New research revolutionizes quadruped bounding with efficient learning method
image: The cover image is based on the Research Article Efficient learning of robust quadruped bounding using pretrained neural networks by Zhicheng Wang et al., https://doi.org/10.1049/csy2.12062. and Original Article Disturbance rejection for biped robots during walking and running using control moment gyroscopes by Haochen Xu et al., https://doi.org/10.1049/csy2.12070. view more
Credit: IET Cyber-Systems and Robotics
In a new study published in special issue of journal Institution of Engineering and Technology (IET) Cyber-systems and Robotics, researchers from Zhejiang University experienced in legged robot motion and control, pre-trained the neural network (NN) using data from a robot operated by conventional model-based controllers. This pre-training served as a preliminary measure to prevent behaviour overriding and reward hacking - a situation where agents secure rewards unexpectedly, typically due to the optimization inadvertently reaching a local optimum rather than the intended one. Following the pre-training, the team implemented deep reinforcement learning (DRL), a trendsetting learning-based approach in legged locomotion control. Notably, a reward function was designed considering contact points and phases, which enforced gait symmetry and periodicity, culminating in an improved bounding performance. The DRL methods developed were initially learned in a simulated environment and then successfully deployed on a real quadruped robot, the Jueying Mini. The resultant locomotion was tested across various environments, both indoors and outdoors, demonstrating efficient computing and excellent locomotion results. The control method developed for the Jueying Mini robot was found to yield robust bounding gaits in both simulation and real-world settings. This has tremendous implications for enhancing the agility and adaptability of quadruped robots in varied indoor and outdoor environments.
The study's next steps involve integrating the current method with environmental perception tools, such as cameras or LiDAR systems. While these were not used in the current study, they can offer more accurate localization of the robot and navigation for bounding across different terrains.
In another study published in the special issue, researchers have pioneered the use of control moment gyroscopes (CMGs) in improving biped robots' stability, particularly during high-speed operations. Biped robots, increasingly used across industries, struggle with balance and disturbance rejection as their speed increases. The newly developed CMG assistance strategy enhances their ability to resist impact and quickly regain balance. Simulation results confirm the CMGs' effectiveness in significantly enhancing robots' stability. This innovative use of CMGs represents a leap in biped robotics, with plans to further integrate CMGs for improved real-world performance in high-dynamic motions.
###
References
DOI
Funding information
This work was supported by the National Key R&D Program of China (Grant No. 2020YFB1313300) and Key Research Project of Zhejiang Lab (Grant No. 2021NB0AL03).
About IET Cyber-Systems and Robotics
IET Cyber-Systems and Robotics is a Gold Open Access journal co-published by the Institution of Engineering and Technology (IET) and Zhejiang University Press that publishes novel research and survey articles in the broad areas of cyber-systems and robotics, with an emphasis on artificial intelligent systems enabled by advanced electronics and modern information technologies. The journal has been indexed by ESCI, EI Compendex, Scopus, Inspec, DOAJ, etc.