智慧系統之感知與決策

Welcome to the Perception and Decision Making in Intelligent Systems! In recent years, we have witnessed tremendous progress in intelligent systems such as self-driving cars and robotics. We have witnessed significant progress in social media and demonstrations, including Jensen Huang's GTC and Computex Talk (https://www.youtube.com/live/pKXDVsWZmUU?si=-A4QE2dF9_hoE92f&t=5351). Do you know how they realize these applications? Do you know how recent advances in artificial intelligence power these systems? What are the new challenges of applying AI to these intelligent systems? Please sign up for this course if you are interested in diving into this field! The intended learning outcomes of this course are: - Identify the key components of intelligent systems - Explain the key components of intelligent systems, i.e., robot navigation and robot manipulation systems - Apply key components to build robot navigation and manipulation systems - Explain the difference between conventional and recent data-driven intelligent systems - Develop your own solution for intelligent systems

Programming (C/C++/Python), Linear Algebra, Probability, Computer Vision, and Machine Learning

Course Assignment: 50% (4 or 5 computer assignments) - HW1: Robot Navigation - 3D Scene Reconstruction - HW2: Robot Navigation - 3D Semantic Mapping - HW3: Robot Navigation - Path Planning - HW4: Robot Manipulation Final Project (per group, 2-3 people a group): 40% - Participate in Embodied AI Challenges (https://embodied-ai.org/) - Present YOUR algorithm for solving one of the challenges by the end of the semester Class Participation: 10% Proactively engage in class discussions (My intention is not to keep you in class, but to make you “think” and “discuss” so that you “learn.”)

• Spatial Representation and Image Formation
• State Estimation
• Planning and Control
• Robot Navigation
• Robot Manipulation
• Language-Guided Intelligent Systems

Slides, papers, and online resources