High-Fidelity Integrated Aerial Platform Simulation for Control, Perception, and Learning

摘要

This paper presents a simulator framework tailored Integrated Aerial Platforms (IAPs) using multiple quadrotors. Our framework prioritizes photo and contact fidelity, achieved through a modular design that balances rendering and dynamics computation. Key features include: i) support for diverse IAP configurations; ii) a customizable physics engine for realistic motion and contact simulation for aerial manipulation; and iii) Unreal Engine 5 for lifelike rendering, with sensor designs for visual-inertial SLAM positioning simulation. We showcase our framework’s versatility through a range of scenarios, including trajectory tracking for both fully and under-actuated IAPs, peg-in-hole and direct wrench control tasks under external wrench influence, tightly-coupled SLAM positioning with physical constraints, and air docking task training and testing using offline-to-online reinforcement learning. Furthermore, we validate our simulator framework’s fidelity by comparing results with real flight data for trajectory tracking and direct wrench control tasks. Our simulator framework promises to be valuable for developing and testing integrated aerial platform systems for aerial manipulation. Note to Practitioners—Motivated by the demand for effective simulation tools for Integrated Aerial Platforms (IAPs), this research addresses a significant gap in the availability of comprehensive simulation platforms designed to meet their unique challenges. This paper presents a high-fidelity simulation platform tailored specifically for IAPs, supporting a variety of configurations and capabilities. The platform not only generates high-fidelity image data and facilitates contact simulation but also serves as a vital resource for advancing perception, control, and learning for IAPs. By offering a robust simulation environment, this work aims to bridge the divide between theoretical research and practical applications, ultimately driving advancements in the field of aerial robotics.