Kinematic Kitbashing for Modeling Functional Articulated Objects

2025-10-14

AI Summary

This paper addresses the problem of automatic synthesis of function-aware articulated objects—generating geometrically valid assemblies that satisfy user-specified functional objectives, such as collision-free actuation, end-effector reachability, and trajectory tracking. To this end, we propose Kinematic Kitbashing, the first framework unifying kinematics-aware geometric matching with function-driven optimization. Our method employs a vector distance function based on motion sequence sampling for robust part alignment and introduces a kinematics-aware connection energy term. Leveraging an annealed Riemannian Langevin dynamics sampler, we jointly optimize part placement and functional objectives while handling non-differentiable constraints. Experiments demonstrate that our approach significantly outperforms prior methods across geometric validity, kinematic feasibility, and functional metrics. We successfully synthesize high-quality, animatable objects—including wheeled mechanisms, multi-segment lamps, gear-propeller systems, and reconfigurable furniture—demonstrating broad applicability and practical utility.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Search and Optimization: Sampling/Simulation-based Search
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Agentic search

Abstract

We introduce Kinematic Kitbashing, an automatic framework that synthesizes functionality-aware articulated objects by reusing parts from existing models. Given a kinematic graph with a small collection of articulated parts, our optimizer jointly solves for the spatial placement of every part so that (i) attachments remain geometrically sound over the entire range of motion and (ii) the assembled object satisfies user-specified functional goals such as collision-free actuation, reachability, or trajectory following. At its core is a kinematics-aware attachment energy that aligns vector distance function features sampled across multiple articulation snapshots. We embed this attachment term within an annealed Riemannian Langevin dynamics sampler that treats functionality objectives as additional energies, enabling robust global exploration while accommodating non-differentiable functionality objectives and constraints. Our framework produces a wide spectrum of assembled articulated shapes, from trash-can wheels grafted onto car bodies to multi-segment lamps, gear-driven paddlers, and reconfigurable furniture, and delivers strong quantitative improvements over state-of-the-art baselines across geometric, kinematic, and functional metrics. By tightly coupling articulation-aware geometry matching with functionality-driven optimization, Kinematic Kitbashing bridges part-based shape modeling and functional assembly design, empowering rapid creation of interactive articulated assets.

Problem

• Automatically synthesizes functionality-aware articulated objects
• Solves spatial placement ensuring geometric soundness and functional goals
• Bridges part-based shape modeling with functional assembly design

Innovation

• Automatically synthesizes functional articulated objects by reusing parts
• Uses kinematics-aware attachment energy for geometric alignment
• Employs annealed Riemannian Langevin dynamics for robust optimization