Apr 28PIA project’s achievement at NeurIPS AIDO6Author: Robert Moni, András Kalapos, András Béres, Bence Hámori, Dávid Bárdos, Tibor Áron Tóth, Gyires-Tóth Bálint In December 2021 our team competed with 5 different solutions at the 6th edition of the AI Driving Olympics (AIDO) which was part of the 35th conference on Neural Information Processing Systems (NeurIPS). In…Self Driving Cars5 min read
Mar 3, 2021Using Transfer Learning to solve the simulator-to-real problem in the Duckietown environmentAuthor: Zoltán Lőrincz Introduction Throughout the previous semesters, I used Imitation Learning to carry out lane following in the Duckietown¹ environment. The agents were trained in the Duckietown simulator using different Imitation Learning methods such as Behavioral Cloning², Dataset Aggregation³ (DAgger) and Generative Adversarial Imitation Learning⁴ (GAIL). …Deep Learning6 min read
Feb 26, 2021PIA project’s perseveranceAuthor: Robert Moni Sorry for the clickbait, but no, we aren’t the engineers that put together the Perseverance Mars rover, although we do possess the right amount of perseverance to achieve our goals. This blog post attempts to provide a summary of our latest research achievements under the aegis of…Deep Learning5 min read
Feb 25, 2021Deep Learning-based Semantic Segmentation in Simulation and Real-World for Autonomous Vehicles — part 2Author: Zsombor Tóth Part 1 of this blog post can be found here. Introduction Deep Learning is one of the most important techniques of autonomous vehicles nowadays. There are many components of a self-driving vehicle that can be realized with the help of deep neural networks (e.g. car and pedestrian detection…Neural Networks4 min read
Feb 25, 2021Apply semi-supervised learning for semantic segmentationAuthor: Gábor Lant One of the key strength of deep learning is that it can work with a large amount of data to train machine learning models. These models can be trained to find the underlying structure of the data. On the other hand, this also means that data is…Deep Learning4 min read
Feb 25, 2021Disjoint Datasets in Multi-task Learning with Deep Neural Networks for Autonomous DrivingAuthor: Tamás Illés Introduction In Machine Learning (ML), we typically care about optimizing for a particular metric, whether this is a score on a certain benchmark or a business Key Performance Indicator (KPI). In order to do this, we generally train a single model or an ensemble of models to perform…Deep Learning4 min read
Feb 25, 2021Supervised and Unsupervised Representation Learning for Reinforcement LearningAuthor: András Béres Introduction Recently the topic of self-driving cars has received great attention both from academia and the public. While Deep Learning can provide us tools for processing vast amounts of sensor data, Reinforcement Learning promises us the ability to take the right actions in complex interactive environments. …Deep Learning5 min read
Feb 25, 2021Lane following in the Duckietown environment under extreme conditionsAuthor: Péter Almási I set the goal to create a method for controlling vehicles to perform autonomous lane following using deep reinforcement learning. The agent is trained in a simulated environment without any real-world data and is tested in the real world. …Deep Learning6 min read
Feb 25, 2021Deep Reinforcement Learning for Vehicle Control based on SegmentationAuthor: Márton Tim In Deep Reinforcement Learning (DRL), convergence and low performance of the resulting agent is often an issue that just intensifies as the problem becomes increasingly complex and complicated. …Deep Learning9 min read
Jan 14, 2021Link Prediction on Large Graphs with Variational AutoencodersAuthor: Dániel Unyi Link prediction is to predict whether two components in a network are likely to interact with each other. It’s a fundamental task in network science, with a wide variety of real-world applications. Examples include predicting friendship links on social media, identifying hidden communities, or discovering drug-drug interactions…Graph5 min read
