Robot-assisted manipulation of flexible components in the production of electric vehicles

Flexible components such as cables and cable harnesses play a key role in the production of electric vehicles. However, they cannot be handled automatically due to a lack of robust processes. The »RoboCable« project researches new AI methods for robot-assisted handling and manipulation of flexible components.

In our approach, robots learn tasks virtually in the simulation environment and from real sensor data. The sensors enable autonomous execution of learned assembly activities. Despite the variability of flexible components and process uncertainties, new assembly tasks can be learned in simulation, allowing existing tasks to continue without interruption, thereby minimizing programming and downtime. RoboCable also facilitates the use of lightweight robots, alongside traditional industrial robots.