A Nonparametric Motion Flow Model for Human Robot Cooperation
This addresses the problem of enabling more adaptive and efficient human-robot cooperation in collaborative tasks, though it appears incremental as it builds on existing motion modeling approaches.
The paper tackles the problem of modeling human motion for human-robot cooperation by proposing a nonparametric motion flow model that uses Gaussian processes to measure trajectory similarity, and applies it to optimize robot control via reward functions. The result shows comparable performance to state-of-the-art methods with full observations and superior performance with partial trajectory information, as measured by RMS error.
In this paper, we present a novel nonparametric motion flow model that effectively describes a motion trajectory of a human and its application to human robot cooperation. To this end, motion flow similarity measure which considers both spatial and temporal properties of a trajectory is proposed by utilizing the mean and variance functions of a Gaussian process. We also present a human robot cooperation method using the proposed motion flow model. Given a set of interacting trajectories of two workers, the underlying reward function of cooperating behaviors is optimized by using the learned motion description as an input to the reward function where a stochastic trajectory optimization method is used to control a robot. The presented human robot cooperation method is compared with the state-of-the-art algorithm, which utilizes a mixture of interaction primitives (MIP), in terms of the RMS error between generated and target trajectories. While the proposed method shows comparable performance with the MIP when the full observation of human demonstrations is given, it shows superior performance with respect to given partial trajectory information.