KinScene: Model-Based Mobile Manipulation of Articulated Scenes

TL;DR

KinScene enables mobile robots to autonomously understand and manipulate complex articulated scenes through a full-stack approach, facilitating long-horizon tasks in real-world environments.

Contribution

This work introduces KinScene, a novel system for scene-level articulation modeling and planning for mobile manipulation of multiple objects.

Findings

Accurately constructs scene-level kinematic models

Enables long-horizon manipulation in real-world scenes

Demonstrates repeatable and effective scene understanding

Abstract

Sequentially interacting with articulated objects is crucial for a mobile manipulator to operate effectively in everyday environments. To enable long-horizon tasks involving articulated objects, this study explores building scene-level articulation models for indoor scenes through autonomous exploration. While previous research has studied mobile manipulation with articulated objects by considering object kinematic constraints, it primarily focuses on individual-object scenarios and lacks extension to a scene-level context for task-level planning. To manipulate multiple object parts sequentially, the robot needs to reason about the resultant motion of each part and anticipate its impact on future actions. We introduce KinScene, a full-stack approach for long-horizon manipulation tasks with articulated objects. The robot maps the scene, detects and physically interacts with articulated objects, collects observations, and infers the articulation properties. For sequential tasks, the robot plans a feasible series of object interactions based on the inferred articulation model. We demonstrate that our approach repeatably constructs accurate scene-level kinematic and geometric models, enabling long-horizon mobile manipulation in a real-world scene. Code and additional results are available at https://chengchunhsu.github.io/KinScene/