Related papers: Learning Deep Generative Spatial Models for Mobile…

Neural networks are often regarded as universal equations that can estimate any function. This flexibility, however, comes with the drawback of high complexity, rendering these networks into black box models, which is especially relevant in…

For autonomous agents to act as trustworthy partners to human users, they must be able to reliably communicate their competency for the tasks they are asked to perform. Towards this objective, we develop probabilistic world models based on…

Deep generative models provide a systematic way to learn nonlinear data distributions, through a set of latent variables and a nonlinear "generator" function that maps latent points into the input space. The nonlinearity of the generator…

We give algorithms with provable guarantees that learn a class of deep nets in the generative model view popularized by Hinton and others. Our generative model is an $n$ node multilayer neural net that has degree at most $n^{\gamma}$ for…

Recent progress in deterministic prompt learning has become a promising alternative to various downstream vision tasks, enabling models to learn powerful visual representations with the help of pre-trained vision-language models. However,…

Traditional place categorization approaches in robot vision assume that training and test images have similar visual appearance. Therefore, any seasonal, illumination and environmental changes typically lead to severe degradation in…

The objective of this work is to augment the basic abilities of a robot by learning to use sensorimotor primitives to solve complex long-horizon manipulation problems. This requires flexible generative planning that can combine primitive…

We present a Deep Learning based system for the twin tasks of localization and obstacle avoidance essential to any mobile robot. Our system learns from conventional geometric SLAM, and outputs, using a single camera, the topological pose of…

Deep generative models have been used in recent years to learn coherent latent representations in order to synthesize high-quality images. In this work, we propose a neural network to learn a generative model for sampling consistent indoor…

This paper provides a review of deep learning applications in scene understanding in autonomous robots, including innovations in object detection, semantic and instance segmentation, depth estimation, 3D reconstruction, and visual SLAM. It…

Unmanned aerial vehicles (UAVs) are frequently used for aerial mapping and general monitoring tasks. Recent progress in deep learning enabled automated semantic segmentation of imagery to facilitate the interpretation of large-scale complex…

Environment perception is a crucial ability for robot's interaction into an environment. One of the first steps in this direction is the combined problem of simultaneous localization and mapping (SLAM). A new method, called G-SLAM, is…

Vehicle trajectory prediction is crucial for autonomous driving and advanced driver assistant systems. While existing approaches may sample from a predicted distribution of vehicle trajectories, they lack the ability to explore it -- a key…

Traditional deep generative models of images and other spatial modalities can only generate fixed sized outputs. The generated images have exactly the same resolution as the training images, which is dictated by the number of layers in the…

The need for consistent treatment of uncertainty has recently triggered increased interest in probabilistic deep learning methods. However, most current approaches have severe limitations when it comes to inference, since many of these…

This paper presents a novel probabilistic approach to deep robot learning from demonstrations (LfD). Deep movement primitives (DMPs) are deterministic LfD model that maps visual information directly into a robot trajectory. This paper…

Semantic segmentation enables robots to perceive and reason about their environments beyond geometry. Most of such systems build upon deep learning approaches. As autonomous robots are commonly deployed in initially unknown environments,…

We introduce the Generalized Energy Based Model (GEBM) for generative modelling. These models combine two trained components: a base distribution (generally an implicit model), which can learn the support of data with low intrinsic…

The objective of this work is to augment the basic abilities of a robot by learning to use new sensorimotor primitives to enable the solution of complex long-horizon problems. Solving long-horizon problems in complex domains requires…

Implicit generative models have the capability to learn arbitrary complex data distributions. On the downside, training requires telling apart real data from artificially-generated ones using adversarial discriminators, leading to unstable…