相关论文: Learning to Predict Robot Keypoints Using Artifici…

We introduce a novel formulation for incorporating visual feedback in controlling robots. We define a generative model from actions to image observations of features on the end-effector. Inference in the model allows us to infer the robot…

Humans rely on effective representations to learn from few examples and abstract useful information from sensory data. Inducing such representations in machine learning models has been shown to improve their performance on various…

Algorithmic case-based decision support provides examples to help human make sense of predicted labels and aid human in decision-making tasks. Despite the promising performance of supervised learning, representations learned by supervised…

In the industrial domain, the pose estimation of multiple texture-less shiny parts is a valuable but challenging task. In this particular scenario, it is impractical to utilize keypoints or other texture information because most of them are…

In meta-learning approaches, it is difficult for a practitioner to make sense of what kind of representations the model employs. Without this ability, it can be difficult to both understand what the model knows as well as to make meaningful…

We describe an algorithm for motion planning based on expert demonstrations of a skill. In order to teach robots to perform complex object manipulation tasks that can generalize robustly to new environments, we must (1) learn a…

The task of 6D object pose estimation from RGB images is an important requirement for autonomous service robots to be able to interact with the real world. In this work, we present a two-step pipeline for estimating the 6 DoF translation…

Creating computer vision datasets requires careful planning and lots of time and effort. In robotics research, we often have to use standardized objects, such as the YCB object set, for tasks such as object tracking, pose estimation,…

Imitation can allow us to quickly gain an understanding of a new task. Through a demonstration, we can gain direct knowledge about which actions need to be performed and which goals they have. In this paper, we introduce a new approach to…

Predictive human models often need to adapt their parameters online from human data. This raises previously ignored safety-related questions for robots relying on these models such as what the model could learn online and how quickly could…

This paper proposes to use keypoints as a self-supervision clue for learning depth map estimation from a collection of input images. As ground truth depth from real images is difficult to obtain, there are many unsupervised and…

Applying end-to-end learning to solve complex, interactive, pixel-driven control tasks on a robot is an unsolved problem. Deep Reinforcement Learning algorithms are too slow to achieve performance on a real robot, but their potential has…

Operating directly from raw high dimensional sensory inputs like images is still a challenge for robotic control. Recently, Reinforcement Learning methods have been proposed to solve specific tasks end-to-end, from pixels to torques.…

Medical imaging classifiers can achieve high predictive accuracy, but quantifying their uncertainty remains an unresolved challenge, which prevents their deployment in medical clinics. We present an algorithm that can modify any classifier…

Computational image reconstruction algorithms generally produce a single image without any measure of uncertainty or confidence. Regularized Maximum Likelihood (RML) and feed-forward deep learning approaches for inverse problems typically…

We are motivated by the problem of learning policies for robotic systems with rich sensory inputs (e.g., vision) in a manner that allows us to guarantee generalization to environments unseen during training. We provide a framework for…

Perception systems, especially cameras, are the eyes of automated driving systems. Ensuring that they function reliably and robustly is therefore an important building block in the automation of vehicles. There are various approaches to…

Video prediction methods generally consume substantial computing resources in training and deployment, among which keypoint-based approaches show promising improvement in efficiency by simplifying dense image prediction to light keypoint…

We introduce an approach to building a custom model from ready-made self-supervised models via their associating instead of training and fine-tuning. We demonstrate it with an example of a humanoid robot looking at the mirror and learning…

We consider the visual feature selection to improve the estimation quality required for the accurate navigation of a robot. We build upon a key property that asserts: contributions of trackable features (landmarks) appear linearly in the…