# CAD2RL: Real Single-Image Flight without a Single Real Image

arXiv: https://arxiv.org/abs/1611.04201 · HTML: https://mlsanity.com/paper/1611.04201/

## Key facts

- Cited by 233 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2016.

## Built on by (most cited first, 30 of 233)

- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning](https://mlsanity.com/paper/2108.06266/) (2021)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned](https://mlsanity.com/paper/2102.02915/) (2021)
- [Real-World Humanoid Locomotion with Reinforcement Learning](https://mlsanity.com/paper/2303.03381/) (2023)
- [Maximum Entropy RL (Provably) Solves Some Robust RL Problems](https://mlsanity.com/paper/2103.06257/) (2021)
- [Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes](https://mlsanity.com/paper/2408.03539/) (2024)
- [Evolving Curricula with Regret-Based Environment Design](https://mlsanity.com/paper/2203.01302/) (2022)
- [A Survey of Zero-shot Generalisation in Deep Reinforcement Learning](https://mlsanity.com/paper/2111.09794/) (2021)
- [Agent AI: Surveying the Horizons of Multimodal Interaction](https://mlsanity.com/paper/2401.03568/) (2024)
- [FSDR: Frequency Space Domain Randomization for Domain Generalization](https://mlsanity.com/paper/2103.02370/) (2021)
- [Learning High-Speed Flight in the Wild](https://mlsanity.com/paper/2110.05113/) (2021)
- [Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots](https://mlsanity.com/paper/2103.14295/) (2021)
- [Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability](https://mlsanity.com/paper/2107.06277/) (2021)
- [The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixels](https://mlsanity.com/paper/2101.02722/) (2021)
- [State-Only Imitation Learning for Dexterous Manipulation](https://mlsanity.com/paper/2004.04650/) (2020)
- [NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation](https://mlsanity.com/paper/2504.13055/) (2025)
- [Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation](https://mlsanity.com/paper/2105.14829/) (2021)
- [A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning](https://mlsanity.com/paper/2208.07860/) (2022)
- [Understanding Domain Randomization for Sim-to-real Transfer](https://mlsanity.com/paper/2110.03239/) (2021)
- [Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller](https://mlsanity.com/paper/1911.09676/) (2019)
- [Asymmetric self-play for automatic goal discovery in robotic manipulation](https://mlsanity.com/paper/2101.04882/) (2021)
- [Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes](https://mlsanity.com/paper/2110.06192/) (2021)
- [CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learning](https://mlsanity.com/paper/2212.05711/) (2022)
- [Vision-Language Navigation with Random Environmental Mixup](https://mlsanity.com/paper/2106.07876/) (2021)
- [Robot Learning from Randomized Simulations: A Review](https://mlsanity.com/paper/2111.00956/) (2021)
- [How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligence](https://mlsanity.com/paper/2305.01263/) (2023)
- [Holo-Dex: Teaching Dexterity with Immersive Mixed Reality](https://mlsanity.com/paper/2210.06463/) (2022)
- [VeLO: Training Versatile Learned Optimizers by Scaling Up](https://mlsanity.com/paper/2211.09760/) (2022)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)

## Abstract (arXiv)

Deep reinforcement learning has emerged as a promising and powerful technique for automatically acquiring control policies that can process raw sensory inputs, such as images, and perform complex behaviors. However, extending deep RL to real-world robotic tasks has proven challenging, particularly in safety-critical domains such as autonomous flight, where a trial-and-error learning process is often impractical. In this paper, we explore the following question: can we train vision-based navigation policies entirely in simulation, and then transfer them into the real world to achieve real-world flight without a single real training image? We propose a learning method that we call CAD2RL, which can be used to perform collision-free indoor flight in the real world while being trained entirely on 3D CAD models. Our method uses single RGB images from a monocular camera, without needing to explicitly reconstruct the 3D geometry of the environment or perform explicit motion planning. Our learned collision avoidance policy is represented by a deep convolutional neural network that directly processes raw monocular images and outputs velocity commands. This policy is trained entirely on simulated images, with a Monte Carlo policy evaluation algorithm that directly optimizes the network's ability to produce collision-free flight. By highly randomizing the rendering settings for our simulated training set, we show that we can train a policy that generalizes to the real world, without requiring the simulator to be particularly realistic or high-fidelity. We evaluate our method by flying a real quadrotor through indoor environments, and further evaluate the design choices in our simulator through a series of ablation studies on depth prediction. For supplementary video see: https://youtu.be/nXBWmzFrj5s