Cesium Tiles for High-realism Simulation and Comparing SLAM Results in Corresponding Virtual and Real-world Environments

TL;DR

This work demonstrates that Cesium Tiles-derived digital twins, integrated with the AirSim simulator and Unreal Engine, can closely predict real-world SLAM results by reproducing a real flight at a fixed location and comparing against a simulated counterpart. By extracting large-scale voxel models from Cesium Tiles and aligning point clouds via ICP, the study shows that mean alignment errors are similar between real and simulated data ($ ext{mean} ightarrow$ approximately $0.55$–$0.57$ m) with comparable spread, while simulated data yield denser point clouds. The methodology combines cine-camera-driven tile caching, voxel-grid geometry extraction, and ICP-based evaluation to enable robust, scalable, and repeatable SLAM assessments in virtual replicas of real environments. The findings suggest that digital twins based on Cesium Tiles can serve as effective proxies for real-world testing, facilitating environment-specific robotics development and performance optimization before field deployment.

Abstract

This article discusses the use of a simulated environment to predict algorithm results in the real world. Simulators are crucial in allowing researchers to test algorithms, sensor integration, and navigation systems without deploying expensive hardware. This article examines how the AirSim simulator, Unreal Engine, and Cesium plugin can be used to generate simulated digital twin models of real-world locations. Several technical challenges in completing the analysis are discussed and the technical solutions are detailed in this article. Work investigates how to assess mapping results for a real-life experiment using Cesium Tiles provided by digital twins of the experimental location. This is accompanied by a description of a process for duplicating real-world flights in simulation. The performance of these methods is evaluated by analyzing real-life and experimental image telemetry with the Direct Sparse Odometry (DSO) mapping algorithm. Results indicate that Cesium Tiles environments can provide highly accurate models of ground truth geometry after careful alignment. Further, results from real-life and simulated telemetry analysis indicate that the virtual simulation results accurately predict real-life results. Findings indicate that the algorithm results in real life and in the simulated duplicate exhibited a high degree of similarity. This indicates that the use of Cesium Tiles environments as a virtual digital twin for real-life experiments will provide representative results for such algorithms. The impact of this can be significant, potentially allowing expansive virtual testing of robotic systems at specific deployment locations to develop solutions that are tailored to the environment and potentially outperforming solutions meant to work in completely generic environments.

Figures (11)

• Figure 1: (a,b) show images collected in real-life and simulated aerial experiments over the UNC Charlotte football stadium. This article proposes techniques that use Google's realistic 3D models in UAS 3D mapping and SLAM research.
• Figure 2: (a,b) show how differences in the cine-camera viewpoint and the viewpoints onboard perception sensors can generate incorrect image data. (a) shows a payload camera view distinct from the cine-camera; the black region on the horizon is due to a missing tile of model data. (b) uses our proposed method to tailor the cine-camera position and shows the missing geometry correctly rendered.
• Figure 3: An example of converting a geometric model to a voxel model using AirSim's simCreateVoxelGrid() function.
• Figure 4: An example of using ICP algorithm to align two point clouds Zodage-2021-129203. Red: source point cloud. Blue: target point cloud. Purple: registration result.
• Figure 5: (a) Cinebot 30 drone with DJI O3 camera. (b) Image of the drone operator during a flight test.