Preeti
An international group of researchers has developed a new method to imitate human motion using central pattern generators (CPGs) and deep reinforcement learning (DRL). This approach allows for smooth transitions between walking and running, adaptation to unstable surfaces, and generation of movements in the absence of motion data. The breakthrough was published in the journal IEEE Robotics and Automation Letters on April 15, 2024.
Walking and running involve biological redundancies that enable adjustments to the environment and speed. Reproducing these movements in robots is challenging due to the complexity and unknown environments. Traditional models struggle with unknown environments, leading to inefficiency. Deep reinforcement learning and imitation learning have been used to address these challenges.
By combining imitation learning with CPG-like controllers and reflex neural networks, researchers achieved remarkable adaptability and stability in motion generation. The adaptive imitated CPG (AI-CPG) method imitates human motion effectively. This breakthrough represents a significant advancement in generative AI technologies for robot control.
The research group included members from Tohoku University and the Swiss Federal Institute of Technology in Lausanne. The study was published in IEEE Robotics and Automation Letters. This new approach has the potential for various applications across industries.
Source link
Source link: https://techxplore.com/news/2024-05-approach-generative-ai-imitate-human.amp
GIPHY App Key not set. Please check settings