Towards Autonomous Grading In The Real World

TL;DR

This paper investigates autonomous grading with dozers, developing simulation and prototype environments, and demonstrates how learning agents can generalize from simulation to real-world scenarios.

Contribution

It introduces a realistic simulation and scaled prototype for autonomous dozer grading, and shows how learning agents can bridge the simulation-reality gap.

Findings

Heuristics work in simulation but fail in real scenarios.

Learning agents can generalize from simulation to real environments.

Simulation-guided learning improves real-world performance.

Abstract

In this work, we aim to tackle the problem of autonomous grading, where a dozer is required to flatten an uneven area. In addition, we explore methods for bridging the gap between a simulated environment and real scenarios. We design both a realistic physical simulation and a scaled real prototype environment mimicking the real dozer dynamics and sensory information. We establish heuristics and learning strategies in order to solve the problem. Through extensive experimentation, we show that although heuristics are capable of tackling the problem in a clean and noise-free simulated environment, they fail catastrophically when facing real world scenarios. As the heuristics are capable of successfully solving the task in the simulated environment, we show they can be leveraged to guide a learning agent which can generalize and solve the task both in simulation and in a scaled prototype environment.