Analysis and Transfer of Human Movement Manipulability in Industry-like Activities

Abstract

Humans exhibit outstanding learning, planning and adaptation capabilities while performing different types of industrial tasks. Given some knowledge about the task requirements, humans are able to plan their limbs motion in anticipation of the execution of specific skills. For example, when an operator needs to drill a hole on a surface, the posture of her limbs varies to guarantee a stable configuration that is compatible with the drilling task specifications, e.g. exerting a force orthogonal to the surface. Therefore, we are interested in analyzing the human arms motion patterns in industrial activities. To do so, we build our analysis on the so-called manipulability ellipsoid, which captures a posture-dependent ability to perform motion and exert forces along different task directions. Through thorough analysis of the human movement manipulability, we found that the ellipsoid shape is task dependent and often provides more information about the human motion than classical manipulability indices. Moreover, we show how manipulability patterns can be transferred to robots by learning a probabilistic model and employing a manipulability tracking controller that acts on the task planning and execution according to predefined control hierarchies.

Biomimetic Approaches for Human Arm Motion Generation: Literature Review and Future Directions

“…In that work, a profile of the manipulability ellipsoid was used to control a humanoid robot. Building on that method, Jaquier et al later showed [84] that the manipulability ellipsoid was task-dependent, and it could be transferred to robots for human-like movement. Sentis et al [85] showed that it was possible to use the gradient projection to apply multiple criteria recursively to refine the performed motion.…”

A Riemannian Take on Human Motion Analysis and Retargeting

“…Such mappings were manually defined for similar kinematics [21] or learned automatically from data [28]. To bypass the complexity of these mappings, several works instead focused on transferring the functional part of the motion by mapping endeffector trajectories [29] or manipulability patterns [30].…”