RoboSimStudio: An Interactive Toolkit for Rapid Real2Sim of Robot Manipulation Tasks
arXiv cs.AI · 14 Oct 2026, 03:55 AEST
RoboSimStudio is an interactive toolkit designed for rapid real-to-simulation of robot manipulation tasks. It allows users to refine simulations based on observed physical behavior by making solver choices and physical parameters editable.
Key facts
- It is difficult to accurately model the physics of the interaction between a robot and the objects it manipulates, including contact mechanics, coupled contact dynamics, deformations, stiffness and friction.
- We present RoboSimStudio (RSS), an interactive toolkit that makes choices of solver, contact model, and physical parameters explicit and editable, allowing both humans and coding agents to iteratively refine simulations based on observed physical behavior.
- We implement RSS with the open Newton physics simulation system and describe experiments with human-guided real2sim using (1) visual evaluation, (2) force-feedback and (3) agentic Real2Sim2Real.
Read aloud
RoboSimStudio is an interactive toolkit designed for rapid real-to-simulation of robot manipulation tasks. It allows users to refine simulations based on observed physical behavior by making solver choices and physical parameters editable. It is difficult to accurately model the physics of the interaction between a robot and the objects it manipulates, including contact mechanics, coupled contact dynamics, deformations, stiffness and friction. We present RoboSimStudio RSS, an interactive toolkit that makes choices of solver, contact model, and physical parameters explicit and editable, allowing both humans and coding agents to iteratively refine simulations based on observed physical behavior. We implement RSS with the open Newton physics simulation system and describe experiments with human-guided real2sim using one visual evaluation, two force-feedback and three agentic Real2Sim2Real.
Sources in this cluster
- RoboSimStudio: An Interactive Toolkit for Rapid Real2Sim of Robot Manipulation Tasks
arXiv cs.AI · 14 Oct 2026, 03:55 AEST