Human-Like Arm Motion Generation: A Review

Abstract

In the last decade, the objectives outlined by the needs of personal robotics have led to the rise of new biologically-inspired techniques for arm motion planning. This paper presents a literature review of the most recent research on the generation of human-like arm movements in humanoid and manipulation robotic systems. Search methods and inclusion criteria are described. The studies are analysed taking into consideration the sources of publication, the experimental settings, the type of movements, the technical approach, and the human motor principles that have been used to inspire and assess human-likeness. Results show that there is a strong focus on the generation of single-arm reaching movements and biomimetic-based methods. However, there has been poor attention to manipulation, obstacle-avoidance mechanisms, and dual-arm motion generation. For these reasons, human-like arm motion generation may not fully respect human behavioural and neurological key features and may result restricted to specific tasks of human-robot interaction. Limitations and challenges are discussed to provide meaningful directions for future investigations.

Human Prediction of Robot’s Intention in Object Handling Tasks

“…Additionally, we included other trajectory characteristics such as duration, distance traveled, the sum of acceleration-change (AC) and speed-change (SC). These characteristics were investigated in both jointsspace (denoted as joint-space or JS) and end-effector (denoted as EF) space (Gulletta et al, 2020); which applied to trajectory characteristics such as distance traveled, a sum of SC, a sum of AC, and the sum of JC. In total, there were 11 trajectory characteristics considered in this study:…”

“…Wurhofer et al (2015) found that a lack of transparency had a negative impact on the acceptance of robotic technology in the workplace. To address this issue, the robotics research community proposed to improve human's prediction of a robot's intention by adjusting the robot's behavior (Gulletta et al, 2020).…”

“…To address this gap in generalization, the research community proposed the biomimetics method, where robots used a generic movement model that had been researched in computational human behavior modeling (Schwartz, 2016;Gulletta et al, 2020). Cabrera Ubaldi (2018) generated human-like variability of a trajectory to be used in classifiers training for recognizing human gestures.…”

Dynamic Primitives Limit Human Force Regulation During Motion

“…Angular position along the elliptical path was defined using the eccentric anomaly 1 , E, such that E = atan(ay/bx), where a and b were half the length of the major and minor axes of the ellipse, respectively. x and y were the magnitudes of the position vector in the direction of the major and minor axes in Cartesian space, respectively.…”