Inicio  /  Applied Sciences  /  Vol: 13 Par: 19 (2023)  /  Artículo
ARTÍCULO
TITULO

Adaptive Locomotion Learning for Quadruped Robots by Combining DRL with a Cosine Oscillator Based Rhythm Controller

Xiaoping Zhang    
Yitong Wu    
Huijiang Wang    
Fumiya Iida and Li Wang    

Resumen

Animals have evolved to adapt to complex and uncertain environments, acquiring locomotion skills for diverse surroundings. To endow a robot?s animal-like locomotion ability, in this paper, we propose a learning algorithm for quadruped robots based on deep reinforcement learning (DRL) and a rhythm controller that is based on a cosine oscillator. For a quadruped robot, two cosine oscillators are utilized at the hip joint and the knee joint of one leg, respectively, and, finally, eight oscillators form the controller to realize the quadruped robot?s locomotion rhythm during moving. The coupling between the cosine oscillators of the rhythm controller is realized by the phase difference, which is simpler and easier to realize when dealing with the complex coupling relationship between different joints. DRL is used to help learn the controller parameters and, in the reward function design, we address the challenge of terrain adaptation without relying on the complex camera-based vision processing but based on the proprioceptive information, where a state estimator is introduced to achieve the robot?s posture and help finally utilize the food-end coordinate. Experiments are carried out in CoppeliaSim, and all of the flat, uphill and downhill conditions are considered. The results show that the robot can successfully accomplish all the above skills and, at the same time, with the reward function designed, the robot?s pitch angle, yaw angle and roll angle are very small, which means that the robot is relatively stable during walking. Then, the robot is transplanted to a new scene; the results show that although the environment is previously unencountered, the robot can still fulfill the task, which demonstrates the effectiveness and robustness of this proposed method.

 Artículos similares

       
 
Shabnom Mustary, Mohammod Abul Kashem, Mohammad Asaduzzaman Chowdhury and Jia Uddin    
Robotics is a crucial technology of Industry 4.0 that offers a diverse array of applications in the industrial sector. However, the quality of a robot?s manipulator is contingent on its stability, which is a function of the manipulator?s parameters. In p... ver más
Revista: Computers

 
Elena Rubies, Ricard Bitriá, Eduard Clotet and Jordi Palacín    
This work presents a remote control device designed to drive the arm gestures of an assistant humanoid mobile robot. The remote control is a master device with two passive arms configured to replicate the four degrees of freedom of each arm of the origin... ver más
Revista: Applied Sciences

 
Chang-Wan Ha, Sungho Jung, Jinseong Park and Jaewon Lim    
Magnetic levitation can reduce particulate contamination that occurs during wafer transportation in the semiconductor manufacturing process. This technology radically eliminates contact between the wafer and the transport system, reducing friction, wear,... ver más
Revista: Applied Sciences

 
Suleiman Abu Kharmeh, Emad Natsheh, Batoul Sulaiman, Mohammad Abuabiah and Saed Tarapiah    
Datasets used for artificial-neural-network and machine-learning applications play a vital role in the research and application of such techniques in solving real-life problems. The construction and availability of large datasets to be used in the off-li... ver más
Revista: Applied Sciences

 
Nikolaos Kladovasilakis, Ioannis Kostavelis, Paschalis Sideridis, Eleni Koltzi, Konstantinos Piliounis, Dimitrios Tzetzis and Dimitrios Tzovaras    
During the last decade, soft robotic systems, such as actuators and grippers, have been employed in various commercial applications. Due to the need to integrate robotic mechanisms into devices operating alongside humans, soft robotic systems concentrate... ver más
Revista: Applied Sciences