Event
Tendon-driven jellyfish robot achieves reinforcement-learning-based deep closed-loop control
1 reports · 1 sources
Jiarui Peng et al. proposed a tendon-driven biomimetic jellyfish robot and developed a reinforcement-learning-based closed-loop depth regulation controller, which achieved closed-loop depth regulation in both simulation and real-machine experiments. Each actuator of the robot combines a flexible substrate with discrete constraints, enabling 150° bending, with tendon displacement and bending angle approximately linear; the 8 actuators are driven by 4 servos, enabling stable swimming, posture adjustment, and self-recovery.
Report timeline
- Reinforcement Learning-Based Tendon-Driven Bionic Jellyfish Robot Achieves Closed-Loop Depth Control
A tendon-driven bionic jellyfish robot achieves 150° bending through soft actuators that combine a flexible substrate with discrete constraints, with tendon displacement and bending angle approximately linear. Eight actuators driven by four servos enable stable swimming, attitude adjustment, and self-righting. A reinforcement learning controller trained on this linear actuation characteristic achieved closed-loop depth regulation in both simulation and physical experiments.
arXiv cs.RO ·