Faster Confined Space Manufacturing Teleoperation Through Dynamic Autonomy With Task Dynamics Imitation Learning
- 30 January 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 5 (2) , 2357-2364
Abstract
Limited-access manufacturing, such as aircraft wing assembly, currently requires humans to be inside ergonomically-challenging environments. Small rapidly deployable robots can substantially improve manufacturing safety and productivity. However, (relatively rapid) full automation remains elusive due to high-level of uncertainty in the environment, lack of cost-effective programming for low volume production, and difficulty of deploying adequate number of sensors in the confined space. Moreover, currently, teleoperation (remote human control of a robot via a force-reflection device) with typical levels of training and limited transparency of hardware is too slow for manufacturing applications. In this context, the main contribution of this article is to enable limited-access robotics for manufacturing by reducing cycle times through the use of statistical, model-based, dynamic autonomy: (rapid) full automation when certain, and (slower but robust) teleoperation when uncertain. A user study (n = 8) with an experimental robot platform shows that the dynamic autonomy reduces process completion time by 54.0% and human operator energy expenditure by 80.5% as compared with teleoperation without dynamic autonomy.Keywords
Funding Information
- Boeing Corporation through the Boeing Advanced Research Center
This publication has 17 references indexed in Scilit:
- Optimization of Temporal Dynamics for Adaptive Human-Robot Interaction in Assembly Manufacturing2012
- Haptic shared control: smoothly shifting control authority?Cognition, Technology & Work, 2011
- A survey of robot learning from demonstrationRobotics and Autonomous Systems, 2009
- Robot Programming by Demonstration2008
- Apprenticeship learning via inverse reinforcement learning2004
- Force reflection, shared control, and time delay in telemanipulation2003
- Learning long-term dependencies in NARX recurrent neural networksIEEE Transactions on Neural Networks, 1996
- Definitions, Models and Measures of Human Workload1979
- Estimating the Dimension of a ModelThe Annals of Statistics, 1978
- A new look at the statistical model identificationIEEE Transactions on Automatic Control, 1974