Fully Autonomous WheeL Loaders for efficient HAndling of Heterogeneous Materials

The aim of the ALL-4-eHAM project is to develop a generic, modularized system for autonomous wheel loaders that carries out all parts of the material handling cycle in the context of an asphalt production site.

Apart from the difficulties that arise from the need to perceive and navigate in a dynamic, unstructured outdoor environment, the main challenge represented in this scenario lies in the loading aspect. The task of the wheel loaders is to load heterogeneous materials from piles continuously heaped up by human operators and to transport the material to and unload it into pockets at a defined place. The shape of the piles is of course not known in advance and changes continuously. The materials differ substantially in their properties and accordingly the way they have to be handled. Given the material properties, the optimal loading procedure has to be determined from a simulation of the material behavior and the current state of the pile, following a complex set of rules.

In order to achieve a system that is economically superior to current solutions based on human operators, the whole material handling cycle, and in particular the loading/unloading procedure needs to be optimized in terms of speed and energy efficiency. The goal of the project is to develop a demonstrator system, which carries out the material handling cycle at 70% the productivity of a skilled human driver and 70% of the fuel efficiency, measured as the mass of the moved material relative to the consumed energy (ton/liter fuel). At the end of the project, one autonomous wheel loader will be demonstrated, running for one hour continuously at an NCC asphalt mill. Due to its generic and highly ambitious goal, the solutions developed in the project will be applicable to the wide class of scenarios where grained materials have to be handled.

The project is a collaborative effort between the AASS Learning Systems Lab at Örebro University, NCC and Volvo CE.

This project is co-sponsored by the KK-foundation.