Optimizing Autonomous Wheel Loader Performance—An End-to-End Approach
Open Access
- 12 July 2025
- journal article
- research article
- Published by MDPI AG in Automation
- Vol. 6 (3) , 31
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.Keywords
Funding Information
- Komatsu Ltd.
This publication has 28 references indexed in Scilit:
- Planning the trajectory of an autonomous wheel loader and tracking its trajectory via adaptive model predictive controlRobotics and Autonomous Systems, 2020
- Computational exploration of robotic rock loadingRobotics and Autonomous Systems, 2018
- Optimal control of wheel loader actuators in gravel applicationsAutomation in Construction, 2018
- Admittance Control for Robotic Loading: Design and Experiments with a 1‐Tonne Loader and a 14‐Tonne Load‐Haul‐Dump MachineJournal of Field Robotics, 2016
- Wheel loader operation—Optimal control compared to real drive experienceControl Engineering Practice, 2016
- Path planning, modeling and simulation of an autonomous articulated heavy construction machine performing a loading cycleApplied Mathematical Modelling, 2013
- Curvature continuous path generation for autonomous vehicle using B-spline curvesComputer-Aided Design, 2010
- An automated digging control for a wheel loaderRobotica, 2001
- The Development, Control and Operation of an Autonomous Robotic ExcavatorJournal of Intelligent & Robotic Systems, 1998
- The NURBS Book1997