arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.09192cs.RO
收藏

基于任务和运动模拟的特征空间拓扑映射无度量探索

Metric-Free Exploration for Topological Mapping by Task and Motion Imitation in Feature Space

University of Oxford(牛津大学);New York University(纽约大学)

Yuhang He, Irving Fang, Yiming Li, Rushi Bhavesh Shah, Chen Feng

摘要:

我们提出了DeepExplorer,一个简单而轻量级的无度量探索方法,用于未知环境的拓扑映射。它完全在图像特征空间中执行任务和运动规划(TAMP)。任务规划器是一个循环网络,使用最新的图像观察序列来产生一个功能作为下一个最佳探索目标。然后,运动规划器利用当前特征和幻觉特征来生成使智能体朝向该目标的动作。这两个规划者通过专家演示的深度监督模仿学习进行联合训练。在探索过程中,我们迭代地调用两个规划器来预测下一个动作,并通过不断地将最新的图像观察和动作附加到地图上并使用视觉位置识别(VPR)进行闭环来构建拓扑地图。由此产生的拓扑地图有效地表示了环境的连通性和可通行性,因此它可以用于视觉导航等任务。我们在Gibson和MP 3D等大规模模拟数据集上展示了DeepExplorer的探索效率和强大的sim 2sim泛化能力。通过在生成的拓扑地图上的图像-目标导航性能进一步验证了其有效性。我们进一步展示了其强大的zero-shot sim 2 real泛化能力在现实世界的实验。源代码可从\url{https://ai4ce.github.io/DeepExplorer/}获得。

英文摘要:

We propose DeepExplorer, a simple and lightweight metric-free exploration method for topological mapping of unknown environments. It performs task and motion planning (TAMP) entirely in image feature space. The task planner is a recurrent network using the latest image observation sequence to hallucinate a feature as the next-best exploration goal. The motion planner then utilizes the current and the hallucinated features to generate an action taking the agent towards that goal. The two planners are jointly trained via deeply-supervised imitation learning from expert demonstrations. During exploration, we iteratively call the two planners to predict the next action, and the topological map is built by constantly appending the latest image observation and action to the map and using visual place recognition (VPR) for loop closing. The resulting topological map efficiently represents an environment's connectivity and traversability, so it can be used for tasks such as visual navigation. We show DeepExplorer's exploration efficiency and strong sim2sim generalization capability on large-scale simulation datasets like Gibson and MP3D. Its effectiveness is further validated via the image-goal navigation performance on the resulting topological map. We further show its strong zero-shot sim2real generalization capability in real-world experiments. The source code is available at \url{https://ai4ce.github.io/DeepExplorer/}.

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。

↑