Analyzing the Effects of Human-Aware Motion Planning on Close-Proximity Human–Robot Collaboration

Abstract

Objective:The objective of this work was to examine human response to motion-level robot adaptation to determine its effect on team fluency, human satisfaction, and perceived safety and comfort.Background:The evaluation of human response to adaptive robotic assistants has been limited, particularly in the realm of motion-level adaptation. The lack of true human-in-the-loop evaluation has made it impossible to determine whether such adaptation would lead to efficient and satisfying human–robot interaction.Method:We conducted an experiment in which participants worked with a robot to perform a collaborative task. Participants worked with an adaptive robot incorporating human-aware motion planning and with a baseline robot using shortest-path motions. Team fluency was evaluated through a set of quantitative metrics, and human satisfaction and perceived safety and comfort were evaluated through questionnaires.Results:When working with the adaptive robot, participants completed the task 5.57% faster, with 19.9% more concurrent motion, 2.96% less human idle time, 17.3% less robot idle time, and a 15.1% greater separation distance. Questionnaire responses indicated that participants felt safer and more comfortable when working with an adaptive robot and were more satisfied with it as a teammate than with the standard robot.Conclusion:People respond well to motion-level robot adaptation, and significant benefits can be achieved from its use in terms of both human–robot team fluency and human worker satisfaction.Application:Our conclusion supports the development of technologies that could be used to implement human-aware motion planning in collaborative robots and the use of this technique for close-proximity human–robot collaboration.

Dominance and movement cues of robot motion: A user study on trust and predictability

“…A higher number of trials utilizing the same movement strategy could have resulted in more substantiated evaluations. As noted in [16], longer-term studies are necessary to determine whether the effects found in this study are weakened or strengthened by longer exposure to the robot and how trust and expectations develop over time. A long-term study will appear as part of follow up work.…”

“…Movement cues have the potential to give human coworkers insights into robot intention, which can improve human performance in terms of time to completion (TTC) [16] and improve trust [1]. To achieve this, the motion needs to be predictable.…”

“…Previous works claim that humans prefer to perform their own task and make the robot wait, rather than yielding priority to the robot [15], [16]. Observation of human behavior during submissive movement strategies showed that 22 of the participants chose to continue with their task when the robot approached the workspace and then stopped, indicating that they were comfortable assuming a more dominant role in the interaction, whereas only 3 moved their hand or body back to allow the robot to continue, indicating that they allowed the robot to dominate in the interaction.…”

Interpretable models for fast activity recognition and anomaly explanation during collaborative robotics tasks

“…We evaluate RAPTOR using three activity datasets: a publicly available single person activity dataset with Kinectderived skeletal position features (UTKinect [11]); a motioncapture dataset of reaching behaviors from a stationary manufacturing task (Static-Reach [7]); and a new motion capture dataset of a mobile automotive final assembly manufacturing task (Dynamic-AutoFA) depicted in Figure 2.…”

“…In human-robot collaboration, the ability of a team member to quickly and reliably interpret teammates' actions and intentions is critical to achieving satisfactory robot performance and team fluency. This type of anticipatory information can improve task completion time, idle time, concurrent motion, and human-robot separation distance during human-robot collaboration [1], [2], [3], [4], [5], [6], [7]. Thus, rapid classification is a key attribute of an effective approach to activity recognition, as it allows for real-time situational awareness at the speed of the available sensing hardware.…”