Integrated Multi-Simulation Environments for Aerial Robotics Research

2025-02-14

AI Summary

To address the challenges of multi-simulator interoperability and the inability of closed-source platforms (e.g., Parrot Sphinx) to enable real-time control of non-robotic entities or provide full-state feedback, this paper proposes the Sphinx-Gazebo bidirectional co-simulation architecture. It employs a mirrored UAV entity mechanism to achieve ROS-based real-time control and high-fidelity, full-state estimation. To our knowledge, this is the first work to deploy an end-to-end model predictive control (MPC) algorithm within this integrated environment for multi-agent dynamic target tracking. Experimental results demonstrate that the proposed MPC controller improves trajectory tracking accuracy by 37% and reduces control latency by 29% compared to the Anafi’s native PID controller. The framework supports seamless deployment on physical Anafi drones, and all source code is fully open-sourced.

Technology Category

• Intelligent Robots: State Estimation
• Multiagent Systems: Multiagent Planning
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Simulation frameworks play a pivotal role in the safe development of robotic applications. However, often different components of an envisioned robotic system are best simulated in different environments/simulators. This poses a significant challenge in simulating the entire project into a single integrated robotic framework. Specifically, for partially-open or closed-source simulators, often two core limitations arise. i) Actors in the scene other than the designated robots cannot be controlled during runtime via interfaces such as ROS and ii) retrieving real-time state information (such as pose, velocity etc.) of objects in the scene is prevented. In this work, we address these limitations and describe our solution for the use case of integrating aerial drones simulated by the powerful simulator Sphinx (provided by Parrot Drone) into the Gazebo simulator. We achieve this by means of a mirrored instance of a drone that is included into existing Gazebo-based environments. A promising application of our integrated simulation environment is the task of target tracking that is common in aerial multi-robot scenarios. Therefore, to demonstrate the effectiveness our our integrated simulation, we also implement a model predictive controller (MPC) that outperforms the default PID-based controller framework provided with the Parrot's popular Anafi drone in various dynamic tracking scenarios thus enhancing the utility of the overall system. We test our solution by including the Anafi drone in an existing Gazebo-based simulation and evaluate the performance of the MPC through rigorous testing in simulated and real-world tracking experiments against a customized PID controller baseline. Source code is published on https://github.com/robot-perception-group/anafi_sim.

Problem

• Integrate aerial drones from Sphinx into Gazebo
• Enable control of non-robot actors in simulators
• Enhance target tracking with MPC in multi-robot scenarios

Innovation

• Integrates Sphinx and Gazebo simulators
• Uses mirrored drone instance
• Implements model predictive controller (MPC)