1 Modular Parallel Manipulator for Long-Term Soft Robotic Data Collection

TL;DR

This paper introduces a modular, soft-robotic manipulation platform designed for long-term, large-scale data collection in soft robotics, enabling reinforcement learning directly on hardware with flexible, customizable modules.

Contribution

The work presents a novel modular soft robotic platform compatible with various fabrication methods, facilitating scalable data collection and direct hardware reinforcement learning.

Findings

Successfully validated hardware for policy gradient reinforcement learning

Demonstrated compatibility with multiple soft robotic fingers

Characterized design constraints for scalable extensions

Abstract

Performing long-term experimentation or large-scale data collection for machine learning in the field of soft robotics is challenging, due to the hardware robustness and experimental flexibility required. In this work, we propose a modular parallel robotic manipulation platform suitable for such large-scale data collection and compatible with various soft-robotic fabrication methods. Considering the computational and theoretical difficulty of replicating the high-fidelity, faster-than-real-time simulations that enable large-scale data collection in rigid robotic systems, a robust soft-robotic hardware platform becomes a high priority development task for the field. The platform's modules consist of a pair of off-the-shelf electrical motors which actuate a customizable finger consisting of a compliant parallel structure. The parallel mechanism of the finger can be as simple as a single 3D-printed urethane or molded silicone bulk structure, due to the motors being able to fully actuate a passive structure. This design flexibility allows experimentation with soft mechanism varied geometries, bulk properties and surface properties. Additionally, while the parallel mechanism does not require separate electronics or additional parts, these can be included, and it can be constructed using multi-functional soft materials to study compatible soft sensors and actuators in the learning process. In this work, we validate the platform's ability to be used for policy gradient reinforcement learning directly on hardware in a benchmark 2D manipulation task. We additionally demonstrate compatibility with multiple fingers and characterize the design constraints for compatible extensions.