Hybrid learning and planning improve robotic assembly from imperfect CAD data
CAD-Based Relation Learning and Geometric-Symbolic Planning for Robotic Assembly
Robotics
Summary
Planning how robots take apart or assemble complex machines is hard because there are so many possible ways to do it, and CAD models often lack clear contact details. The authors combine a neural network that guesses relationships between parts from 3D point clouds with human checks to fix mistakes. They turn these relations into a symbolic graph that helps a planner find good sequences for robot actions efficiently. Their method is much faster and more successful than previous ones, even on big assemblies with many parts.
What this means in practice
- •For industrial automation teams: Create faster and more reliable robotic assembly and disassembly plans from imperfect CAD models to speed up factory setup and maintenance.
- •For robotic system integrators: Incorporate human verification with AI-driven planning to handle uncertain or incomplete CAD data in robotic assembly workflows.
Authors
Fabian Harlacher, Christian Friedrich
Abstract
Assembly Sequence Planning (ASP) remains a challenging problem due to its combinatorial nature, making exhaustive planning approaches impractical for complex industrial assemblies. Furthermore, many CAD models lack reliable semantic contact information or require extensive manual preprocessing, limiting the applicability of existing methods. This paper presents a hybrid ASP framework combining learning-based relation extraction with geometric-symbolic reasoning to generate feasible robotic disassembly sequences from imperfect CAD data. A neural network predicts semantic geometric relations from point clouds, while human-in-the-loop verification enables correction of uncertain predictions and planning failures. Extracted relations are transformed into a symbolic assembly graph, enabling a geometric-symbolic planner to efficiently compute locally valid sets of robotic manipulation primitives. A visibility-based ray-casting strategy guides the search for feasible disassembly directions without requiring an exhaustive combinatorial search, while the local solution space enables efficient sequence optimization. The framework is evaluated on an introduced assembly dataset and on the ASAP test dataset. On the ASAP test dataset, the proposed planner achieves an 85.83% planning success rate while reducing the median planning time by more than one order of magnitude across all assembly sizes and by more than a factor of 50 for assemblies with more than 30 components compared to the baseline. The results demonstrate that the proposed hybrid framework enables efficient robotic assembly sequence planning from imperfect CAD data while substantially reducing planning time. By combining learning-based feature segmentation, human-in-the-loop verification, and geometric-symbolic reasoning, the framework provides a practical foundation for scalable and adaptable robotic assembly and disassembly planning.