Human Preferences in Industrial Human-Robot Interactions
نویسندگان
چکیده
Joint-action is one of the key research areas in robotics and especially important in physical human-robot interaction. The two main criteria for robots, which should be integrated in everyday life, are safety and efficiency. Therefore, it is of particular interest to understand how humans work together in order to transfer the resulting facts from these studies to direct human-robot interaction. In this work, we investigate a simple case of physical human-robot interaction, i.e. the handing over of small objects from a robot to the human. Experiments, in which six cubes were handed over from the robot to the human, were performend with two different robot systems, a robot arm in a humanoid set-up and a typical industrial set-up. Two different velocity profiles were integrated in the robot systems, a trapezoidal velocity profile in joint coordinates and a human inspired minimum jerk profile in cartesian coordinates. In both set-ups the use of the minimum jerk profile lead to shorter reaction times of the humans for the interaction. The humanoid setup showed with both profiles shorter reaction times than the industrial setup. It was also investigated in the experiments, whether the human body position adopts during the experiments to an optimal position for the hand-over. During the experiments the body spatial position stayed largely invariant, which indicates, that the subjects were not frightened and felt comfortable with the given hand over position. The result of our experiments along with the given comparison to natural human-human behaviour provides a solid basis for more efficiency of collaboration of humans and assistive robot systems.
منابع مشابه
Optimization of Temporal Dynamics for Adaptive Human-Robot Interaction in Assembly Manufacturing
Human-robot collaboration presents an opportunity to improve the efficiency of manufacturing and assembly processes, particularly for aerospace manufacturing where tight integration and variability in the build process make physical isolation of robotic-only work challenging. In this paper, we develop a robotic scheduling and control capability that adapts to the changing preferences of a human...
متن کاملLearning preferences for manipulation tasks from online coactive feedback
We consider the problem of learning preferences over trajectories for mobile manipulators such as personal robots and assembly line robots. The preferences we learn are more intricate than simple geometric constraints on trajectories; they are rather governed by the surrounding context of various objects and human interactions in the environment. We propose a coactive online learning framework ...
متن کاملAn Experimental Study on Blinking and Eye Movement Detection via EEG Signals for Human-Robot Interaction Purposes Based on a Spherical 2-DOF Parallel Robot
Blinking and eye movement are one of the most important abilities that most people have, even people with spinal cord problem. By using this ability these people could handle some of their activities such as moving their wheelchair without the help of others. One of the most important fields in Human-Robot Interaction is the development of artificial limbs working with brain signals. The purpos...
متن کاملA Model for Verbal and Non-Verbal Human-Robot Collaboration
We are motivated by building a system for an autonomous robot companion that collaborates with a human partner for achieving a common mission. The objective of the robot is to infer the human’s preferences upon the tasks of the mission so as to collaborate with the human by achieving human’s non-favorite tasks. Inspired by recent researches about the recognition of human’s intention, we propose...
متن کاملBall Trajectory Estimation and Robot Control to Reach the Ball Using Single Camera
In robotics research, catching a projectile object with a robotic system is one of the challenging problems. The outcome of these researches can be used in a wide range of applications such as video surveillance systems, analysis of sports videos, monitoring programs for human activities, and human-machine interactions. In this paper, we propose a new vision-based algorithm to estimate the traj...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2008