Motion Planning for Cutting Flexible Objects Based on Contact State Recognition

Humans possess an outstanding ability to understand contact states, thereby leading appropriate actions. In this study, we consider the operation of autonomous machining tasks on heterogeneous materials using robots; mechanism poses a challenge as robotic is mainly performed homogeneous current technology. Herein, propose method recognize e.g. and deformation types fragile objects, selectively process parts tissues without damaging other tissues. Furthermore, identification proposed based time-delay neural network (TDNN) identify objects their types, such elastic plastic, for real-time applications. We used multi degrees-of-freedom (DoF) arm cut objects. examined planning trajectory states identified by TDNN during cutting motion. The selective motion robot was demonstrated with high success rates despite variations in speed.