Data-Driven Control for Continuum Robots Based on Discrete Zeroing Neural Networks

Collision-free path planning for cable-driven continuum robot based on improved artificial potential field

“…The step size of λ t and δ t should be chosen based on the task requirements of the system for that the step size should be taken large when the continuum robot is far from the target point to better improve the speed of path generation, and meanwhile, the small step size should be set to improve the planning accuracy when reaching near the target point. According to engineering experience, the decay function for step size can be designed as (18)…”

“…Meanwhile, it is well known that the mapping between the configuration space and work space of continuum robot is highly complicated. Several scholars have conducted researches on the collision-free path planning for the continuum robot and related strategies have been addressed, such as Jacobian-based method [12], rapidly-exploring random trees (RRT) [13], optimization method [14][15][16], intelligent learning [17,18], curve simulation method [19], APF [20][21][22], follow the leader (FTL) [23,24] and other methods [25][26][27]. Memar et al [12] proposed an improved Jacobian-based motion planning method based on the constant curvature model.…”

“…J Lai et al [14] computed the inverse kinematics by solving a damped least-square optimization problem for the task of tip trajectory tacking under constrained conditions. T Ning et al [18] presented a data-driven model-free motion control strategy based on continuous-time zeroing neural network, which shows superior performance in terms of accuracy. However, the scheme only utilizes the end-effector position feedback for trajectory tracking, which ignoring the attitude of the continuum robot.…”

Continuum Robots and Magnetic Soft Robots: From Models to Interdisciplinary Challenges for Medical Applications

“…Various machine-learning models have been successfully employed in various application scenarios of continuum robots. These models include neural networks [ 142 , 143 , 144 ], reinforcement learning [ 145 ], support vector machines [ 146 ], and a myriad of combined strategies [ 147 ]. They have demonstrated exceptional performance in trajectory prediction, action recognition, and fault detection.…”

Modeling of continuum robots: A review

“…Time zeroing neural network in continuum robot control has been validated initially as well, while in 2022 research the discrete zeroing neural networks can also be applied to CRs kinematic control problems [22]. This modality-free control scheme obtains the positive discretization formulation, furthermore, with high control accuracy.…”