Sort by: Year Popularity Relevance

Practical Issues of Action-conditioned Next Image Prediction

, , , , ,  - 2018

The problem of action-conditioned image prediction is to predict the expected next frame given the current camera frame the robot observes and an action selected by the robot. We provide the first comparison of two recent popular models, especially for image prediction on cars. Our major finding is that action tiling encoding is the most importan...


Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car

, , , , , ,  - 2017

As part of a complete software stack for autonomous driving, NVIDIA has created a neural-network-based system, known as PilotNet, which outputs steering angles given images of the road ahead. PilotNet is trained using road images paired with the steering angles generated by a human driving a data-collection car. It derives the necessary domain kn...


Deep Reinforcement Learning framework for Autonomous Driving

, , ,  - 2017

Reinforcement learning is considered to be a strong AI paradigm which can be used to teach machines through interaction with the environment and learning from their mistakes. Despite its perceived utility, it has not yet been successfully applied in automotive applications. Motivated by the successful demonstrations of learning of Atari games and...


The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation

, , , ,  - 2016

State-of-the-art approaches for semantic image segmentation are built on Convolutional Neural Networks (CNNs). The typical segmentation architecture is composed of (a) a downsampling path responsible for extracting coarse semantic features, followed by (b) an upsampling path trained to recover the input image resolution at the output of the model...


Learning And-Or Models to Represent Context and Occlusion for Car Detection and Viewpoint Estimation

, ,  - 2015

This paper presents a method for learning And-Or models to represent context and occlusion for car detection and viewpoint estimation. The learned And-Or model represents car-to-car context and occlusion configurations at three levels: (i) spatially-aligned cars, (ii) single car under different occlusion configurations, and (iii) a small number o...


Predicting Driver Attention in Critical Situations

, , , , ,  - 2017

Robust driver attention prediction for critical situations is a challenging computer vision problem, yet essential for autonomous driving. Because critical driving moments are so rare, collecting enough data for these situations is difficult with the conventional in-car data collection protocol---tracking eye movements during driving. Here, we fi...


Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?

, , , , ,  - 2016

Deep learning has rapidly transformed the state of the art algorithms used to address a variety of problems in computer vision and robotics. These breakthroughs have relied upon massive amounts of human annotated training data. This time consuming process has begun impeding the progress of these deep learning efforts. This paper describes a metho...


Deep convolutional neural networks for pedestrian detection

, , , , ,  - 2015

Pedestrian detection is a popular research topic due to its paramount importance for a number of applications, especially in the fields of automotive, surveillance and robotics. Despite the significant improvements, pedestrian detection is still an open challenge that calls for more and more accurate algorithms. In the last few years, deep learni...


Deep Attention Recurrent Q-Network

, , , ,  - 2015

A deep learning approach to reinforcement learning led to a general learner able to train on visual input to play a variety of arcade games at the human and superhuman levels. Its creators at the Google DeepMind's team called the approach: Deep Q-Network (DQN). We present an extension of DQN by "soft" and "hard" attention mechanisms. Tests of the...


Traffic Sign Classification Using Deep Inception Based Convolutional Networks

 - 2015

In this work, we propose a novel deep network for traffic sign classification that achieves outstanding performance on GTSRB surpassing all previous methods. Our deep network consists of spatial transformer layers and a modified version of inception module specifically designed for capturing local and global features together. This features adopt...