In a livestream on X and YouTube, the company's embodied AI model and self-developed High-Performance 6-Axis Robot Arm autonomously identified, picked, reoriented, and fed highly variable parcels into a live sorting workflow, achieving 1,816 parcels per hour with over 98% accuracy.

SHENZHEN, China, Aug. 13, 2026 /PRNewswire/ -- X Square Robot, an embodied AI company building general-purpose robots and foundation models for real-world environments, has demonstrated a system that automates one of the hardest front-end jobs in logistics: moving parcels from the messy piles left by truck unloading onto the sorting line. In a livestream on X and YouTube on August 12, the company's proprietary WALL-B AI foundation model worked with its self-developed High-Performance 6-Axis Robot Arm to identify, pick, organize, and feed parcels one by one onto a conveyor for scanning and automated sorting.

Parcel induction is a highly labor-intensive "3D" task — dull, dirty, and dangerous, with operators facing high labor demand, turnover, and challenges in staffing night shifts and seasonal peaks. As labor costs rise, automation that can operate continuously offers a potential path to improving productivity and ROI.

This is the step where lab demos usually fall short. A parcel pile changes with every pick. Boxes and soft packages overlap, labels point the wrong way, and the best grasping surface is often buried. At the unloading dock, that messiness makes parcel induction a bottleneck for throughput and one of the most labor-intensive stages of sorting.

"The question in logistics automation is not whether a robot can make one clean pick," said Wang Qian, Founder and CEO of X Square Robot. "It is whether it keeps making good decisions as the pile changes, recovers when something goes wrong, and keeps the rest of the operation moving. We designed the automation around the work itself, not around an idealized environment."

At the core of this capability is X Square Robot's proprietary embodied AI foundation model, WALL-B. In the live demonstration, the model showed how this learned understanding translates into real-time action: assessing each parcel and its surroundings, determining how it should be handled, and adapting the manipulation strategy as conditions change. Rather than relying on manually programmed rules for every parcel type, WALL-B enables the robot to respond to unexpected situations in the physical world — as demonstrated when its 6-axis arm dynamically intervened to rescue a misrouted parcel.

Turning these decisions into physical action is the High-Performance 6-Axis Robot Arm. Its multi-angle range of motion allows the system to approach packages from different directions to pick, flip, flatten and reposition them. Before a parcel reaches the conveyor, the arm can turn labels toward the scanner, smooth soft packaging and square up boxes. These may seem like small adjustments, but they can improve barcode scanning and reduce the returns and manual handling caused by poorly positioned packages.

Rather than asking one robot to perform every task, X Square Robot takes a purpose-built approach, designing the system around the specific demands of parcel induction. The result is a focused combination of speed, accuracy, and cost, matching the hardware and AI to the workflow rather than forcing the workflow to fit the robot.

For X Square Robot, the demonstration is ultimately about more than moving parcels. It reflects the company's broader vision for embodied intelligence: making AI practical in the real world and enabling robots to perceive, reason, and act in complex physical environments.

About X Square Robot

X Square Robot develops general-purpose embodied intelligence robots with high-precision manipulation capabilities. The company is building foundation models for the physical world, integrating models, robotic hardware and scalable, model-driven high-quality data pipeline system. Its robots are designed to perceive, reason and act across long-horizon tasks in home and everyday environments, research and education, logistics and warehousing, and industrial operations.

For more information, visit https://x2robot.com/.