Bridging the Sim-to-Real Gap with Dynamic Compliance Tuning for Industrial Insertion
Authors:
- Xiang ZhangXZXiang Zhang
- Masayoshi TomizukaMTMasayoshi Tomizuka
- Hui LiHLHui Li
Preprint
Abstract
Contact-rich manipulation tasks often exhibit a large sim-to-real gap. For instance, industrial assembly tasks frequently involve tight insertions where the clearance is less than \(0.1\) mm and can even be negative when dealing with a deformable receptacle. This narrow clearance leads to complex contact dynamics that are difficult to model accurately in simulation, making it challenging to transfer simulation-learned policies to real-world robots. In this paper, we propose a novel framework for robustly learning manipulation skills for real-world tasks using only the simulated data. Our framework consists of two main components: the ``Force Planner'' and the ``Gain Tuner''. The Force Planner is responsible for planning both the robot motion and desired contact forces, while the Gain Tuner dynamically adjusts the compliance control gains to accurately track the desired contact forces during task execution. The key insight of this work is that by adaptively adjusting the robot's compliance control gains during task execution, we can modulate contact forces in the new environment, thereby generating trajectories similar to those trained in simulation and narrows the sim-to-real gap. Experimental results show that our method, trained in simulation on a generic square peg-and-hole task, can generalize to a variety of real-world insertion tasks involving narrow or even negative clearances, all without requiring any fine-tuning.
Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Prim-LAfD: A Framework to Learn and Adapt Primitive-Based Skills from Demonstrations for Insertion TasksIFAC-PapersOnLine, 2023
- IndustReal: Transferring Contact-Rich Assembly Tasks from Simulation to Reality2023
- Learning Generalizable Pivoting Skills2023
- Reinforcement Learning of Impedance Policies for Peg-in-Hole Tasks: Role of Asymmetric MatricesIEEE Robotics and Automation Letters, 2022
- Factory: Fast Contact for Robotic Assembly2022
- Learning Variable Impedance Control via Inverse Reinforcement Learning for Force-Related TasksIEEE Robotics and Automation Letters, 2021
- Learning dexterous in-hand manipulationThe International Journal of Robotics Research, 2019
- Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Tasks2019
- Learning motions from demonstrations and rewards with time-invariant dynamical systems based policiesAutonomous Robots, 2017
- Learning variable impedance controlThe International Journal of Robotics Research, 2011