HEAP: Human-Guided Learning and Benchmarking of Robotic Heap Sorting

Robotic heap sorting is of interest for many applications, such as nuclear decommissioning, recycling and manufacturing. Our team investigates novel robot manipulation and machine learning algorithms that can learn from human guidance and shared control. 

HEAP project is a European consortium that investigates robotic sorting of unstructured heaps of unknown objects.

The consortium consists of the University of Nottingham (coordinator), TU Wien (Markus Vinze), IDIAP in Switzerland (Jean-Marc Odobez), INRIA Nancy (Serena Ivaldi) and IIT in Italy (Lorenzo Natale).

The consortium aims at building an end-to-end benchmarking framework, which includes rigorous scientific methodology and experimental tools for application in realistic scenarios. Benchmark scenarios are being developed with off-the-shelf manipulators and grippers, allowing to create an affordable setup that can be easily reproduced both physically and in simulation.