Disassembly from scratch: An object-centric approach for robotic autonomous disassembly with zero contact/interference information

Disassembly is important to circular economy, yet it remains challenging to be robotised due to the inherent uncertainty of end-of-life (EoL) products (e.g., corrosion, rust and missing part). A key challenge in robotising disassembly is that the interference information (e.g., spatial relations of components and assembly methods) is usually unavailable or inaccurate. To address this core problem, this paper presents an object-centric disassembly (OCD) framework, allowing robots to adapt dynamically to varying conditions without requiring prior knowledge of component contacts or interferences. In this framework, an OCD model is constructed in which individual disassembly tasks and their associated conditions are represented as modular units that are continuously refined through autonomous exploration. The performance of the framework is evaluated using a robotic platform integrating intelligent perception, planning, and execution modules for autonomous disassembly under uncertain environments. Experimental evaluations provide evidence that the proposed method enhances the flexibility and adaptability of robotic disassembly. Our approach and this new capability allow disassembly robots to handle real-world uncertainties effectively, eliminating the need for pre-defined interference information. • Proposes an object-centric disassembly (OCD) framework for robotic autonomy. • Enables disassembly from scratch without prior contact or interference data. • Validates the OCD model on a robotic platform with perception, planning, and execution. • Demonstrates adaptability of robotic disassembly to real-world uncertainties. • Supports industrial remanufacturing and the transition to a circular economy.