Evolution of central pattern generators for the control of a five-link bipedal walking mechanism

Abstract

Central pattern generators (CPGs), with a basis is neurophysiological studies, are a type of neural network for the generation of rhythmic motion. While CPGs are being increasingly used in robot control, most applications are handtuned for a specific task and it is acknowledged in the field that generic methods and design principles for creating individual networks for a given task are lacking. This study presents an approach where the connectivity and oscillatory parameters of a CPG network are determined by an evolutionary algorithm with fitness evaluations in a realistic simulation with accurate physics. We apply this technique to a five-link planar walking mechanism to demonstrate its feasibility and performance. In addition, to see whether results from simulation can be acceptably transferred to real robot hardware, the best evolved CPG network is also tested on a real mechanism. Our results also confirm that the biologically inspired CPG model is well suited for legged locomotion, since a diverse manifestation of networks have been observed to succeed in fitness simulations during evolution.

When Specialists Transition to Generalists: Evolutionary Pressure in Lexicase Selection

“…Evolutionary robotics (Nolfi and Floreano, 2000) applies evolutionary principles to the optimization of robotic systems. ER applications include legged locomotion control (Baydin, 2012;Clune et al, 2009), morphological optimization (Paul and Bongard, 2001), and the transfer of controllers to reality (Ruud et al, 2016;Koos et al, 2010) among others. In many cases, ER approaches are moving beyond single objective fitness metrics to enhance the resilience, robustness, and generalizability of controllers (Pinville et al, 2011).…”

Hybrid Adaptive Robust Control Based on CPG and ZMP for a Lower Limb Exoskeleton

“…26 To optimize the CPG parameter, including the parameters of each oscillator and the weight of the coupling between them, evolutionary algorithms are applied. [28][29][30] Hybrid CPG and controller or movement characteristics of the robot such as stability have been applied in order to ameliorate exoskeleton performance and also boom the controllability of such devices. [15][16][17][18][19][20][21][22][23][24][25] Stability is one of the crucial duties of walking mechanisms during gaiting.…”

Improving the parameters of neural oscillators to generate joint trajectories of an exoskeleton for lower limbs

“…Few works have described a suitable methodology to find optimal parameters to this neural oscillators model. In [11] is described a system where the internal connection structure and the feedback pathways from the environment were subject to a genetic algorithm optimization. This system find optimal parameters for a network of neural oscillators applied to a five-link planar bipedal robot.…”