A dual-arm robotic system for automated multi-branch wire harness assembly in automotive industry

Abstract

Wire harnesses are critical components in modern vehicles, responsible for transmitting electrical signals and power to sensors and actuators. Despite the high level of automation in the automotive industry, wire harness manufacturing still relies heavily largely depends on manual assembly. This is due to the significant challenges posed by the process, such as the complexity of perceiving and manipulating flexible materials and the high degree of customization required. As a result, existing solutions only address specific assembly tasks, rather than the entire process are fragmented, unable to scale to full production, and remain economically unviable for high-mix scenarios. To bridge this gap, this paper presents a novel robotic system for fully automating wire harness assembly. The system adopts a task-level programming methodology that leverages process knowledge to enable fast and easy reconfiguration. Additionally, it incorporates specific solutions to address key challenges in multi-branch wire harness manipulation, such as cable separation and entanglement prevention. The system’s performance was evaluated in two real-world assembly scenarios using a dual-arm robot. Experimental results demonstrate the system’s effectiveness and ease of reconfiguration, achieving success rates of 55% and 73% in two complex multi-branch wire harness assembly processes, and highlight areas of improvement, which will be further investigated in future works. The system repository is openly available allowing other researchers to build their solutions upon the proposed methodology.