HyperDrone: Simulation-to-Reality Transfer at Millions of Frames per Second
Abstract
HyperDrone is a GPU-accelerated quadrotor simulator using a ray-tracing engine to render high-fidelity observations at high speed, enabling vision-based policy training and real-world transfer.
We present HyperDrone, an extremely fast quadrotor simulator focused on high-performance batch rendering that is more than 20x faster than existing state-of-the-art batch quadrotor simulators. HyperDrone combines highly optimized multirotor dynamics with HyperLux, a new ray-tracing engine that supports Nvidia OptiX, Vulkan, Apple Metal and WebGPU backends that takes full advantage of modern ray-tracing hardware, capable of running both components entirely on the GPU. HyperLux renders RGB, depth, semantic/instance segmentation, surface normals and optical flow observations at configurable levels of fidelity, including reflections, realistic lighting, motion blur, anti-aliasing, and Physically Based Rendering (PBR). Even in the highest-fidelity settings, HyperLux achieves millions of Frames Per Second (FPS) on consumer-grade GPUs while rendering realistic 3D scenes. We demonstrate the merits of HyperDrone by training a vision-based yaw-control policy purely in simulation and transferring it to a real small-scale quadrotor (Crazyflie) with a camera, running completely onboard.
Community
๐ HyperDrone: Drone simulator at >10M FPS
โก๏ธ HyperLux: Massively parallel ray tracing for RL
๐ Any GPU: Nvidia, Apple Metal, Vulkan, WebGPU
๐ฆพ Sim2Real transfer of an RGB policy
โ
Accepted at CoRL 2026
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- PhyVisGen: Physically and Visually High-Fidelity Robotic Manipulation Data Generation (2026)
- Cross-Platform Benchmark of Neural 3D Reconstruction for Autonomous Laboratory Robots (2026)
- CRESSim-Neo: A Batched GPU Simulation Engine for Surgical Robotics and Robot Learning (2026)
- A Hybrid and Hierarchical Ray Tracing Method for Efficient 3D Gaussian Rendering (2026)
- DEXTERA: From a Single Image to Deployable Dexterous Manipulation via Real-to-Sim-to-Real (2026)
- Demonstration Synthesis from a Single Scan via Gaussian Splatting for Visuomotor Policy Learning (2026)
- Function-Preserving Data Generation for Zero-Shot Real-to-Sim-to-Real Manipulation (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2610.28950 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper