Pointing is an important mode of interaction with robots. While large amounts of prior studies focus on recognition of human pointing, there is a lack of investigation into generating context-aware human-like pointing gestures, a shortcoming we hope to address. We first collect a rich dataset of human pointing gestures and corresponding pointing target locations with accurate motion capture. Analysis of the dataset shows that it contains various pointing styles, handedness, and well-distributed target positions in surrounding 3D space in both single-target pointing scenario and two-target point-and-place.We then train reinforcement learning (RL) control policies in physically realistic simulation to imitate the pointing motion in the dataset while maximizing pointing precision reward.We show that our RL motion imitation setup allows models to learn human-like pointing dynamics while maximizing task reward (pointing precision). This is promising for incorporating additional context in the form of task reward to enable flexible context-aware pointing behaviors in a physically realistic environment while retaining human-likeness in pointing motion dynamics. ; QC 20220607
Towards Context-Aware Human-like Pointing Gestures with RL Motion Imitation
2022-01-01
Conference paper
Electronic Resource
English
DDC: | 629 |
Guiding Quadrotor Landing with Pointing Gestures
Springer Verlag | 2020
|Guiding Quadrotor Landing with Pointing Gestures
TIBKAT | 2020
|Visual recognition of pointing gestures for human-robot interaction
British Library Online Contents | 2007
|