ACE Robotics 用 Mundo 世界模型让机器人完成酒店洗衣全流程
ACE Robotics Pairs Mundo World Model With Self-Improving Skills to Run a Hotel Laundry Workflow
ACE Robotics 把 Mundo 世界模型和机上技能拼成了一套酒店洗衣机器人，失败案例能反哺技能改进，单轮 18.6 秒。想看世界模型怎么在真实场景落地的，这篇比纯实验室 demo 有参考价值，做具身智能的可以细看。
ACE Robotics 展示了一套酒店洗衣工作流方案，由 Mundo 世界模型负责任务规划，云端规划器与机载技能模块配合执行，机器人可以端到端完成分拣、处理等洗衣环节。
技术架构上采用"双脑"设计：世界模型在云端做长程任务规划，机器本体上的技能模块负责具体动作执行。官方称技能通过真实失败案例持续自我改进（RSI），单轮完整流程耗时压缩到 18.6 秒。
洗衣场景是典型的非结构化柔性物料处理，布料抓取一直是机器人落地的难点，这类方案如果可靠，可推广到酒店、医院等布草量大、人力成本高的行业，也是世界模型+技能学习路线的一次实际验证。
ACE Robotics Pairs Mundo World Model With Self-Improving Skills to Run a Hotel Laundry Workflow
ACE Robotics uses its Mundo world model, a cloud planner and on-robot skills to run hotel laundry end to end. Skills improve from real failures, it says, cutting a full run to 18.6 seconds.
This report is categorized under AITOP's "Products" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include ACE Robotics, Mundo, 世界模型, 具身智能.
Primary source verification: published directly by Pandaily with first-party authority.
