DATA8010 - Embodied AI: Perception, Representation and Action
Course Instructor
Professor Yanchao YANG
Assistant Professor
HKU Musketeers Foundation Institute of Data Science and
Department of Electrical and Electronic Engineering, HKU
Professor Yanchao Yang is an Assistant Professor in the Department of Electrical and Electronic Engineering (EEE) and the HKU Musketeers Foundation Institute of Data Science (HKU-IDS). Before joining HKU, he was a Postdoctoral Research Fellow at Stanford University with Prof. Leonidas J. Guibas at the Geometric Computation Group. He received his Ph.D. from the University of California, Los Angeles (UCLA), working with Prof. Stefano Soatto. Earlier, he obtained his Master’s and Bachelor’s degrees from KAUST and USTC, respectively. He researches at the intersection of computer vision, machine learning, and robotics, with a long-term goal in developmental embodied intelligence. He currently focuses on self-supervised and semi-supervised techniques that allow autonomous agents to learn perception and representation at low-annotation regimes for physical interactions in open environments.
Professor Yanchao Yang is an Assistant Professor in the Department of Electrical and Electronic Engineering (EEE) and the HKU Musketeers Foundation Institute of Data Science (HKU-IDS). Before joining HKU, he was a Postdoctoral Research Fellow at Stanford University with Prof. Leonidas J. Guibas at the Geometric Computation Group. He received his Ph.D. from the University of California, Los Angeles (UCLA), working with Prof. Stefano Soatto. Earlier, he obtained his Master’s and Bachelor’s degrees from KAUST and USTC, respectively. He researches at the intersection of computer vision, machine learning, and robotics, with a long-term goal in developmental embodied intelligence. He currently focuses on self-supervised and semi-supervised techniques that allow autonomous agents to learn perception and representation at low-annotation regimes for physical interactions in open environments.
Course Description
This course will explore various topics in Embodied Artificial Intelligence (AI), which is concerned with the perception and representation of the physical world by autonomous agents and their consequent physical interactions. Specifically, the course will cover how an agent can infer the physical and semantic states of the scene, e.g., via 3D reconstruction and semantic parsing; how these perceptions can be represented in a way that facilitates reasoning with both efficiency and explainability; and how actions can be made in order to achieve downstream interaction tasks. By the end of this course, students will have gained an understanding of the fundamentals of perception, representation, and control in AI systems, as well as learned how embodied agents can be used to interact with and manipulate the physical world.
This course is designed for students with electrical engineering or computer science backgrounds who aim to perform research in the intersection of computer vision, machine learning, and robotics.
Prerequisites
Basic knowledge of linear algebra, probability and random processes, optimization, signal processing, and machine learning will ease the digestion of the course materials.
HKU IDS
Research Postgraduate Programme
DATA8010 - Embodied AI: Perception, Representation and Action (Application)
Course Instructor
Prof Yanchao YANG
Course Description
This course will explore various topics in Embodied Artificial Intelligence (AI), which is concerned with the perception and representation of the physical world by autonomous agents and their consequent physical interactions. Specifically, the course will cover how an agent can infer the physical and semantic states of the scene, e.g., via 3D reconstruction and semantic parsing; how these perceptions can be represented in a way that facilitates reasoning with both efficiency and explainability; and how actions can be made in order to achieve downstream interaction tasks. By the end of this course, students will have gained an understanding of the fundamentals of perception, representation, and control in AI systems, as well as learned how embodied agents can be used to interact with and manipulate the physical world.
This course is designed for students with electrical engineering or computer science backgrounds who aim to perform research in the intersection of computer vision, machine learning, and robotics.
Prerequisites
Basic knowledge of linear algebra, probability and random processes, optimization, signal processing, and machine learning will ease the digestion of the course materials.