Abstract
In this study, the authors focus on the structural design of and recovery methods for a damaged quadruped robot with a limited number of functional legs. Because the pre-designed controller cannot be executed when the robot is damaged, a control strategy to avoid task failures in such a scenario should be developed. Not only the control method but also the shape and structure of the robot itself are significant for the robot to be able to move again after damage. We present a caterpillar-inspired quadruped robot (CIQR) and a self-learning mudskipper inspired crawling (SLMIC) algorithm in this research. The CIQR is realized by imitating the prolegs of caterpillars and by using a numerical optimization technique. A reinforcement learning method called Q-learning is employed to improve the adaptability of locomotion based on the crawling behavior of mudskipper. The results show that the proposed robotic platform and recovery method can improve the moving ability of the damaged quadruped robot with a few active legs in both simulations and experiments. Moreover, we obtained satisfactory results showing that a damaged multi-legged robot with at least one leg could travel properly along the required direction. Furthermore, the presented algorithm can successfully be employed in a damaged quadruped robot with fewer than four legs.
Highlights
In recent years, legged robots have been widely utilized in several applications due to the fact that legged robots are more flexible than wheel-based robots in terms of mobility and energy efficiency [1].Despite the agility and complex maneuverability of legged robots over wheeled robots, one major drawback is their inability to operate when they are damaged
Two major experiments were conducted in a simulation environment and with a real robot to evaluate the performance and improvement of the proposed robot structural design and the recovery method
To achieve the designed upright structure, the shape of the legs of caterpillar-inspired quadruped robot (CIQR) was optimized by numerical simulation as mentioned in the first part of this experiment
Summary
In recent years, legged robots have been widely utilized in several applications due to the fact that legged robots are more flexible than wheel-based robots in terms of mobility and energy efficiency [1]. The robot could start the process of identifying its current model and employing an evolutionary algorithm to determine the behavior (self-learning method) that provided the best movement. They showed that a robot with the broken legs can travel forward. The Q-learning method is integrated with mudskipper-inspired behavior to enable the robot to move faster in a more efficient manner Both numerical simulation and practical experiment with a CIQR are conducted to test the performance of proposed recovery algorithm.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
