Neural Semantic 3D World Modeling and Mapping

You are in taxonomy page

Neural Semantic 3D World Modeling and Mapping

This lecture overviews neural semantic 3D world modeling and mapping  that has many applications in 3D world mapping and in attaching semantics to the world maps It covers the following topics in detail: neural disparity/depth estimation and joint 3D scene geometry and semantics estimation. Their results are then transferred in semantic 3D world maps (e.g., semantic octomaps). Dynamic and static semantic map annotations (e.g., no flight zones, crowd areas) are also attached to such 3D world maps as KML documents.

Should you require access to the resource, please contact the author directly.

Introduction to Computer Vision

A detailed introduction to computer vision will be made: image/video sampling, Image and video acquisition, Camera geometry, Stereo and Multiview imaging, Structure from motion, Structure from X, 3D Robot Localization and Mapping, Semantic 3D world mapping, 3D object localization, Multiview object detection and tracking, Object pose estimation.

Should you require access to the resource, please contact the author directly.

Robot Learning

The talk discusses the long-standing vision of creating autonomous robots capable of assisting humans in daily life. A crucial step toward this goal is enabling robots to learn tasks based on environmental cues or higher-level instructions. However, current learning techniques face challenges in scaling to high-dimensional manipulator or humanoid robots. The speaker presents a general framework for learning motor skills in robotics, inspired by analytical robotics methods. This framework involves creating representations of motor skills using parameterised motor primitive policies as building blocks for generating movements. Additionally, there’s a learned task execution module that transforms these movements into motor commands.

Probabilistic Logics to Neuro-Symbolic Artificial Intelligence

A central challenge to contemporary AI is to integrate learning and reasoning. The integration of learning and reasoning has been studied for decades already in the fields of statistical relational artificial intelligence and probabilistic programming. StarAI has focussed on unifying logic and probability, the two key frameworks for reasoning, and has extended this probabilistic logics machine learning principles. I will argue that StarAI and Probabilistic Logics form an ideal basis for developing neuro-symbolic artificial intelligence techniques. Thus neuro-symbolic computation = StarAI + Neural Networks. Many parallels will be drawn between these two fields and will be illustrated using the Deep Probabilistic Logic Programming language DeepProbLog.Speaker

Robots Learning (Through) Interactions

The acquisition and self-improvement of novel motor skills is among the most important problems in robotics. I will discuss various learning techniques we developed that enable robots to have complex interactions with their environment and humans. Complexity arises from dealing with high-dimensional input data, non-linear dynamics in general and contacts in particular, multiple reference frames, and variability in objects, environments and tasks. A human teacher is always involved in the learning process, either directly (providing data) or indirectly (designing the optimisation criterion), which raises the question: How to best make use of the interactions with the human teacher to render the learning process efficient and effective? I will discuss various methods we have developed in the fields of supervised learning, imitation learning, reinforcement learning, and interactive learning. All these concepts will be illustrated with benchmark tasks and real robot experiments ranging from fun (ball-in-a-cup) to more applied (sorting products).

Towards Trustworthy AI – Integrating Reasoning and Learning

Europe has taken a clear stand that we want AI, but we do not want just any AI. We want AI that we can trust. This talk will present the European approach to Trustworthy AI and give an overview of some of the interesting research problems related to Trustworthy AI. Special emphasis will be placed on the need to integrate reasoning and learning to combine the power of data-driven methods with the formal guarantees and general solutions provided by reasoning-based approaches. The successful realisation of Trustworthy AI will be paramount for addressing the major challenges we as a global society is facing. The talk is partly based on the ongoing work in the H2020 ICT-48 network TAILOR which has the goal of developing the scientific foundations for Trustworthy AI through integrating learning, optimisation and reasoning.