RiCo: Neural Simulation of Rigid-Body Interactions via Local Contact Reasoning

2026-10-08

AI Summary

This study addresses the challenge of accurately simulating the influence of local contacts on motion during rigid body interactions. To this end, it proposes RiCo, a neural framework that leverages sparse contact-point neighborhood modeling to constrain cross-object reasoning to proximal surfaces. By jointly reasoning over geometric, kinematic, and physical properties, RiCo captures local contact effects while significantly reducing computational costs and preserving fine-grained interaction details. Evaluated on the MOVi benchmark, this neural local contact reasoning approach reduces positional and orientational errors by 31%–35%, achieving high-fidelity contact simulation. Furthermore, the framework demonstrates strong zero-shot generalization capabilities to complex scenes comprising up to 270 objects.

Abstract

Accurate simulation of rigid-body interactions is essential for predictive physical world models. Despite recent progress in modeling object dynamics, capturing how local contacts between surfaces shape object motion remains challenging. While end-to-end world models predict interactions across entire scenes or objects, in practice, rigid-body contact is inherently local, and only nearby surfaces can directly exchange contact forces. Motivated by this observation, we introduce Rigid-body Contact Reasoning (RiCo), which represents interactions between objects through sparse neighborhoods of contact surface points. RiCo combines each point's state with the relative geometry, motion, and physical properties of nearby surfaces, then reasons across the object's points to determine how these local contacts jointly affect its motion. By confining cross-object reasoning to nearby surfaces while propagating contact information within each rigid body, RiCo retains fine-grained interaction details without the cost of modeling every pair of scene points. Such properties enable RiCo a higher accuracy and contact fidelity. Experiments on MOVi-benchmark demonstrate that RiCo reduces 100-frame position and orientation errors by 31-35% and approximately 38%, respectively, compared with baselines. Moreover, RiCo achieves high contact fidelity, with ground-truth-relative penetration-time and mean-depth differences of 11.0% and 2.22 mm, respectively. RiCo further generalizes zero-shot from small-scale training scenarios to scenes containing 270 objects. Our real-world multi-ball collision experiments further provide preliminary evidence of sim-to-real transfer.

Problem

• rigid-body simulation
• local contact reasoning
• world models
• contact fidelity
• neural simulation

Innovation

• Local Contact Reasoning
• Rigid-Body Dynamics
• Sparse Neighborhoods
• Neural Simulation
• Zero-shot Generalization