AI Research for Autonomous Driving

 Our next technical evening of 2019, to be held in the National Library of Technology, will look at research in the area of usage of Artificial Intelligence in the development of autonomous driving, its problems, opportunities and challenges.

 

Development of autonomous cars is not only a futuristic concept, but it is here already now. Big international companies, as well as universities are joining the race to deliver the technologies. AI is an omnipresent technology associated with almost every area of our lives. Autonomous cars are not an exception.

 

Come and listen to the stories of Patrick Perez and Matthieu Cord, representatives of Valeo.ai, a special research group focused on the use of AI technology in automotive and Tomáš Svoboda, chair at the Department of Cybernetics from Czech Technical University.

 

Date: Wednesday 17.4.2019

Address:

Národní technická knihovna
Technická 2710/6
160 80, Prague
Czech Republic

Entrance number NTK3

Schedule:

Doors open [05:00 PM]
Presentations & open discussion [05:30 PM]
Networking & Drinks [08:00 PM]

 

Speakers:

Patrick Pérez – Director Valeo.ai

Title: Unsupervised domain adaptation with application to urban scene analysis

Abstract: In numerous real world applications, no matter how much energy is devoted to build real and/or synthetic training datasets, there remains a large distribution gap between these data and those met at run-time. This gap results in severe, possibly catastrophic, performance loss. This problem is especially acute for automated and autonomous driving systems, where generalizing well to diverse testing environments remains a major challenge. One promising tool to mitigate this issue it unsupervised domain adaptation (UDA), which assumes that un-annotated data from the “test domain” are available at training time, along with the annotated data from the “source domain”. We will discuss different ways to approach UDA, with application to semantic segmentation and object detection in urban scenes. We will introduce a new approach, called AdvEnt, that relies on combining adversarial training with minimization of decision entropy (seen as a proxy for uncertainty).  

Matthieu Cord – Professor of Computer Science, Sorbonne University and Researcher at Valeo.ai

Title: Designing multimodal deep architectures for Visual Question Answering

Abstract: Multimodal representation learning for text and image has been extensively studied in recent years. Currently, one of the most popular tasks in this field is Visual Question Answering (VQA). I will introduce this complex multimodal task, which aims at answering a question about an image. To solve this problem, visual and textual deep nets models are required and, high level interactions between these two modalities have to be carefully designed into the model in order to provide the right answer. This projection from the unimodal spaces to a multimodal one is supposed to extract and model the relevant correlations between the two spaces. Besides, the model must have the ability to understand the full scene, focus its attention on the relevant visual regions and discard the useless information regarding the question.

Tomáš Svoboda – Associate Professor at Czech Technical University, chair of the Department of Cybernetics

Title: Learning for traversing rough terrain

Abstract: Autonomous traversal of difficult obstacles and rough terrain in general is one of the essential functionalities required for deploying search and rescue robot. The talk will discuss several learning algorithms for controling robot morphology – configuration of articulated parts and their compliance. Algorithms use both interoceptive and exteroceptive data. Our story begins with a classical Reinforcement learning approach and ends with domain transfer by employing generative adversarial models for bridging the gap between simulated and real world.

Výzkum umělé inteligence pro autonomní řízení

 Náš následující technický večer se bude konat v Národní technické knihovně. Zabývat se budeme výzkumem v oblasti umělé inteligence (AI) pro autonomní řízení, souvisejícimi problémy a výzvami.

Vývoj autonomních vozidel už nepředstavuje hudbu budoucnosti, ale dneška. Začíná boj jak mezi nadnárodními korporáty, menšími společnostmi, tak i univerzitami, kdo dřív dodá bezchybnou technologii. Umělá inteligence začíná být nedílnou součástí všech oblastí našeho života a autonomní auta nejsou vyjímkou.

Přijďte a poslechněte si zkušenosti našich kolegů Patricka Pereze a Matthieu Corda z Valeo.ai, výzkumné skupiny specializované na využití umělé inteligence v automotive, a váženého hosta, Tomáše Svobody, vedoucího Katedry kybernetiky z ČVUT.

Datum: Středa 17.4.2019

Adresa:

Národní technická knihovna
Technická 2710/6
160 80 Praha
Česká republika

Vchod NTK3

Program:

[17:00] otevíráme
[17:30] prezentace a otevřená diskuse
[20:00] networking a občerstvení

Řečníci:

Patrick Pérez – ředitel Valeo.ai

Title: Unsupervised domain adaptation with application to urban scene analysis

Abstract: In numerous real world applications, no matter how much energy is devoted to build real and/or synthetic training datasets, there remains a large distribution gap between these data and those met at run-time. This gap results in severe, possibly catastrophic, performance loss. This problem is especially acute for automated and autonomous driving systems, where generalizing well to diverse testing environments remains a major challenge. One promising tool to mitigate this issue it unsupervised domain adaptation (UDA), which assumes that un-annotated data from the “test domain” are available at training time, along with the annotated data from the “source domain”. We will discuss different ways to approach UDA, with application to semantic segmentation and object detection in urban scenes. We will introduce a new approach, called AdvEnt, that relies on combining adversarial training with minimization of decision entropy (seen as a proxy for uncertainty).

Matthieu Cord – profesor na univerzitě Paris Sorbonne a výzkumník ve Valeo.ai

Title: Designing multimodal deep architectures for Visual Question Answering

Abstract: Multimodal representation learning for text and image has been extensively studied in recent years. Currently, one of the most popular tasks in this field is Visual Question Answering (VQA). I will introduce this complex multimodal task, which aims at answering a question about an image. To solve this problem, visual and textual deep nets models are required and, high level interactions between these two modalities have to be carefully designed into the model in order to provide the right answer. This projection from the unimodal spaces to a multimodal one is supposed to extract and model the relevant correlations between the two spaces. Besides, the model must have the ability to understand the full scene, focus its attention on the relevant visual regions and discard the useless information regarding the question.

Tomáš Svoboda – docent na Českém vysokém učení technickém, vedoucí katedry kybernetiky

Title: Learning for traversing rough terrain

Abstract: Autonomous traversal of difficult obstacles and rough terrain in general is one of the essential functionalities required for deploying search and rescue robot. The talk will discuss several learning algorithms for controling robot morphology – configuration of articulated parts and their compliance. Algorithms use both interoceptive and exteroceptive data. Our story begins with a classical Reinforcement learning approach and ends with domain transfer by employing generative adversarial models for bridging the gap between simulated and real world.