JODA: Composable Joint Dynamics for Articulated Objects

TL;DR

JODA introduces a structured, interpretable framework for modeling detailed joint dynamics in articulated objects, enabling realistic simulation and control through inference and refinement from multimodal data.

Contribution

It presents a novel joint-level dynamics representation using a three-channel field, integrating vision-language models for inference and enabling controllable, differentiable simulation.

Findings

JODA accurately models diverse joint behaviors.

The framework supports manipulation and gradient-based refinement.

Code and assets will be publicly released.

Abstract

Articulated objects used in simulation and embodied AI are typically specified by geometry and kinematic structure, but lack the fine-grained dynamical effects that govern realistic mechanical behavior, such as frictional holding, detents, soft closing, and snap latching. Existing approaches either ignore the detailed structure of dynamics entirely, or use simple models with limited expressiveness. We introduce JODA, a framework for generating joint-level dynamics as a structured three-channel field over the joint degree of freedom, capturing conservative forces, dry friction, and damping. Instantiated using shape-constrained piecewise cubic interpolation (PCHIP), this formulation defines a compact and expressive function space that is both interpretable and compatible with differentiable simulation. Building on this representation, we develop methods for inferring and refining joint dynamics from multimodal inputs. Given visual observations and joint context, a vision-language model proposes structured dynamical primitives, which are composed into a unified dynamics field. The resulting representation supports both direct manipulation and gradient-based refinement. We demonstrate that JODA enables plausible and controllable modeling of diverse joint behaviors, providing a unified interface for inference, editing, and optimization. Code and example assets with their generated profiles will be released upon publication.