Optimizing wheel loader performance -- an end-to-end approach

TL;DR

This paper presents an end-to-end optimization approach for wheel loader operations that uses deep neural network world models and look-ahead tree search to improve efficiency over traditional strategies.

Contribution

It introduces a novel integrated planning method combining deep learning and look-ahead search for wheel loader task optimization.

Findings

6% efficiency improvement over greedy strategy

14% efficiency improvement over fixed controller

Effective prediction of pile state evolution

Abstract

Wheel loaders in mines and construction sites repeatedly load soil from a pile to load receivers. Automating this task presents a challenging planning problem since each loading's performance depends on the pile state, which depends on previous loadings. We investigate an end-to-end optimization approach considering future loading outcomes and transportation costs between the pile and load receivers. To predict the evolution of the pile state and the loading performance, we use world models that leverage deep neural networks trained on numerous simulated loading cycles. A look-ahead tree search optimizes the sequence of loading actions by evaluating the performance of thousands of action candidates, which expand into subsequent action candidates under the predicted pile states recursively. Test results demonstrate that, over a horizon of 15 sequential loadings, the look-ahead tree search is 6% more efficient than a greedy strategy, which always selects the action that maximizes the current single loading performance, and 14% more efficient than using a fixed loading controller optimized for the nominal case.