Examining the simulation-to-reality gap of a wheel loader digging in deformable terrain

TL;DR

This study evaluates how accurately physics-based simulations can replicate real wheel loader operations in deformable terrain, focusing on the simulation-to-reality gap and control transfer robustness.

Contribution

It provides a detailed analysis of the simulation-to-reality gap for wheel loaders in deformable terrain and assesses control transfer effects across simulation fidelities.

Findings

Simulation-to-reality gap is around 10%, weakly dependent on fidelity.

Real-time capable simulations are feasible with acceptable accuracy.

Control performance drops by about 5% when transferring across simulation domains.

Abstract

We investigate how well a physics-based simulator can replicate a real wheel loader performing bucket filling in a pile of soil. The comparison is made using field test time series of the vehicle motion and actuation forces, loaded mass, and total work. The vehicle was modeled as a rigid multibody system with frictional contacts, driveline, and linear actuators. For the soil, we tested discrete element models of different resolutions, with and without multiscale acceleration. The spatio-temporal resolution ranged between 50-400 mm and 2-500 ms, and the computational speed was between 1/10,000 to 5 times faster than real-time. The simulation-to-reality gap was found to be around 10% and exhibited a weak dependence on the level of fidelity, e.g., compatible with real-time simulation. Furthermore, the sensitivity of an optimized force feedback controller under transfer between different simulation domains was investigated. The domain bias was observed to cause a performance reduction of 5% despite the domain gap being about 15%.