Multidimensional cerebellar computations for flexible kinematic control of movements

Both the environment and our body keep changing dynamically. Hence, ensuring movement precision requires adaptation to multiple demands occurring simultaneously. Here we show that the cerebellum performs the necessary multi-dimensional computations for the flexible control of different movement parameters depending on the prevailing context. This conclusion is based on the identification of a manifold-like activity in both mossy fibers (MF, network input) and Purkinje cells (PC, output), recorded from monkeys performing a saccade task. Unlike MFs, the properties of PC manifolds developed selective representations of individual movement parameters. Error feedback-driven climbing fiber input modulated the PC manifolds to predict specific, error type-dependent changes in subsequent actions. Furthermore, a feed-forward network model that simulated MF-to-PC transformations revealed that amplification and restructuring of the lesser variability in the MF activity is a pivotal circuit mechanism. Therefore, flexible control of movement by the cerebellum crucially depends on its capacity for multi-dimensional computations.

Rolling Biped Polynomial Motion Planning

This work discloses a kinematic control model to describe the geometry of motion of a two-wheeled biped’s limbs. Limb structure is based on a four-bar linkage useful to alleviate damping motion during self-balance. The robot self-balancing kinematics geometry combines with user-customized polynomial vector fields. The vector fields generate safe reference trajectories. Further, the robot is forced to track the reference path by a model-based time-variant recursive controller. The proposed formulation showed effectiveness and reliable performance through numerical simulations.

Kinematic Control of Manipulator with Remote Center of Motion Constraints Synthesised by a Simplified Recurrent Neural Network

Redundancy manipulators need favorable redundancy resolution to obtain suitable control actions to guarantee accurate kinematic control. Among numerous kinematic control applications, some specific tasks such as minimally invasive manipulation/surgery require the distal link of a manipulator to translate along such fixed point. Such a point is known as remote center of motion (RCM) to constrain motion planning and kinematic control of manipulators. Recurrent neural network (RNN) which possesses parallel processing ability, is a powerful alternative and has achieved success in conventional redundancy resolution and kinematic control with physical constraints of joint limits. However, up to now, there still is few related works on the RNNs for redundancy resolution and kinematic control of manipulators with RCM constraints considered yet. In this paper, for the first time, an RNN-based approach with a simplified neural network architecture is proposed to solve the redundancy resolution issue with RCM constraints, with a new and general dynamic optimization formulation containing the RCM constraints investigated. Theoretical results analyze and convergence properties of the proposed simplified RNN for redundancy resolution of manipulators with RCM constraints. Simulation results further demonstrate the efficiency of the proposed method in end-effector path tracking control under RCM constraints based on a redundant manipulator.

Inverse Kinematic Control of a Delta Robot Using Neural Networks in Real-Time

This paper presents an inverse kinematic controller using neural networks for trajectory controlling of a delta robot in real-time. The developed control scheme is purely data-driven and does not require prior knowledge of the delta robot kinematics. Moreover, it can adapt to the changes in the kinematics of the robot. For developing the controller, the kinematic model of the delta robot is estimated by using neural networks. Then, the trained neural networks are configured as a controller in the system. The parameters of the neural networks are updated while the robot follows a path to adaptively compensate for modeling uncertainties and external disturbances of the control system. One of the main contributions of this paper is to show that updating the parameters of neural networks offers a smaller tracking error in inverse kinematic control of a delta robot with consideration of joint backlash. Different simulations and experiments are conducted to verify the proposed controller. The results show that in the presence of external disturbance, the error in trajectory tracking is bounded, and the negative effect of joint backlash in trajectory tracking is reduced. The developed method provides a new approach to the inverse kinematic control of a delta robot.

ALGORITHMS FOR KINEMATIC CONTROL OF MULTI-LINK MANIPULATION ROBOTS BASED ON A FUZZY NEURAL NETWORK

The paper considers the possibility of constructing a kinematic control algorithm for manipulating robots with a serial-connected links. The construction of a control system based on a fuzzy neural network is proposed. The results of experimental studies on the selection of parameters of a fuzzy neural network in accordance with the set optimality criterion (in terms of speed), taking into account the subsequent iterative refinement by the Newton-Raphson method, are presented. The following network parameters are considered: the number and type of node membership functions, the size of the training sample with a different number of training approaches. An algorithm for forming a training sample for fuzzy neural networks is proposed in order to reduce the positioning error of the working body of the manipulating mechanism near the outer boundary of the workspace. The possibility of adapting the kinematic control algorithms by adjusting the parameters of the membership functions in the network nodes when performing the same type of tasks, based on the data of the Newton-Raphson refinement algorithm, is demonstrated. In the framework of this work, a comparative analysis of the developed kinematic control algorithm with algorithms based on iterative and neural network methods for solving the inverse kinematics problem of a manipulative robot is carried out. The conclusion is made about the increase in the speed for calculations of kinematic control algorithms while maintaining the required accuracy