A Hybrid Framework for Understanding and Predicting Human Reaching Motions

Abstract

Robots collaborating naturally with a human partner in a confined workspace need to understand and predict human motions. For understanding, a model-based approach is required as the human motor control system relies on the biomechanical properties to control and execute actions. The model-based control models explain human motions descriptively, which in turn enables predicting and analyzing human movement behaviors. In motor control, reaching motions are framed as an optimization problem. However, different optimality criteria predict disparate motion behavior. Therefore, the inverse problem-finding the optimality criterion from a given arm motion trajectory-is not unique. This paper implements an inverse optimal control (IOC) approach to determine the combination of cost functions that governs a motion execution. The results indicate that reaching motions depend on a trade-off between kinematics and dynamics related cost functions. However, the computational efficiency is not sufficient for online prediction to be utilized for HRI. In order to predict human reaching motions with high efficiency and accuracy, we combine the IOC approach with a probabilistic movement primitives formulation. This hybrid model allows an online-capable prediction while taking into account motor variability and the interpersonal differences. The proposed framework affords a descriptive and a generative model of human reaching motions which can be effectively utilized online for human-in-the-loop robot control and task execution.

Skill-based Shared Control

“…A generalized treatment of human-policy identification or human intention detection is out-of-scope of this work -it is a challenging problem with many factors often leading to models that are computationally infeasible for online prediction [25]. However, several domains we identified as our target are conducive to some simplifying assumptions: we assume (i) a given finite set of skill models denoted S, by an expert operator, that contain all motion patterns required for the completion of the task at hand, and (ii) the novice operator is skilled enough to enact teleoperation motions that, albeit sub-optimal, are identifiable by an off-the-shelf policy prediction method given S.…”

Data Driven Models for Human Motion Prediction in Human-Robot Collaboration

“…Mainprice et al used the IOC algorithm to learn the cost function from the demonstration trajectory of the collaborative assembly task, the human motion from the current configuration to the target area is predicted by iteratively replanning the predicted trajectory using learned cost function [36]. Oguz et al proposed a framework that combines the IOC method with the probabilistic motion primitive formulation, which can learn the motor variability as well as the interpersonal variance at the same time [37]. Besides, Ben Amor et al extended the concept of imitation learning to human-robot interaction scenarios and introduced a new representation called interaction primitives [38].…”

Predictive Modeling of Periodic Behavior for Human-Robot Symbiotic Walking

“…By incorporating the full joint trajectory distribution IPs enable the inference of all modeled parameters based on a sample set of observed parameters. This approach has proven capable in several different scenarios [20][21][22][23][24]. However while potential for rhythmic behaviors has been proposed before, careful management of basis functions as well as modifications to phase estimation must be made to to take periodicity into account.…”