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.
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.
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.