Abstract: Recognizing and reproducing spatiotemporal motions are necessary when analyzing behaviors and movements during human-robot interaction. Rigid body motion trajectories are proven as compact and informative clues in characterizing motions. A flexible dual square-root function (DSRF) descriptor for representing rigid body motion trajectories, which can offer robustness in the description over raw data, was proposed in our previous study. However, this study focuses on exploring the application of the DSRF descriptor for effective backward motion reproduction and motion recognition. Specifically, two DSRF-based reproduction methods are initially proposed, including the recursive reconstruction and online optimization. New trajectories with novel situations and contextual information can be reproduced from a single demonstration while preserving the similarities with the original demonstration. Furthermore, motion recognition based on DSRF descriptor can be achieved by employing a template matching method. Finally, the experimental results demonstrate the effectiveness of the proposed method for rigid body motion reproduction and recognition.

Key words: human-robot interaction, rigid body motion trajectory, trajectory description, motion reproduction and recognition

摘要： 在人机交互中，时空运动的识别和复现是分析人体行为和运动必要的前提条件。刚体运动轨迹被证明可以为运动描述提供充分信息线索。在之前的研究中，我们提出了一种灵活的双平方根函数轨迹描述（DSRF）来表示刚体运动轨迹，它相对于原始数据提供鲁棒的描述。本研究的重点是探索DSRF描述子在有效的运动复现和运动识别中的应用。具体而言，本文提出了两种基于DSRF的复现方法，包括递归重构和在线优化。具有上下文信息的新轨迹可以从单个示教轨迹复现，同时保留与原始轨迹的相似性。此外，采用模板匹配方法实现了基于DSRF描述子的运动识别。实验结果验证了该方法对刚体运动的再现和识别的有效性。

关键词: 人机交互，刚体运动轨迹，轨迹描述，运动复现与识别