# Augmenting Imitation Experience via Equivariant Representations

arXiv: https://arxiv.org/abs/2110.07668 · HTML: https://mlsanity.com/paper/2110.07668/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 43 references that are in the map.
- First posted on arXiv 14 Oct 2021.

## Builds on (most cited first, 30 of 31)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks](https://mlsanity.com/paper/2006.10503/) (2020)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [End-to-end Driving via Conditional Imitation Learning](https://mlsanity.com/paper/1710.02410/) (2017)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data](https://mlsanity.com/paper/1807.02547/) (2018)
- [Harmonic Networks: Deep Translation and Rotation Equivariance](https://mlsanity.com/paper/1612.04642/) (2016)
- [Gauge Equivariant Convolutional Networks and the Icosahedral CNN](https://mlsanity.com/paper/1902.04615/) (2019)
- [Understanding image representations by measuring their equivariance and equivalence](https://mlsanity.com/paper/1411.5908/) (2014)
- [Volumetric and Multi-View CNNs for Object Classification on 3D Data](https://mlsanity.com/paper/1604.03265/) (2016)
- [A General Theory of Equivariant CNNs on Homogeneous Spaces](https://mlsanity.com/paper/1811.02017/) (2018)
- [Learning Steerable Filters for Rotation Equivariant CNNs](https://mlsanity.com/paper/1711.07289/) (2017)
- [DART: Noise Injection for Robust Imitation Learning](https://mlsanity.com/paper/1703.09327/) (2017)
- [Adversarial AutoAugment](https://mlsanity.com/paper/1912.11188/) (2019)
- [A Kernel Theory of Modern Data Augmentation](https://mlsanity.com/paper/1803.06084/) (2018)
- [Learning to Compose Domain-Specific Transformations for Data Augmentation](https://mlsanity.com/paper/1709.01643/) (2017)
- [Automatic Data Augmentation for Generalization in Deep Reinforcement Learning](https://mlsanity.com/paper/2006.12862/) (2020)
- [Plannable Approximations to MDP Homomorphisms: Equivariance under Actions](https://mlsanity.com/paper/2002.11963/) (2020)
- [CubeNet: Equivariance to 3D Rotation and Translation](https://mlsanity.com/paper/1804.04458/) (2018)
- [Equivariant Multi-View Networks](https://mlsanity.com/paper/1904.00993/) (2019)
- [Learning image representations tied to ego-motion](https://mlsanity.com/paper/1505.02206/) (2015)
- [Quaternion Equivariant Capsule Networks for 3D Point Clouds](https://mlsanity.com/paper/1912.12098/) (2019)
- [Equivariant Hamiltonian Flows](https://mlsanity.com/paper/1909.13739/) (2019)
- [PVNet: A Joint Convolutional Network of Point Cloud and Multi-View for 3D Shape Recognition](https://mlsanity.com/paper/1808.07659/) (2018)
- [Equivariant Transformer Networks](https://mlsanity.com/paper/1901.11399/) (2019)
- [AirSim Drone Racing Lab](https://mlsanity.com/paper/2003.05654/) (2020)
- [Learning an Effective Equivariant 3D Descriptor Without Supervision](https://mlsanity.com/paper/1909.06887/) (2019)

## Built on by (most cited first, 1 of 1)

- [Tube-NeRF: Efficient Imitation Learning of Visuomotor Policies from MPC using Tube-Guided Data Augmentation and NeRFs](https://mlsanity.com/paper/2311.14153/) (2023)

## Abstract (arXiv)

The robustness of visual navigation policies trained through imitation often hinges on the augmentation of the training image-action pairs. Traditionally, this has been done by collecting data from multiple cameras, by using standard data augmentations from computer vision, such as adding random noise to each image, or by synthesizing training images. In this paper we show that there is another practical alternative for data augmentation for visual navigation based on extrapolating viewpoint embeddings and actions nearby the ones observed in the training data. Our method makes use of the geometry of the visual navigation problem in 2D and 3D and relies on policies that are functions of equivariant embeddings, as opposed to images. Given an image-action pair from a training navigation dataset, our neural network model predicts the latent representations of images at nearby viewpoints, using the equivariance property, and augments the dataset. We then train a policy on the augmented dataset. Our simulation results indicate that policies trained in this way exhibit reduced cross-track error, and require fewer interventions compared to policies trained using standard augmentation methods. We also show similar results in autonomous visual navigation by a real ground robot along a path of over 500m.