Reinforcement Learning to improve delta robot throws for sorting scrap metal

TL;DR

This paper introduces a reinforcement learning approach to improve the efficiency of scrap metal sorting with delta robots by learning optimal throw positions and speeds, achieving significant speedups and accuracy in simulation and real-world transfer.

Contribution

It presents a new simulation environment for RL-based pick-and-throw strategies and demonstrates their effectiveness in improving sorting speed and accuracy over traditional methods.

Findings

89% accuracy in simulation

51% increase in throughput

Successful transfer of policies to real robots without fine-tuning

Abstract

This study proposes a novel approach based on reinforcement learning (RL) to enhance the sorting efficiency of scrap metal using delta robots and a Pick-and-Place (PaP) process, widely used in the industry. We use three classical model-free RL algorithms (TD3, SAC and PPO) to reduce the time to sort metal scraps. We learn the release position and speed needed to throw an object in a bin instead of moving to the exact bin location, as with the classical PaP technique. Our contribution is threefold. First, we provide a new simulation environment for learning RL-based Pick-and-Throw (PaT) strategies for parallel grippers. Second, we use RL algorithms for learning this task in this environment resulting in 89% accuracy while speeding up the throughput by 51% in simulation. Third, we evaluate the performances of RL algorithms and compare them to a PaP and a state-of-the-art PaT method both in simulation and reality, learning only from simulation with domain randomisation and without fine tuning in reality to transfer our policies. This work shows the benefits of RL-based PaT compared to PaP or classical optimization PaT techniques used in the industry.