A Versatile Door Opening System with Mobile Manipulator through Adaptive Position-Force Control and Reinforcement Learning
Preprint
Abstract
The ability of robots to navigate through doors is crucial for their effective operation in indoor environments. Consequently, extensive research has been conducted to develop robots capable of opening specific doors. However, the diverse combinations of door handles and opening directions necessitate a more versatile door opening system for robots to successfully operate in real-world environments. In this paper, we propose a mobile manipulator system that can autonomously open various doors without prior knowledge. By using convolutional neural networks, point cloud extraction techniques, and external force measurements during exploratory motion, we obtained information regarding handle types, poses, and door characteristics. Through two different approaches, adaptive position-force control and deep reinforcement learning, we successfully opened doors without precise trajectory or excessive external force. The adaptive position-force control method involves moving the end-effector in the direction of the door opening while responding compliantly to external forces, ensuring safety and manipulator workspace. Meanwhile, the deep reinforcement learning policy minimizes applied forces and eliminates unnecessary movements, enabling stable operation across doors with different poses and widths. The RL-based approach outperforms the adaptive position-force control method in terms of compensating for external forces, ensuring smooth motion, and achieving efficient speed. It reduces the maximum force required by 3.27 times and improves motion smoothness by 1.82 times. However, the non-learning-based adaptive position-force control method demonstrates more versatility in opening a wider range of doors, encompassing revolute doors with four distinct opening directions and varying widths.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Autonomous robot-driven deliveries: A review of recent developments and future directionsTransportation Research Part E: Logistics and Transportation Review, 2022
- Efficient multitask learning with an embodied predictive model for door opening and entry with whole-body controlScience Robotics, 2022
- Assistive Delivery Robot Application for Real-World Postal ServicesIEEE Access, 2021
- Learning Kinematic Feasibility for Mobile Manipulation Through Deep Reinforcement LearningIEEE Robotics and Automation Letters, 2021
- Robust and adaptive door operation with a mobile robotIntelligent Service Robotics, 2021
- Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement LearningIEEE Robotics and Automation Letters, 2021
- Whole-Body MPC for a Dynamically Stable Mobile ManipulatorIEEE Robotics and Automation Letters, 2019
- Optimal Energy Consumption for Mobile Manipulators Executing Door-Opening TaskMathematical Problems in Engineering, 2018
- Multiple Working Mode Control of Door-Opening With a Mobile Modular and Reconfigurable RobotIEEE/ASME Transactions on Mechatronics, 2013
- Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography1987