Motion Planning by Demonstration With Human-Likeness Evaluation for Dual-Arm Robots

Abstract

Abstract-The paper presents a planning procedure that allows an anthropomorphic dual-arm robotic system to perform a manipulation task in a natural human-like way by using demonstrated human movements. The key idea of the proposal is to convert the demonstrated trajectories into attractive potential fields defined over the configuration space and then use an RRT * -based planning algorithm that minimizes a path-cost function designed to bias the tree growth towards the human-demonstrated configurations. The paper presents a description of the proposed approach as well as results from a conceptual and a real application example, the latter using a real anthropomorphic dual-arm robotic system. A path-quality measure, based on first-order synergies (correlations between joint velocities) obtained from real human movements, is also proposed and used for evaluation and comparison purposes. The obtained results show that the paths obtained with the proposed procedure are more human-like.

Aspectos técnicos de los robots co-trabajadores con operadores humanos

“…A continuación, se estudian las relaciones entre las variaciones de las articulaciones del robot cuando realiza estos movimientos, tanto en lo relativo a posición como a velocidades (denominadas sinergias de orden cero y uno respectivamente). Estas sinergias permiten definir un subespacio donde realizar la planificación de movimientos, obteniéndose movimientos con apariencia humana y, además, de manera eficiente al reducirse la dimensión del espacio de planificación (García et al, , 2018.…”

Planning Hand-Arm Grasping Motions with Human-Like Appearance

“…In this way, the pre-grasp synergies explain the hand motions in the pre-grasp phase in all the grasps, and each set of grasp synergies model the hand motions of each grasp family (Table I shows the accumulated sample variance for the obtained set of synergies). For a robotic hand with n DOFs, the synergies define an n-dimensional box centered at the barycenter of the configurations used to obtain the synergies and with each side aligned with a synergy [27]. So that the box contains the (100−α)% of the configuration distribution (i.e.…”

“…the ratio of iterations in which the sample trees actually grow), the path length (measured in C as the weighted sum of accumulated joint movements along the path), and the path human-likeness. The human-likeness index computes the misalignment of a path with respect to some given reference human movements [27]. Here, natural free-movements of the operator while moving freely the fingers in an unconstrained way (i.e.…”

Efficient Body Motion Quantification and Similarity Evaluation Using 3-D Joints Skeleton Coordinates

“…U NDERSTANDING human behavior is indispensable for automating many tasks. Human body motion analysis is a branch of understanding human behavior, and it is fundamental for various applications, such as surveillance [1]- [3], human-computer interaction [4]- [6], health care of the elderly [7], [8], human gait analysis [9], [10], and robotics [11]- [16]. A variety of motion capture systems have been built to capture the human motion using different techniques, including wearable devices and sensors, multiple cameras, or even a single camera.…”