Multi-Step Recurrent Q-Learning for Robotic Velcro Peeling
- Resource Type
- Conference
- Authors
- Yuan, Jiacheng; Hani, Nicolai; Isler, Volkan
- Source
- 2021 IEEE International Conference on Robotics and Automation (ICRA) Robotics and Automation (ICRA), 2021 IEEE International Conference on. :6657-6663 May, 2021
- Subject
- Aerospace
Bioengineering
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
General Topics for Engineers
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Geometry
Strips
Uncertainty
Force measurement
Conferences
Grasping
Benchmark testing
- Language
- ISSN
- 2577-087X
Learning object manipulation is a critical skill for robots to interact with their environment. Even though there has been significant progress in robotic manipulation of rigid objects, interacting with non-rigid objects remains challenging for robots. In this work, we introduce velcro peeling as a new application for robotic manipulation of non-rigid objects in complex environments. We present a method of learning force-based manipulation from noisy and incomplete sensor inputs in partially observable environments by modeling long term dependencies between measurements with a multi-step deep recurrent network. We present experiments on a real robot to show the necessity of modeling these long term dependencies and validate our approach in simulation and robot experiments. Our results show that using tactile input enables the robot to overcome geometric uncertainties present in the environment with high fidelity in ∼ 90% of all cases, outperforming the baselines by a large margin.