Towards Autonomous Grading In The Real World
This addresses the problem of autonomous construction grading for robotics, but it is incremental as it builds on existing simulation-to-real methods.
The paper tackled autonomous grading with a dozer, showing that heuristics work in simulation but fail in real-world scenarios, and that using heuristics to guide a learning agent enables generalization to both simulation and a scaled prototype environment.
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.