The REACH lab is involved in a number of projects related to physical human-robot interaction. We have investigated hybrid actuation approaches and controls for the purposes of achieving higher performance while maintaining safety through a low output impedance. We have also developed methods that enable robots to learn about the constraints of physical tasks by learning from demonstrations using instrumented tools (e.g., tongs with force-torque sensors to measure interaction wrenches). As part of a NASA University Leadership Initiative project, we have developed shared autonomy methods where an operator provides informed real-time corrections to the robot while it completes contact-rich tasks, such as sanding or polishing. The research results have applications in industrial manufacturing and novice interactions with robots.
Senft, E., M. Hagenow, P. Praveena, R. Radwin, M. Zinn, M. Gleicher, and B. Mutlu. “A Method For Automated Drone Viewpoints to Support Remote Robot Manipulation”. 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022, pp. 7704-11.
Hagenow, M., E. Senft, E. Laske, K. Hambuchen, T. Fong, R. Radwin, M. Zinn, M. Gleicher, and B. Mutlu. “Registering Articulated Objects With Human-in-the-Loop Corrections”. 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022, pp. 2343-50.
Hagenow, M., E. Senft, R. Radwin, M. Gleicher, B. Mutlu, and M. Zinn. “Corrective Shared Autonomy for Addressing Task Variability”. IEEE Robotics and Automation Letters, Vol. 6, no. 2, 2021, pp. 3720-7.
Hagenow, M., E. Senft, R. Radwin, M. Gleicher, B. Mutlu, and M. Zinn. “Informing Real-Time Corrections in Corrective Shared Autonomy Through Expert Demonstrations”. IEEE Robotics and Automation Letters, Vol. 6, no. 4, 2021, pp. 6442-9.
Hagenow, M., M. Gleicher, B. Mutlu, B. Zhang, and M. Zinn. “Recognizing Orientation Slip in Human Demonstrations”. 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021, pp. 2790-7.
No posts currently available to show