N環球 N GLOBE
Global Technology

Otto Group and Sereact bring NVIDIA-powered physical AI robots to e-commerce returns

· N GLOBE

Otto Group and Sereact will deploy AI-controlled dual-arm systems to inspect and sort returned orders, starting with ten systems at a logistics centre in Poland and scaling to 25.

German retail group Otto Group and robotics software company Sereact announced on October 28 a two-phase rollout of AI-controlled robots for one of e-commerce's hardest manual tasks: inspecting and sorting returned customer orders.

A two-phase rollout

Ten AI-controlled dual-arm systems will first be deployed at Otto Group's logistics centre in Poland. A second phase would add 15 more robotic arms based on initial results, bringing the total to 25. The two companies are jointly developing and refining the technology, and Otto Group will evaluate a broader rollout across its logistics network if the second phase succeeds.

Why returns resist automation

Returned items arrive folded, crumpled and repackaged, and a multi-category retailer's assortment never stops changing. Traditional automation depends on known products and predictable presentation; returns offer neither. Sereact's physical AI model, Cortex, is built for exactly this challenge: it generalizes to objects it has never seen and decides in real time how to grasp each item, assess its condition and route it.

The NVIDIA stack behind it

Cortex is built on NVIDIA's physical AI stack. Sereact uses NVIDIA Isaac Sim and NVIDIA Isaac Lab to turn real picks from the returns line into thousands of simulated variants, and NVIDIA Cosmos world foundation models to re-render them across garment states, packaging, materials and lighting. New policies are post-trained on NVIDIA Blackwell GPUs and tested against held-out cases before reaching the robots. When a robot struggles with an item, a tested fix can return within days rather than weeks.

Robots as a service

Under a Robotics-as-a-Service model, Sereact operates and maintains the systems. Employees hand over repetitive grasping and lifting and take on supervision, exception handling and quality checks. Source: GlobeNewswire press release, October 28, 2026.

💬 Comments

No comments yet. Be the first!