始相机数据和与任务相关的系统状态，例如在无人机比赛的情况下，门与无人机的相对姿态。我们将这两种数据模式输入到一个新的因子化架构中，该架构通过变分自动编码器学习联合低维嵌入。然后将这种紧凑的表示输入到控制策略中，我们在模拟器中使用专家轨迹的模仿学习进行训练。我们分析了使用我们提出的表示学习的丰富的潜在空间，并表明与端到端学习或纯无监督特征提取器相比，使用我们的跨模态架构显着提高了控制策略性能。我们还提出了在不同的轨道配置和环境条件下通过门的无人机导航的现实世界的结果。我们提出的方法完全在船上运行，可以成功地在模拟和现实中推广学习到的表示和策略，显著优于基线方法。补充视频：https://youtu.be/VKc3A5HlUU8

英文摘要：

Machines are a long way from robustly solving open-world perception-control tasks, such as first-person view (FPV) aerial navigation. While recent advances in end-to-end Machine Learning, especially Imitation and Reinforcement Learning appear promising, they are constrained by the need of large amounts of difficult-to-collect labeled real-world data. Simulated data, on the other hand, is easy to generate, but generally does not render safe behaviors in diverse real-life scenarios. In this work we propose a novel method for learning robust visuomotor policies for real-world deployment which can be trained purely with simulated data. We develop rich state representations that combine supervised and unsupervised environment data. Our approach takes a cross-modal perspective, where separate modalities correspond to the raw camera data and the system states relevant to the task, such as the relative pose of gates to the drone in the case of drone racing. We feed both data modalities into a novel factored architecture, which learns a joint low-dimensional embedding via Variational Auto Encoders. This compact representation is then fed into a control policy, which we trained using imitation learning with expert trajectories in a simulator. We analyze the rich latent spaces learned with our proposed representations, and show that the use of our cross-modal architecture significantly improves control policy performance as compared to end-to-end learning or purely unsupervised feature extractors. We also present real-world results for drone navigation through gates in different track configurations and environmental conditions. Our proposed method, which runs fully onboard, can successfully generalize the learned representations and policies across simulation and reality, significantly outperforming baseline approaches. Supplementary video: https://youtu.be/VKc3A5HlUU8

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。

摘要：

英文摘要：

相关论文