Impact Localization for Haptic Input Devices Using Hybrid Laminates with Sensoric Function

Abstract

The required energy savings can be achieved in all automotive domains through weight savings and the merging of manufacturing processes in production. This fact is taken into account through functional integration in lightweight materials and manufacturing in a process close to large-scale production. In previous work, separate steps of a process chain for manufacturing a center console cover utilizing a sensoric hybrid laminate have been developed and evaluated. This includes the process steps of joining, forming and inline polarization as well as connecting to an embedded system. This work continues the research process by evaluating impact localization methods to use the center console as a haptic input device. For this purpose, different deep learning methods are derived from the state of the art and analyzed for their applicability in two consecutive studies. The results show that MLPs, LSTMs, GRUs and CNNs are suitable to localize impacts on the novel laminate with high localization rates of up to 99%, and thus the usability of the developed laminate as a haptic input device has been proven.

Keywords

• impact localization
• localization
• machine learning
• deep learning
• artificial intelligence
• hybrid assembled composite