This article presents a solution to the problem of gait synthesis for a three-legged robot with three actuators in each leg. In other words, it is shown how to coordinate the robot leg actuators in order to maximize the robot walking speed. The position in time of each leg actuator is described by a periodic function that is found by using a reinforcement learning technique called Learning Automata. MATLAB/Simulink and the SimMechanics Toolbox are used to simulate possible solutions for the problem and the simulated robot response is evaluated at the end of each trial. After the reinforcement learning algorithm converges to a solution, it is applied to the real robot that was built using the Bioloid Comprehensive Kit, an educational robot kit manufactured by Robotis. The response of the real robot is then evaluated and compared with the simulated robot response. It is shown that proposed solution generates a quite satisfactory gait for the real robot.

No abstract

This article is concerned with the gait synthesis problem of a hybrid robot (in this case, a four-legged robot with free wheels on its feet) considering multiple criteria. It is assumed that the position of each leg actuator over time is described by a periodic function with parameters that are determined using the learning automata reinforcement learning algorithm. Analysis of the robot morphology is used to group similar legs and decrease the number of actuator functions that must be determined. MATLAB/Simulink/SimMechanics Toolbox are used to simulate the robot gait. The simulated robot response is evaluated by the reinforcement learning algorithm considering: 1) the robot frontal speed, 2) the "smoothness" of the robot movements, 3) the largest torque required by all leg actuators, and 4) the robot energy consumption. When the reinforcement learning algorithm converges to a good solution, it is applied to the real robot which was built using the Bioloid Comprehensive Kit, an educational robot kit manufactured by ROBOTIS. The responses of the simulated and real robot are then compared and are shown to be similar.

Actuator Coordination for Legged Mobile Robots Using Reinforcement Learning: Simulation and ImplementationThis article presents a solution to the problem of how to coordinate the actuators of a legged robot such that its frontal speed is maximized. It is assumed that the position of each leg actuator is described by a periodic function that has to be determined using a reinforcement learning technique called Learning Automata. Analysis of the robot morphology is used to group similar legs and decrease the number of actuator functions that must be determined. MATLAB/Simulink and the SimMechanics Toolbox are used to simulate the robot walking on a flat surface. The simulated robot response is evaluated by the reinforcement learning technique considering: 1) the robot frontal speed, 2) the smoothness of the robot movements, 3) the largest torque required by all actuators, and 4) the energy consumption. After the reinforcement learning algorithm converges to a solution, the actuators functions are applied to the real robot that was built using the Bioloid Comprehensive Kit, an educational robot kit manufactured by Robotis. The response of the real robot is then evaluated and RESUMOEste artigo apresenta uma solução para o problema de coordenação dos atuadores das pernas de robôs móveis com o objetivo principal de maximizar a sua velocidade frontal.É assumido que a posição no tempo de cada atuadoré descrita por uma função periódica que deve ser determinada de forma iterativa por um algoritmo de aprendizado por reforço. As pernas similares do robô são identificadas e agrupadas visando diminuir o número de funções que precisam ser determinadas. O toolbox SimMechanics do software MATLAB/Simulinké usado para simular o caminhar do robô em uma superfície plana. O desempenho do robô simuladoé medido considerando: a) a velocidade frontal e a suavidade na locomoção do robô, e b) o máximo torque e o consumo de energia dos atuadores. As funções que foram determinadas no ambiente de simulação pelo algoritmo de reforço são então usadas nos atuadores do robô real construído usando o

No abstract