ACE ROBOTICS today unveiled Kairos 3.1, its latest action-oriented world model, alongside Ambient Capture Engine 2.0 and three commercial solutions spanning instant retail, hospitality and outdoor service scenarios. The announcements were made at a forum organized during the 2026 World Artificial Intelligence Conference.
Kairos 3.1 is designed as a natively unified model integrating generative, physical and cognitive intelligence within a single architecture. Built on a hybrid Transformer architecture with a shared mixed-attention mechanism, it brings visual observations, language instructions, force and tactile signals, and policy trajectories into a unified latent space. This supports an "understand, reason, execute and reflect" loop, enabling robots to break down long-horizon tasks, simulate physical cause and effect, rank actions, execute strategies and evaluate outcomes.
At its core is ACE-BRAIN-0.5, which ACE ROBOTICS says achieved state-of-the-art results across 12 public evaluations covering spatial understanding, navigation, manipulation and task-progress assessment. For physical generation and reasoning, Kairos-HomeWorld supports whole-home scene generation built on 300,000 residential floor plans and 5,000 simulated home environments. The model can simulate multiple action trajectories in parallel and rank them based on predicted success and execution cost.
ACE ROBOTICS also introduced the "Information-Density Law" for embodied models, classifying data across five levels from L1 to L5. Ambient Capture Engine 2.0 is a human-centric system for capturing high-density physical-interaction data. It includes ACE Ego Kit, a lightweight wireless wearable with sensors offering sensitivity of 0.01 newtons and joint-angle error less than two degrees. The ACE Data Engine provides automated annotation for long-horizon tasks, incorporating ACE-ViDiHand, a generative 4D hand-motion-capture framework that led three public benchmarks.
Three commercial solutions were introduced: Xiaoman for instant retail paired with the W1 fulfillment robot, which has a robot-to-payload weight ratio under 2:1 and force-control precision within one newton; Xiaoxin for hotel-laundry operations handling collection, loading, unloading, washing, sorting and folding; and Xiaotu for autonomous outdoor operation using a "one brain, many bodies" architecture across multiple quadruped robot platforms.
ACE ROBOTICS also announced partnerships with the Caohejing Development Zone, PetroChina, Kuaikeda and SenseTime Shanhui, and launched the World Model Cloud Ecosystem initiative with Baidu AI Cloud, Alibaba Cloud, Huawei Cloud, Tencent Cloud and SenseCore AI Cloud. The company aims to connect high-density data, unified world models, robot platforms and commercial applications to support the transition of embodied AI to sustained real-world operations.
