China Merchants Lab Unveils LiOS Infrastructure for Robotic Cloth Folding
量子位 · wechat · 2026-08-20
China Merchants Lion Mountain AI Lab showcased a flexible cloth folding solution powered by its self-developed LiOS end-cloud collaborative infrastructure at the 2026 World Robot Conference. The technology addresses the sim-to-real gap via a closed-loop data iteration system covering training, deployment, and Real2Sim teleoperation, boosting training throughput by 5x and evaluation efficiency by 4x.
The lab previously won the ICRA 2026 LeHome Challenge using its proprietary VLA model. The on-site demonstration featured three core capabilities: multi-platform folding, autonomous identification and folding of different garment types, and large-deformation handling. The LiOS architecture comprises a cloud side (supporting 10B+ parameter models), an edge side (real-time execution), and end-cloud collaboration (low-latency video transmission), effectively integrating cloud computing with physical robots.
More from Embodied
- MIT's C-GMT gives humanoid robots whole-body compliance without sacrificing motion tracking — MIT_CSAIL · 2026-10-16
- OpenRoboto, Bittensor's largest robotics subnet, puts its data collectors on Solana via peaqOS — bittingthembits · 2026-10-16
- Robotics data tokenization landscape: Khala maps peaq, THOR, BitRobot and Axis — 0xSammy · 2026-10-16
- Perseverance rover logs 28.1 miles on Mars, breaking Opportunity's record in half the time — BrettKrieger12 · 2026-10-16
- Trossen bimanual arms portion food in commercial kitchen with models fine-tuned via Physical Intelligence API — kscottz · 2026-10-16
- Safeworld emerges from stealth with $12M to build 'CI/CD for robots' safety testing — lukas_m_ziegler · 2026-10-16