Behavioral Cloning for Robotic Connector Assembly: An Empirical Study

TL;DR

This paper investigates the use of behavioral cloning to teach robots connector insertion tasks by learning from human demonstrations, combining visual and force feedback to achieve high success rates.

Contribution

It provides an empirical analysis of different neural network architectures for action prediction in connector assembly, demonstrating over 90% success across various geometries.

Findings

Achieved over 90% success rate in connector insertion tasks.

Compared multiple neural network architectures for effectiveness.

Demonstrated the feasibility of learning from human demonstrations for complex assembly tasks.

Abstract

Automating the assembly of wire harnesses is challenging in automotive, electrical cabinet, and aircraft production, particularly due to deformable cables and a high variance in connector geometries. In addition, connectors must be inserted with limited force to avoid damage, while their poses can vary significantly. While humans can do this task intuitively by combining visual and haptic feedback, programming an industrial robot for such a task in an adaptable manner remains difficult. This work presents an empirical study investigating the suitability of behavioral cloning for learning an action prediction model for connector insertion that fuses force-torque sensing with a fixed position camera. We compare several network architectures and other design choices using a dataset of up to 300 successful human demonstrations collected via teleoperation of a UR5e robot with a SpaceMouse under varying connector poses. The resulting system is then evaluated against five different connector geometries under varying connector poses, achieving an overall insertion success rate of over 90 %.