Bridging the Sim-to-Real Gap in Parallel-Link Leg Mechanisms via Simulator-Side Dynamics Normalization
2026-08-03 • Robotics
Robotics
AI summaryⓘ
The authors studied why simulations of a robot arm (modeled with simple linked parts) don’t always match real-life behavior, especially because some parts of the arm’s dynamics are left out in the simplified model. They introduced a method called Simulator-Side System Normalization (S3N) that adjusts the simulation to better capture the real inertia and damping effects. Their approach improved accuracy significantly in tests measuring joint movement, torque, and ground forces. This helps make robot training in simulation more reliable by reflecting the true physical behavior of the robot.
sim-to-real gapparallel-link mechanismserial-tree surrogateJacobian mappingactuator inertiadampingcoordinate transformationsystem normalizationroot mean square error (RMSE)frequency response
Authors
Jinsong Hong, Jangho Kim, Jihwan Lee, Donghyun Kim, Sehoon Oh
Abstract
This paper addresses the sim-to-real gap in dynamics arising when a parallel-link mechanism is represented by a serial-tree surrogate in simulation. Conventional Jacobian-based state and torque mappings preserve consistency with the kinematic and virtual-work relations but do not account for the coordinate-induced redistribution of actuator inertia and damping and the linkage inertia omitted during serial-tree reduction. To address this gap, Simulator-Side System Normalization (S3N) is proposed to normalize the serial-tree simulator's effective dynamics while preserving its tree topology. S3N-Act incorporates actuator inertia and damping into the serial-coordinate dynamics through coordinate transformation, whereas S3N-Full restores residual linkage inertia by separately identifying actuator- and leg-level frequency responses. In the 2-DoF validation, S3N-Full reduced the joint-position and torque RMSEs by 80.9% and 82.1%, respectively, relative to the Jacobian-mapping baseline. During pitch-in-place motion, S3N-Act and S3N-Full reduced the RMSE of the ground reaction force norm by 65.1% and 62.4%, respectively. During circular locomotion, S3N-Full reduced the phase-averaged, command-normalized sim-to-real gap from 17.3% to 9.9%. These results show that simulator-side normalization improves motion- and force-level sim-to-real consistency. It enables policy training in a serial-tree framework with hardware-consistent dynamics that better represent the physical parallel-link mechanism.