Anytime, Anywhere: Human Arm Pose from Smartwatch Data for Ubiquitous Robot Control and Teleoperation
Anytime, Anywhere: Human Arm Pose from Smartwatch Data for Ubiquitous Robot Control and Teleoperation
复制标题
DOI：
10.1109/iros55552.2023.10341624
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
F. Weigend;Shubham D. Sonawani;M. Drolet;H. B. Amor
中科院分区：
文献类型：
--
作者：
F. Weigend;Shubham D. Sonawani;M. Drolet;H. B. Amor
这项工作设计了一种优化的机器学习方法，用于从单个智能手表估计人类手臂姿势。我们的方法导致可能的手腕和肘部位置的分布，这允许测量不确定性和检测多个可能的手臂姿势解决方案，即，多模态姿态分布。结合估计手臂姿势与语音识别，我们把智能手表变成一个无处不在的，低成本和多功能的机器人控制界面。我们在两个用例中证明，这种直观的控制界面使用户能够快速干预机器人行为，暂时调整他们的目标，或通过模仿来训练全新的控制策略。大量的实验表明，该方法的结果在一个40%的减少预测误差比目前最先进的，并实现了2.56厘米的手腕和肘部位置的平均误差。
This work devises an optimized machine learning approach for human arm pose estimation from a single smart-watch. Our approach results in a distribution of possible wrist and elbow positions, which allows for a measure of uncertainty and the detection of multiple possible arm posture solutions, i.e., multimodal pose distributions. Combining estimated arm postures with speech recognition, we turn the smartwatch into a ubiquitous, low-cost and versatile robot control interface. We demonstrate in two use-cases that this intuitive control interface enables users to swiftly intervene in robot behavior, to temporarily adjust their goal, or to train completely new control policies by imitation. Extensive experiments show that the approach results in a 40% reduction in prediction error over the current state-of-the-art and achieves a mean error of 2.56 cm for wrist and elbow positions.