WALL-A is an end-to-end embodied AI foundation model developed by X Square Robot (Shenzhen, China), part of the Great Wall embodied foundation model series. It integrates autonomous perception, decision-making, and high-precision manipulation using a unified vision-language-action (VLA) architecture combined with world models that predict environmental states before execution. WALL-A powers X Square's wheeled humanoid robots including the Quanta X1 and Quanta X2, enabling tasks in homes, hotels, warehouses, and research facilities.
Primary use case: Research
Height
172 cm
Weight
95 kg
DOF
62
Height
172 cm
Weight
95 kg
Degrees of Freedom
62
Locomotion
Wheeled
Hand Type
unknown
Autonomy Level
fully_autonomous
AI Capabilities
vision, planning, manipulation, learning
Availability
unknown
Primary Use Case
Research
Chinese embodied AI startup X Square Robot just completed a live, uncut package sorting challenge. Relying on simple grippers instead of dexterous hands, the system shattered its throughput target, inevitably drawing comparisons to Figure AI.
ABSTRACT With the increasing demand for inspection, maintenance, and operation in vertical and complex-geometry environments, wall-climbing robots have become essential equipment for high-rise infrastructure maintenance, large-scale industrial inspection, and emergency response. The codesign of adsorption and locomotion is fundamental to ensuring reliable attachment, stable mobility, and robust environmental adaptability. This paper provides a comprehensive review of major adsorption mechanisms—negative pressure, magnetic adsorption, electrostatic adsorption, bioinspired dry adsor
A cleaning service in Shenzhen deploys WALL-A robots from X Square Robot in real homes as part of a partnership with 58 Home, where robots work alongside human cleaners. The robot uses an end-to-end Vision-Language-Action model to handle structured cleaning tasks while humans handle decision-making. This represents a practical deployment strategy rather than a laboratory demonstration, operating in actual apartments with pets, children's toys, and clutter.