Checklist IOAI 2025 Team Challenge · Task 1
Factory of the Future
As a team, program a Galbot humanoid robot to move around a warehouse, avoid obstacles, and quickly shift scattered items from tables onto shelves.
The task
Teams play robot engineers at a 'Factory of the Future' and write a program for Galbot, a wheeled humanoid robot. The job is to tidy a warehouse: move around, find unsorted items lying on tables and place them on shelves without bumping into obstacles on the floor, as quickly as possible.
The guide lists the robot's specifications (including two 7-degree-of-freedom arms with grippers, an omnidirectional wheeled base, a head depth camera and wrist depth cameras), its joint limits and its coordinate frames. Development uses Physics Simulator Edu, a MuJoCo-based simulator from Galbot, with example code for driving the base, moving the arms and grippers, and reading camera images.
According to IOAI's press release, all teams first worked in the simulated factory, and the top 10 teams then ran their code on real Galbot robots in a physically reconstructed factory.
Abridged by SOTA from the official materials. The official statement has the exact rules, and it wins wherever this summary differs.
At a glance
- You get
- Physics Simulator Edu (MuJoCo-based, installed from the
galbot-ioai/physics_sim_eduGitHub repo) with a Galbot G1 robot model, sensor access, and example pick-and-place and A* navigation scripts. - You submit
- A program that controls Galbot to carry out the warehouse-organising tasks.
- Format
- Team Challenge: simulation phase on 4 August 2025 (13:00-18:00), then a real-robot validation phase for the top 10 teams on 6 August 2025 (16:30-18:00)