Tendon-Driven Robotic Jellyfish Achieves RL-Based Closed-Loop Depth Control
ChongZzZhang · x · 2026-09-26
Researchers from Hong Kong Embodied AI Lab, CUHK and HKUST present JellyRobot, a tendon-driven soft robotic jellyfish. Each actuator combines a flexible substrate with discrete constraints, bending up to 150° with near-linear tendon displacement. Eight actuators driven by four servos enable stable swimming, attitude adjustment, and self-righting, while an RL controller achieves closed-loop depth regulation in both simulation and real hardware via sim-to-real transfer without policy fine-tuning. Paper on arXiv, code coming soon.
More from Embodied
- microagi x ElevenLabs: Voice is the most human interface for living with robots — animesh_garg · 2026-09-26
- Andy Matuschak builds Printer Friend: voice-to-paper thermal note device — andy_matuschak · 2026-09-26
- Tesla FSD approved in Belgium as 5th EU country; Tesla data claims ~9.6x lower non-highway crash risk — ElectricRaph · 2026-09-26
- Microsoft Surface execs on the Arm bet with Qualcomm and the AI PC future — BenBajarin · 2026-09-26
- PrismML runs a 2B vision model with 1-bit weights on 4GB smart glasses at 2x speed — lmoroney · 2026-09-26
- Musk lays out his 90%-likely AI future: personal robots and universal high income — XFreeze · 2026-09-26