On CAD Informed Adaptive Robotic Assembly

TL;DR

This paper presents a CAD-informed robotic assembly system that automates the transition from CAD models to adaptive, perception-driven robotic assembly processes, enabling efficient and flexible manufacturing workflows.

Contribution

The system integrates CAD-based intent capture with deep learning perception models trained in simulation to generate task-level instructions for robotic assembly.

Findings

Successful assembly of interlocking 3D parts by two robots

Simulation-tuned recipes transfer effectively to real robots

Perception models accurately identify parts from CAD data

Abstract

We introduce a robotic assembly system that streamlines the design-to-make workflow for going from a CAD model of a product assembly to a fully programmed and adaptive assembly process. Our system captures (in the CAD tool) the intent of the assembly process for a specific robotic workcell and generates a recipe of task-level instructions. By integrating visual sensing with deep-learned perception models, the robots infer the necessary actions to assemble the design from the generated recipe. The perception models are trained directly from simulation, allowing the system to identify various parts based on CAD information. We demonstrate the system with a workcell of two robots to assemble interlocking 3D part designs. We first build and tune the assembly process in simulation, verifying the generated recipe. Finally, the real robotic workcell assembles the design using the same behavior.