AgiBot A2-W is the wheeled variant of the A2 humanoid, using wheels instead of legs for energy-efficient navigation. It features an articulated torso and arms for natural interaction with tools and workstations, advanced perception sensors for mapping and obstacle detection, and processes visual and spatial data in real time. Designed for indoor service environments where smooth locomotion is preferred over bipedal walking.
Primary use case: Indoor service tasks, reception, and interaction in commercial environments; wheeled alternative to bipedal A2 for smoother and more energy-efficient navigation
Height
163 cm
Weight
230 kg
DOF
22
Battery
5 hrs
Height
163 cm
Weight
230 kg
Degrees of Freedom
22
Locomotion
wheeled
Max Lift/Arm
5 kg
Battery Life
5 hrs
Charging Time
2 hrs
Availability
commercial
Primary Use Case
Indoor service tasks, reception, and interaction in commercial environments; wheeled alternative to bipedal A2 for smoother and more energy-efficient navigation
IDC data shows AGIBOT led global humanoid robot shipments in H1 2026, shipping more than 8,600 units—approximately 35% of global shipments of nearly 25,000 units (up 432.1% YoY). The article highlights AGIBOT's milestone of 20,000 cumulative robots produced by September 2026, along with large-scale deployments at Chimelong Spaceship Park (300+ robots) and ASD retail stores (100 AGIBOT X2 units).
AGIBOT has partnered with ASD (SZSE: 002403), a leading Chinese cookware and kitchenware company, to deploy 100 AGIBOT X2 humanoid robots across 100 ASD retail stores in China. The robots serve as in-store sales assistants, handling customer greetings, needs assessment, product recommendations, and handing off promotions and transactions to human staff. A three-day livestream from September 28-30, 2026 showcases the robots operating for 10 consecutive hours daily in stores in Wenling, Shanghai, and Wuxi.
AGIBOT demonstrated its WITA-Omni embodied-native omni-modal model at the Greater Bay Area Film Concert, where robots interacted face-to-face with a celebrity in real-time by identifying speakers, coordinating speech, movement, and expressions dynamically rather than following scripted sequences. The model uses a Thinker-Talker-Actor architecture that aligns speech and physical behavior along the same timeline, achieving top benchmark performance on the DailyOmni evaluation.