A CPG-based gait planning and motion performance analysis for quadruped robot

Abstract

Purpose To achieve stable gait planning and enhance the motion performance of quadruped robot, this paper aims to propose a motion control strategy based on central pattern generator (CPG) and back-propagation neural network (BPNN). Design/methodology/approach First, the Kuramoto phase oscillator is used to construct the CPG network model, and a piecewise continuous phase difference matrix is designed to optimize the duty cycle of walk gait, so as to realize the gait planning and smooth switching. Second, the mapper between CPG output and joint drive is established based on BP neural network, so that the quadruped robot based on CPG control has better foot trajectory to enhance the motion performance. Finally, to obtain better mapping effect, an evaluation function is resigned to evaluate the proximity between the actual foot trajectory and the ideal foot trajectory. Genetic algorithm and particle swarm optimization are used to optimize the initial weights and thresholds of BPNN to obtain more accurate foot trajectory. Findings The method provides a solution for the smooth gait switching and foot trajectory of the robot. The quintic polynomial trajectory is selected to testify the validity and practicability of the method through simulation and prototype experiment. Originality/value The paper solved the incorrect duty cycle under the walk gait of CPG network constructed by Kuramoto phase oscillator, and made the robot have a better foot trajectory by mapper to enhance its motion performance.

Cardioid oscillator-based pattern generator for imitating the time-ratio-asymmetrical behavior of the lower limb exoskeleton

“…On the contrary, the reference trajectory generated by the central pattern generators (CPGs), a biological neural circuit that generates rhythmic behaviors in animals, is periodical and self-excited. It is important to note that these trajectories possess the locked phase relationships and can be adjusted according to environment changes, thereby attracting significant research attention (Conradt, 2003 ; Acebrón et al, 2005 ; de Pina Filho et al, 2005 ; Morimoto et al, 2008 ; Saito et al, 2009 ; Katayama, 2012 ; Mora et al, 2012 ; Dingguo et al, 2017 ; Ferrario et al, 2018 ; Fu et al, 2018 ; Payam et al, 2018 ; Xie et al, 2019 ; Mokhtari et al, 2020 ; Pasandi et al, 2022 ; Wei et al, 2022 ).…”

“…Recently, CPG models, such as neuron-based CPG model (Saito et al, 2009 ; Katayama, 2012 ; Dingguo et al, 2017 ; Ferrario et al, 2018 ; Payam et al, 2018 ; Xie et al, 2019 ; Mokhtari et al, 2020 ; Pasandi et al, 2022 ; Wei et al, 2022 ) and oscillator-based CPG model (Conradt, 2003 ; Acebrón et al, 2005 ; de Pina Filho et al, 2005 ; Morimoto et al, 2008 ; Mora et al, 2012 ; Fu et al, 2018 ), are used for imitating the swing angles of human lower limbs. The former utilizes an oscillator to imitate the functions of neural cells, while the latter utilizes an oscillator to imitate periodic motions/torques.…”

Optimal Trajectory Planning Control for Quadruped Robot

“…Santos et al [5] proposed an omnidirectional motion planning based on the CPG control method, a trajectory planning method for heading motion was designed, and the effectiveness and correctness of this method on the AIBO quadruped robot platform were verified. Wei et al [6] proposed a motion control approach for quadruped robots based on CPG and neural networks, the motion trajectory was a quintic polynomial, and stable gait planning was achieved. Zhong et al [7] planned the centroid trajectory and joint motion trajectory of the robot, and the dynamic gait stable motion was achieved.…”

High Accuracy Human Motion Trajectory Generation for Exoskeleton Robot Using Curve Fitting Technique

“…According to Miskon et al [3], there are three strategies for generating a trajectory for robot applications: off-line, on-line, and combined or hybrid. The off-line strategy is a strategy that uses either a mathematical model such as a polynomial equation [4], Fourier Transform [5], Central Pattern Generation (CPG) [6], Neural Oscillator [7], or uses recorded or normalized human motion data [8]. The advantage of this strategy is that it does not require any dynamic relationship between the robot and the environment.…”

“…These two methods used predefined trajectories generated from mathematical (cubic) or recorded motion data. Other methods like Complementary Limb Motion Estimation (CLME) [18], Neural Oscillator [7], Gait Phase Switching Algorithm (GPSA) [6], Radial Basis Function (RBF) [19], Neural Network [9], polynomial [20,21], Probabilistic Foam Method (PFM) [22] have also been used to improve accuracy of the generated trajectory profiles to the wearer. However, all the methods discussed so far require redefining constraint parameters (i.e., start time, stop time, start velocity, stop velocity, etc.)…”