AGIBOT G2 Robots Complete 1,730 Tasks in 24-Hour Shanghai Store Trial
Four of the six AGIBOT G2 robots passed a performance assessment after a 24-hour trial in a working convenience store.
The test evaluated customer service, retail operations and embodied AI capabilities in a live retail setting.
Six AGIBOT G2 wheeled humanoid robots completed a 24-hour trial at an operating convenience store in Shanghai’s Xuhui District.
The robots performed a combined 1,730 tasks, including customer assistance, coffee preparation, shelf restocking and cleaning.
The trial ran from 10 a.m. on November 2 to 10 a.m. on November 3 and was livestreamed to more than two million viewers across online platforms.
Four of the six robots passed the final performance assessment.
The event concluded AGIBOT’s AI WAVE technology showcase, launched on October 22.
After releases spanning robotics data, simulation, AI models, hardware and operational software, the store trial brought these technologies together in a real-world setting.
It examined how robots perform everyday tasks over an extended operating period and whether embodied AI can move beyond controlled demonstrations into a live, customer-facing environment.
Six Robots Take on Everyday Store Operations
The six G2 robots were assigned distinct roles: customer assistance, shelf inspections, restocking, coffee preparation, checkout and hot food service, and store cleaning. Over 24 hours, they completed 683 customer-service interactions, 369 product pickups and deliveries, 147 coffee orders, 126 breakfast servings, 277 shelf inspections and restocking tasks, and 128 table-cleaning tasks.
The trial covered lunchtime rush, evening peak hours, overnight operations and the next morning’s breakfast rush. Robots were assessed on duty time, task completion, customer feedback, response times and handling of unexpected situations; four passed and two did not meet all criteria.
Two evaluators also ran practical tests: ordering regular and sugar-free Coca-Cola to check product distinction, rearranging chewing gum packs for robots to restore, and blocking an aisle with a person and a box to test obstacle detection and navigation.