Learning Variable Impedance Control for Aerial Sliding on Uneven Heterogeneous Surfaces by Proprioceptive and Tactile Sensing
Authors:
- Weixuan ZhangWZWeixuan Zhang
- Lionel OttLOLionel Ott
- Marco TognonMTMarco Tognon
- Roland SiegwartRSRoland Siegwart
Preprint
Abstract
The recent development of novel aerial vehicles capable of physically interacting with the environment leads to new applications such as contact-based inspection. These tasks require the robotic system to exchange forces with partially-known environments, which may contain uncertainties including unknown spatially-varying friction properties and discontinuous variations of the surface geometry. Finding a control strategy that is robust against these environmental uncertainties remains an open challenge. This paper presents a learning-based adaptive control strategy for aerial sliding tasks. In particular, the gains of a standard impedance controller are adjusted in real-time by a policy based on the current control signals, proprioceptive measurements, and tactile sensing. This policy is trained in simulation with simplified actuator dynamics in a student-teacher learning setup. The real-world performance of the proposed approach is verified using a tilt-arm omnidirectional flying vehicle. The proposed controller structure combines data-driven and model-based control methods, enabling our approach to successfully transfer directly and without adaptation from simulation to the real platform. Compared to fine-tuned state of the art interaction control methods we achieve reduced tracking error and improved disturbance rejection.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- Stability-Guaranteed Reinforcement Learning for Contact-Rich ManipulationIEEE Robotics and Automation Letters, 2021
- Aerial Manipulator Pushing a Movable Structure Using a DOB-Based Robust ControllerIEEE Robotics and Automation Letters, 2020
- Learning Dynamics for Improving Control of Overactuated Flying SystemsIEEE Robotics and Automation Letters, 2020
- Learning Variable Impedance Control for Contact Sensitive TasksIEEE Robotics and Automation Letters, 2020
- Learning Force Control for Contact-Rich Manipulation Tasks With Rigid Position-Controlled RobotsIEEE Robotics and Automation Letters, 2020
- Model-Based Reinforcement Learning Variable Impedance Control for Human-Robot CollaborationJournal of Intelligent & Robotic Systems, 2020
- Power Flow Regulation, Adaptation, and Learning for Intrinsically Robust Virtual Energy TanksIEEE Robotics and Automation Letters, 2019
- A Truly-Redundant Aerial Manipulator System With Application to Push-and-Slide Inspection in Industrial PlantsIEEE Robotics and Automation Letters, 2019
- Physical-Virtual Impedance Control in Ultralightweight and Compliant Dual-Arm Aerial ManipulatorsIEEE Robotics and Automation Letters, 2018
- Survey of Model-Based Reinforcement Learning: Applications on RoboticsJournal of Intelligent & Robotic Systems, 2017