基于视觉演示训练的具身无关导航策略
Embodiment-Agnostic Navigation Policy Trained with Visual Demonstrations
AI总结：
本文提出ViDEN框架，利用深度图像和相对目标位置的视觉演示训练具身无关导航策略，通过扩散策略实时生成无碰撞轨迹，在少量数据下实现优于现有方法的室内外导航性能。
摘要：
在非结构化环境中学习导航对机器人而言是一项具有挑战性的任务。虽然强化学习可能有效，但它通常需要大量数据收集，并且可能带来风险。相比之下，从专家演示中学习提供了一种更高效的方法。然而，许多现有方法依赖于特定的机器人具身、预先指定的目标图像，并且需要大型数据集。我们提出基于视觉演示的具身无关导航（ViDEN）框架，这是一种利用视觉演示来训练具身无关导航策略的新框架。ViDEN利用深度图像降低输入维度，并依赖相对目标位置，使其更能适应多样化的环境。通过在任务中心和具身无关的演示上训练基于扩散的策略，ViDEN能够实时生成无碰撞且自适应的轨迹。我们在人类伸手和跟踪任务上的实验表明，ViDEN优于现有方法，仅需少量数据即可在各种室内和室外导航场景中取得优越性能。项目网站：https://nimicurtis.github.io/ViDEN/。
英文摘要：
Learning to navigate in unstructured environments is a challenging task for robots. While reinforcement learning can be effective, it often requires extensive data collection and can pose risk. Learning from expert demonstrations, on the other hand, offers a more efficient approach. However, many existing methods rely on specific robot embodiments, pre-specified target images and require large datasets. We propose the Visual Demonstration-based Embodiment-agnostic Navigation (ViDEN) framework, a novel framework that leverages visual demonstrations to train embodiment-agnostic navigation policies. ViDEN utilizes depth images to reduce input dimensionality and relies on relative target positions, making it more adaptable to diverse environments. By training a diffusion-based policy on task-centric and embodiment-agnostic demonstrations, ViDEN can generate collision-free and adaptive trajectories in real-time. Our experiments on human reaching and tracking demonstrate that ViDEN outperforms existing methods, requiring a small amount of data and achieving superior performance in various indoor and outdoor navigation scenarios. Project website: https://nimicurtis.github.io/ViDEN/.
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。
