Extraction of person-specific motion style based on a task model and imitation by humanoid robot

Abstract

In this paper, we present a humanoid robot which extracts and imitates the person-specific differences in motions, which we will call style. Synthesizing human-like and stylistic motion variations according to specific scenarios is becoming important for entertainment robots, and imitation of styles is one variation which makes robots more amiable. Our approach extends a learning from observation (LFO) paradigm which enables robots to understand what a human is doing and to extract reusable essences to be learned. The focus is on styles in the domain of LFO and the representation of them using the reusable essences. In this paper, we design an abstract model of a target motion defined in LFO, observe human demonstrations through the model, and formulate the representation of styles in the context of LFO. Then we introduce a framework of generating robot motions that reflect styles which are automatically extracted from human demonstrations. To verify our proposed method we applied it to a ring toss game, and generated robot motions for a physical humanoid robot. Styles from each of three random players were extracted automatically from their demonstrations, and used for generating robot motions. The robot imitates the styles of each player without exceeding the limitation of its physical constraints, while tossing the rings to the goal.

Dynamic locomotion synchronization of bipedal robot and human operator via bilateral feedback teleoperation

“…Before the target can reproduce the motion, the data are modified to respect the robot's (or character) physical structure, dynamic characteristics, and limitations. Frequently, this process is performed by an optimizer that approximates the target's motions to the reference data while maintaining balancing stability (6,7) or the nuances of the movement of a character (8,9). This procedure is time insensitive because it is done offline; thus, the complex whole-body trajectory can be extensively refined and the resulting movement reference can be greatly optimized (10).…”

Investigating Emotion Style in Human Faces and Avatars

“…As an example of work on motion style in the entire human body, Okamoto et al [12], through a learning from observation (LFO) paradigm, presented a humanoid robot which extracts the different person-specific styles of humans performing a physical action such as tossing rings to a goal. By decomposing such action into different parameters, e.g.…”