2023 Volume 12 Issue 4 Pages 786-792
Humans possess an outstanding ability to understand contact states, thereby leading to appropriate actions. In this study, we consider the operation of autonomous machining tasks on heterogeneous materials using robots; this mechanism poses a challenge as robotic machining is mainly performed on homogeneous materials using the current robotic technology. Herein, we propose a method to recognize contact states, e. g. the materials and deformation types of fragile objects, to selectively process parts of tissues without damaging other tissues. Furthermore, an identification method is proposed based on a time-delay neural network (TDNN) to identify fragile objects and their deformation types, such as elastic and plastic, for real-time applications. We used a multi degrees-of-freedom (DoF) robotic arm to cut and process fragile objects. We examined the planning of an appropriate trajectory based on the contact states identified by the TDNN during cutting motion. The selective cutting motion of a robot was demonstrated with high success rates despite variations in the cutting speed.
