Related papers: Augmenting Imitation Experience via Equivariant Re…

Recent advances in deep reinforcement learning require a large amount of training data and generally result in representations that are often over specialized to the target task. In this work, we present a methodology to study the…

A key challenge in complex visuomotor control is learning abstract representations that are effective for specifying goals, planning, and generalization. To this end, we introduce universal planning networks (UPN). UPNs embed differentiable…

In this work we propose a novel end-to-end imitation learning approach which combines natural language, vision, and motion information to produce an abstract representation of a task, which in turn is used to synthesize specific motion…

One of the key challenges in visual imitation learning is collecting large amounts of expert demonstrations for a given task. While methods for collecting human demonstrations are becoming easier with teleoperation methods and the use of…

Event-based cameras are dynamic vision sensors that provide asynchronous measurements of changes in per-pixel brightness at a microsecond level. This makes them significantly faster than conventional frame-based cameras, and an appealing…

Visual representations play a crucial role in developing generalist robotic policies. Previous vision encoders, typically pre-trained with single-image reconstruction or two-image contrastive learning, tend to capture static information,…

Representations are crucial for a robot to learn effective navigation policies. Recent work has shown that mid-level perceptual abstractions, such as depth estimates or 2D semantic segmentation, lead to more effective policies when provided…

Faithfully reconstructing 3D geometry and generating novel views of scenes are critical tasks in 3D computer vision. Despite the widespread use of image augmentations across computer vision applications, their potential remains…

We propose a self-supervised approach for learning representations and robotic behaviors entirely from unlabeled videos recorded from multiple viewpoints, and study how this representation can be used in two robotic imitation settings:…

Data augmentation is an essential technique for improving recognition accuracy in object recognition using deep learning. Methods that generate mixed data from multiple data sets, such as mixup, can acquire new diversity that is not…

Data augmentation methods have played an important role in the recent advance of deep learning models, and have become an indispensable component of state-of-the-art models in semi-supervised, self-supervised, and supervised training for…

Robust reinforcement learning agents using high-dimensional observations must be able to identify relevant state features amidst many exogeneous distractors. A representation that captures controllability identifies these state elements by…

Data augmentation has proved extremely useful by increasing training data variance to alleviate overfitting and improve deep neural networks' generalization performance. In medical image analysis, a well-designed augmentation policy usually…

Recent work has shown that data augmentation has the potential to significantly improve the generalization of deep learning models. Recently, automated augmentation strategies have led to state-of-the-art results in image classification and…

Learning for robot navigation presents a critical and challenging task. The scarcity and costliness of real-world datasets necessitate efficient learning approaches. In this letter, we exploit Euclidean symmetry in planning for 2D…

One powerful paradigm in visual navigation is to predict actions from observations directly. Training such an end-to-end system allows representations useful for downstream tasks to emerge automatically. However, the lack of inductive bias…

In this paper, we present a conditional generative adversarial network-based model for real-time underwater image enhancement. To supervise the adversarial training, we formulate an objective function that evaluates the perceptual image…

End-to-end visual-based imitation learning has been widely applied in autonomous driving. When deploying the trained visual-based driving policy, a deterministic command is usually directly applied without considering the uncertainty of the…

We present a training pipeline for the autonomous driving task given the current camera image and vehicle speed as the input to produce the throttle, brake, and steering control output. The simulator Airsim's convenient weather and lighting…

Vision-language Navigation (VLN) tasks require an agent to navigate step-by-step while perceiving the visual observations and comprehending a natural language instruction. Large data bias, which is caused by the disparity ratio between the…