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 2210.01412cs.RO
收藏

SLOT-V:视觉机器人操作运动规划的观测器模型监督学习

SLOT-V: Supervised Learning of Observer Models for Legible Robot Motion Planning in Manipulation

Uppsala University(乌普萨拉大学);Sorbonne University(索邦大学);Institute for Intelligent Systems and Robotics(智能系统与机器人研究所);CNRS(法国国家科学研究中心)

Sebastian Wallkotter, Mohamed Chetouani, Ginevra Castellano

摘要:

我们提出了SLOT-V,一种新的监督学习框架,学习观察员模型(人类偏好)从机器人运动轨迹中的易读性。易读性衡量(人类)观察者从机器人运动轨迹推断机器人目标的容易程度。当生成这样的轨迹时,现有的规划者通常依赖于估计轨迹候选者的质量的观察者模型。这些观察者模型通常是手工制作的,或者偶尔从演示中学习。在这里,我们建议使用在上述方法的评估过程中经常使用的相同数据格式以监督的方式学习它们。然后,我们证明了SLOT-V的通用性,在一个模拟的操作环境中使用的弗兰卡Rankka。为此,我们证明了它可以学习密切预测各种手工制作的观察者模型,即,SLOT-V的假设空间包含现有的手工模型。接下来,我们通过证明训练好的模型在具有未知目标配置和/或目标计数的环境中继续表现良好来展示SLOT-V的概括能力。最后,我们对SLOT-V的样本效率(和性能)与现有的IRL方法进行了基准测试,并表明SLOT-V可以用更少的数据学习更好的观察者模型。结合起来,这些结果表明SLOT-V可以学习可行的观察者模型。更好的观察者模型意味着更清晰的轨迹,这反过来可能导致更好和更透明的人机交互。

英文摘要:

We present SLOT-V, a novel supervised learning framework that learns observer models (human preferences) from robot motion trajectories in a legibility context. Legibility measures how easily a (human) observer can infer the robot's goal from a robot motion trajectory. When generating such trajectories, existing planners often rely on an observer model that estimates the quality of trajectory candidates. These observer models are frequently hand-crafted or, occasionally, learned from demonstrations. Here, we propose to learn them in a supervised manner using the same data format that is frequently used during the evaluation of aforementioned approaches. We then demonstrate the generality of SLOT-V using a Franka Emika in a simulated manipulation environment. For this, we show that it can learn to closely predict various hand-crafted observer models, i.e., that SLOT-V's hypothesis space encompasses existing handcrafted models. Next, we showcase SLOT-V's ability to generalize by showing that a trained model continues to perform well in environments with unseen goal configurations and/or goal counts. Finally, we benchmark SLOT-V's sample efficiency (and performance) against an existing IRL approach and show that SLOT-V learns better observer models with less data. Combined, these results suggest that SLOT-V can learn viable observer models. Better observer models imply more legible trajectories, which may - in turn - lead to better and more transparent human-robot interaction.

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。

↑