A Dutch company is a market-leading, global partner for future-proof logistic process automation in the warehousing, airports, and parcel sectors. Its extensive portfolio of integrated solutions – innovative systems, intelligent software, and life-cycle services – results in the realization of fast, reliable, and efficient automation technology. The company is a leading supplier of process automation solutions that address the challenges in the parcel market. More than 52 million parcels are sorted by its systems every day, which have been installed for the world’s leading parcel handling companies. Today the company faces many challenges, which they hope to solve with partners. For instance: The growth of e-commerce has resulted in a strong increase of parcel volumes. A large part of those packages that are shipped worldwide are transported in containers. Those containers are loaded manually, while one of the biggest challenges of parcel companies today is labor availability. The company believes that robotic solutions will play an important role to further automate the container loading process. This challenge addresses the 3D bin packing problem of parcel loading, which can be seen as a 3D Tetris game that the robot is playing to fill a container.

SMEs and academia are asked to develop a software component that outputs place poses for a set of parcels that must be loaded in a container. As input partners will receive the dimensions of the parcels and the container, and as output we expect apose for the parcel to be loaded. The company will provide a parameterizable Docker container running the simulation setup. This Docker container will be publicized for the contestants to set up, train and validate their robot controllers for the given tasks.

Participants should prepare a compiled Docker image of their robot controller, which interacts with the provided simulation container via ROS. The contributed robot controller will be evaluated before the conference by the organizers against novel test cases run in the simulation container. The motion planning and control of the robot arm are out of scope for this challenge.