Volkswagen Ag

Felix Stahl

Thomas Eigel

Felix Kallmeyer

Jonas Kaste

Technologies and techniques for automatically generating labeled steering torque data, with which an artificial intelligence (AI) unit is trained to detect hands-off conditions when the vehicle is being operated.

Detection of a hands-off condition through machine learning

The invention relates to a method for improving hands-off recognition in a vehicle with steering torque-based recognition in that swarm data are provided from vehicles that recognize hands-off situations with hand distance sensors in the steering wheel. Both recognition results over a certain route section are compared and, in the case of deviations, the correctness of the results of the hand distance sensors is assumed. On this basis, route sections are determined in which steering torque-based recognition is unreliable. Based on this recognition, systems with steering torque evaluation can then be re-parameterized in order to be more reliable relative to the route.

Growing community of inventors

Braunschweig, Germany

Felix Stahl