Waypoint Models for Instruction-guided Navigation in Continuous Environments
Waypoint Models for Instruction-guided Navigation in Continuous Environments
复制标题
DOI：
10.1109/iccv48922.2021.01488
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Jacob Krantz;Aaron Gokaslan;Dhruv Batra;Stefan Lee;Oleksandr Maksymets
中科院分区：
文献类型：
--
作者：
Jacob Krantz;Aaron Gokaslan;Dhruv Batra;Stefan Lee;Oleksandr Maksymets
很少有研究明确指出动作空间在语言引导的视觉导航中的作用——无论是它对导航成功的影响，还是机器人代理执行结果轨迹的效率。基于最近发布的用于连续环境中指令跟随的VLN-CE[24]设置，我们开发了一类语言条件的路点预测网络来研究这个问题。我们改变这些模型的表达能力，以探索低水平行动和连续航点预测之间的频谱。我们测量了LoCoBot[1]机器人的任务性能和估计执行时间。我们发现更具表现力的模型导致更简单、更快地执行轨迹，但低级别的动作可以通过更好地逼近最短路径来实现更好的导航指标。此外，我们的模型在VLN-CE中的表现优于先前的工作，并在公共排行榜上树立了新的先进水平-在这项具有挑战性的任务中，我们的最佳模型将成功率提高了4%。
Little inquiry has explicitly addressed the role of action spaces in language-guided visual navigation – either in terms of its effect on navigation success or the efficiency with which a robotic agent could execute the resulting trajectory. Building on the recently released VLN-CE [24] setting for instruction following in continuous environments, we develop a class of language-conditioned waypoint prediction networks to examine this question. We vary the expressivity of these models to explore a spectrum between low-level actions and continuous waypoint prediction. We measure task performance and estimated execution time on a profiled LoCoBot [1] robot. We find more expressive models result in simpler, faster to execute trajectories, but lower-level actions can achieve better navigation metrics by approximating shortest paths better. Further, our models outperform prior work in VLN-CE and set a new state-of-the-art on the public leaderboard – increasing success rate by 4% with our best model on this challenging task.