Abstract
This research suggests a deep Q-network learning approach coupled with a layered neural-based locomotion. An analog signal is produced by central pattern generation (CPG) in the higher layers and sent to motor neuron pools in the lower levels. Motor neurons produce joint angular velocity in the lower levels. The neural oscillator model in the spinal cord serves as the foundation for the central pattern generation. It reacts to the pattern of the driving model. Then, using a human musculoskeletal model, the inner state of motor neurons was constructed based on muscle activation. Additionally, the motor neuron (MN) pool is linked to the sensory neuron (SN), which transmits internal feedback from the robot. A humanoid robot simulation using the proposed concept has been used to carry various loads. Adjustments to the robot's behavior to maintain its stance.
Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
