Abstract
Advances of soft robotics enabled better mimicking of biological creatures and closer realization of animalsÂ’ motion in the robotics field. The biological creatureÂ’s movement has morphology and flexibility that is problematic deportation to a bio-inspired robot. This paper aims to study the ability to mimic turtle motion using a soft pneumatic actuator (SPA) as a turtle flipper limb. SPAÂ’s behavior is simulated using finite element analysis to design turtle flipper at 22 different geometrical configurations, and the simulations are conducted on a large pressure range (0.11–0.4 Mpa). The simulation results are validated using vision feedback with respect to varying the air pillow orientation angle. Consequently, four SPAs with different inclination angles are selected to build a bio-mimetic turtle, which is tested at two different driving configurations. The nonlinear dynamics of soft actuators, which is challenging to model the motion using traditional modeling techniques affect the turtleÂ’s motion. Conclusively, according to kinematics behavior, the turtle motion path is modeled using the Echo State Network (ESN) method, one of the reservoir computing techniques. The ESN models the turtle path with respect to the actuatorsÂ’ rotation motion angle with maximum root-mean-square error of 1.04 Ă— 10 – 11. The turtle is designed to enhance the robot interaction with living creatures by mimicking their limbsÂ’ flexibility and the way of their motion. © 2021, The Author(s).
Authors
Soliman M.A., Mousa M.A., Saleh M.A., Elsamanty M., Radwan A.G.
Keywords
–
Document Type
Journal
Source
Scientific Reports, Vol. 11, Art. No. 12076, Doi: 10.1038/s41598-021-91136-z