Articulated Objects Explained: How Robots Grasp Moving 3D Worlds

This article introduces articulated objects — multi-part 3D structures connected by joints like hinges and sliders — explaining their core components (links and joints), common joint types (revolute and prismatic), and why understanding their motion is crucial for robot manipulation, digital twins, and interactive VR/AR environments.

Network Intelligence Research Center (NIRC)
Network Intelligence Research Center (NIRC)
Network Intelligence Research Center (NIRC)
Articulated Objects Explained: How Robots Grasp Moving 3D Worlds

What Are Articulated Objects?

Articulated objects are everywhere in daily life: cabinet doors that swing open, drawers that slide in and out, laptop screens that rotate on hinges, and robot arms with multiple joints. All share a common structure — they consist of multiple relatively rigid parts (called links or parts ) connected by joints that constrain their relative motion.

Core Elements: Parts, Joints, and Motion Relationships

Take a typical cabinet: the cabinet body stays fixed, the door is attached via a hinge (a revolute joint) allowing rotation around a fixed axis, and the drawer moves along rails (a prismatic joint) allowing linear translation. In robotics terminology, the rigid components are Links and the connecting structures that define allowable motion are Joints .

Cabinet door rotating around a hinge
Cabinet door rotating around a hinge
Drawer sliding along rails
Drawer sliding along rails

Common Joint Types

Revolute Joint — enables rotation about a fixed axis (e.g., cabinet doors, refrigerator doors, laptop screens).

Prismatic Joint — enables linear translation along a fixed direction (e.g., drawers, sliding doors).

Robot arm with multiple revolute joints
Robot arm with multiple revolute joints

Why Robots Need to Understand Articulated Objects

For humans, opening a cabinet door is trivial. For a robot, it requires a multi-step perception and planning pipeline:

Part identification — recognize which component is the door versus the cabinet body.

Interaction point detection — locate the handle or graspable area.

Joint type classification — determine whether the door rotates or translates.

Joint parameter estimation — estimate the rotation axis position and orientation (for revolute) or translation direction (for prismatic).

Trajectory planning — compute a collision-free path for the robot arm to actuate the joint correctly.

Robot arm reaching for a cabinet handle
Robot arm reaching for a cabinet handle

If a robot only knows "there is a cabinet" but not how its parts move, it cannot interact with it effectively. This drives modern robotics research from simple object recognition toward deeper structural and kinematic understanding.

Robot manipulating an articulated object
Robot manipulating an articulated object

Broader Applications

Beyond embodied AI and robot simulation, articulated object models are essential for:

Digital twins — giving virtual replicas interactive, physically plausible behavior.

Smart homes — enabling automated interaction with furniture and appliances.

AR/VR — allowing users to manipulate virtual objects with realistic joint constraints.

3D content generation — creating assets that can be animated procedurally.

Moving from "seeing the world" to understanding "why things in the world move the way they do" is a critical step toward robots that operate reliably in real physical environments.

Original Source

Signed-in readers can open the original source through BestHub's protected redirect.

Sign in to view source
Republication Notice

This article has been distilled and summarized from source material, then republished for learning and reference. If you believe it infringes your rights, please contactadmin@besthub.devand we will review it promptly.

Embodied AIRoboticsVR/ARdigital twinsarticulated objectsprismatic jointrevolute joint
Network Intelligence Research Center (NIRC)
Written by

Network Intelligence Research Center (NIRC)

NIRC is based on the National Key Laboratory of Network and Switching Technology at Beijing University of Posts and Telecommunications. It has built a technology matrix across four AI domains—intelligent cloud networking, natural language processing, computer vision, and machine learning systems—dedicated to solving real‑world problems, creating top‑tier systems, publishing high‑impact papers, and contributing significantly to the rapid advancement of China's network technology.

0 followers
Reader feedback

How this landed with the community

Sign in to like

Rate this article

Was this worth your time?

Sign in to rate
Discussion

0 Comments

Thoughtful readers leave field notes, pushback, and hard-won operational detail here.