Neural network control has been a research hotspot in academic fields due to the strong ability of computation. One of its wildly applied fields is robotics. In recent years, plenty of researchers have devised different types of dynamic neural network (DNN) to address complex control issues in robotics fields in reality. Redundant manipulators are no doubt indispensable devices in industrial production. There are various works on the redundancy resolution of redundant manipulators in performing a given task with the manipulator model information known. However, it becomes knotty for researchers to precisely control redundant manipulators with unknown model to complete a cyclic-motion generation CMG task, to some extent. It is worthwhile to investigate the data-driven scheme and the corresponding novel dynamic neural network (DNN), which exploits learning and control simultaneously. Therefore, it is of great significance to further research the special control features and solve challenging issues to improve control performance from several perspectives, such as accuracy, robustness, and solving speed.
The potential research directions can be divided into two parts: theoretical improvement and application innovation. Firstly, aiming at the current neural network (NN)-based solvers, we expect to see more technologies to improve the performance from several perspectives, such as solving speed, control performance, learning efficiency, and robustness. Different types of optimal algorithms, such as quasi-newton method, gradient descent method, genetic algorithm, etc, can be exploited to tackle the problem. In addition, investigations on dynamic neural networks (DNN) to control robots are the main part of the research topic. In general, innovations in neural networks are of great significance in this topic.
Secondly, based on the data acquisition and model analysis, the data-driven method has become an indispensable artificial intelligence technology in modern industrial society with an extensive application prospect. It is widely recognized that the data-driven technology is capable of handling the unknown issues in the system with the remarkable learning ability. In addition, applications on different types of robots are encouraged, including but not limited to redundant manipulators, dual-arm robots, mobile robots, continuum robots, and soft robots.
Neural network control has been a research hotspot in academic fields due to the strong ability of computation. One of its wildly applied fields is robotics. In recent years, plenty of researchers have devised different types of dynamic neural network (DNN) to address complex control issues in robotics fields in reality. Redundant manipulators are no doubt indispensable devices in industrial production. There are various works on the redundancy resolution of redundant manipulators in performing a given task with the manipulator model information known. However, it becomes knotty for researchers to precisely control redundant manipulators with unknown model to complete a cyclic-motion generation CMG task, to some extent. It is worthwhile to investigate the data-driven scheme and the corresponding novel dynamic neural network (DNN), which exploits learning and control simultaneously. Therefore, it is of great significance to further research the special control features and solve challenging issues to improve control performance from several perspectives, such as accuracy, robustness, and solving speed.
The potential research directions can be divided into two parts: theoretical improvement and application innovation. Firstly, aiming at the current neural network (NN)-based solvers, we expect to see more technologies to improve the performance from several perspectives, such as solving speed, control performance, learning efficiency, and robustness. Different types of optimal algorithms, such as quasi-newton method, gradient descent method, genetic algorithm, etc, can be exploited to tackle the problem. In addition, investigations on dynamic neural networks (DNN) to control robots are the main part of the research topic. In general, innovations in neural networks are of great significance in this topic.
Secondly, based on the data acquisition and model analysis, the data-driven method has become an indispensable artificial intelligence technology in modern industrial society with an extensive application prospect. It is widely recognized that the data-driven technology is capable of handling the unknown issues in the system with the remarkable learning ability. In addition, applications on different types of robots are encouraged, including but not limited to redundant manipulators, dual-arm robots, mobile robots, continuum robots, and soft robots.