Visual-Based Forklift Learning System Enabling Zero-Shot Sim2Real Without Real-World Data

TL;DR

This paper introduces a vision-based deep reinforcement learning system for forklift automation that trains entirely in a photorealistic digital environment, enabling successful real-world pallet loading without real-world training data.

Contribution

It presents a novel zero-shot sim2real approach for forklift automation using digital training environments created from CAD data, eliminating the need for real-world data collection.

Findings

Achieved 60% success rate in real-world pallet loading tasks

Demonstrated zero-shot transfer from simulation to real-world without heuristics

Validated approach on a 1/14-scale robotic forklift

Abstract

Forklifts are used extensively in various industrial settings and are in high demand for automation. In particular, counterbalance forklifts are highly versatile and employed in diverse scenarios. However, efforts to automate these processes are lacking, primarily owing to the absence of a safe and performance-verifiable development environment. This study proposes a learning system that combines a photorealistic digital learning environment with a 1/14-scale robotic forklift environment to address this challenge. Inspired by the training-based learning approach adopted by forklift operators, we employ an end-to-end vision-based deep reinforcement learning approach. The learning is conducted in a digitalized environment created from CAD data, making it safe and eliminating the need for real-world data. In addition, we safely validate the method in a physical setting utilizing a 1/14-scale robotic forklift with a configuration similar to that of a real forklift. We achieved a 60% success rate in pallet loading tasks in real experiments using a robotic forklift. Our approach demonstrates zero-shot sim2real with a simple method that does not require heuristic additions. This learning-based approach is considered a first step towards the automation of counterbalance forklifts.