CS 730/830: Intro AI What is AI? This class Problems in AI Prof. Wheeler Ruml Search TA Tianyi Gu “Thinking inside the box.” 5 handouts: course info, project info, schedule, slides, asst 1 sign up sheet/laptop (grading email, piazza) Wheeler Ruml (UNH) Lecture 1, CS 730 – 1 / 23
What is AI? ■ My Definition ■ Robots ■ Intelligence ■ The Goal ■ Relations ■ AI Today ■ Robots Today This class What is AI? Problems in AI Search Wheeler Ruml (UNH) Lecture 1, CS 730 – 2 / 23
My Definition of AI What is AI? ■ My Definition ■ Robots ■ Intelligence ■ The Goal ■ Relations ■ AI Today ■ Robots Today This class Problems in AI Search Wheeler Ruml (UNH) Lecture 1, CS 730 – 3 / 23
What is a Robot? Artificial physical system that takes adaptive action. What is AI? ■ My Definition remote-controlled car ■ Robots ■ ■ Intelligence power tool ■ ■ The Goal robotic surgery ■ Relations ■ ■ AI Today motion sensor ■ ■ Robots Today thermostat ■ This class anti-lock brakes Problems in AI ■ automated delivery Search ■ autopilot ■ self-driving car ■ Ava, Data. . . ■ Wheeler Ruml (UNH) Lecture 1, CS 730 – 4 / 23
What is Intelligence? What behaviors require intelligence? What is AI? What makes an agent intelligent? ■ My Definition ■ Robots ■ Intelligence ■ The Goal ■ Relations ■ AI Today ■ Robots Today This class Problems in AI Search Wheeler Ruml (UNH) Lecture 1, CS 730 – 5 / 23
Different Goals in AI How to understand Intelligence ? What is AI? ■ My Definition ■ Robots ■ Intelligence Cognitive modeling: behaves like a human ■ The Goal ■ Relations Engineering: achieve human performance ■ AI Today Rational: behaves perfectly, normative ■ Robots Today Bounded-rational: behaves as well as possible This class Problems in AI Subfields: knowledge representation and reasoning, computer Search problem-solving, planning, machine learning, natural language processing, (autonomous) robotics, intelligent agents, multi-agent systems, distributed AI, intelligent user interfaces, machine vision Other terms: computational intelligence Related: adaptive behavior, complex adaptive systems, artificial life, cognitive modeling Wheeler Ruml (UNH) Lecture 1, CS 730 – 6 / 23
Relations CS: algorithms ■ What is AI? Engineering: applications ■ My Definition ■ ■ Robots Cognitive psychology: modeling ■ ■ Intelligence ■ The Goal Philosophy: mind, rationality ■ ■ Relations Math: logic, statistics ■ ■ AI Today ■ Robots Today Linguistics: language processing ■ This class Operations research: optimization ■ Problems in AI Economics: agents, incentives ■ Search Wheeler Ruml (UNH) Lecture 1, CS 730 – 7 / 23
AI Today Game playing: chess, checkers, backgammon, Jeopardy!, ■ What is AI? crosswords, go ■ My Definition ■ Robots Design: VLSI, jet engines ■ ■ Intelligence ■ The Goal Diagnosis: POS, NASD, loans, customer service, medical ■ ■ Relations testing and classification, DS1 ■ AI Today ■ Robots Today Planning: airports, flight routes, Dell, DART ■ This class Learning: Amazon, Netflix, Walmart, Facebook ■ Problems in AI Robotics: ping-pong, beer fetch, driving, flying ■ Search Language: voice recognition, translation ■ Vision: scene descriptions, face recognition ■ Hidden: logistics, data center control, distribution centers ■ Wheeler Ruml (UNH) Lecture 1, CS 730 – 8 / 23
Robots Today: Beautiful Hardware What is AI? ■ My Definition ■ Robots ■ Intelligence ■ The Goal ■ Relations ■ AI Today ■ Robots Today This class Problems in AI Search Honda Asimo: virtually no autonomy. Wheeler Ruml (UNH) Lecture 1, CS 730 – 9 / 23
Robots Today: Beautiful Hardware What is AI? ■ My Definition ■ Robots ■ Intelligence ■ The Goal ■ Relations ■ AI Today ■ Robots Today This class Problems in AI Search NASA Mars Science Lab: some navigation autonomy. Wheeler Ruml (UNH) Lecture 1, CS 730 – 9 / 23
Robots Today: Beautiful Hardware What is AI? ■ My Definition ■ Robots ■ Intelligence ■ The Goal ■ Relations ■ AI Today ■ Robots Today This class Problems in AI Search NASA Deep Space 1: temporarily self-commanded. Wheeler Ruml (UNH) Lecture 1, CS 730 – 9 / 23
Robots Today: Beautiful Hardware What is AI? ■ My Definition ■ Robots ■ Intelligence ■ The Goal ■ Relations ■ AI Today ■ Robots Today This class Problems in AI Search AUVs: dynamic environment, poor communication. Wheeler Ruml (UNH) Lecture 1, CS 730 – 9 / 23
Robots Today: Beautiful Hardware What is AI? ■ My Definition ■ Robots ■ Intelligence ■ The Goal ■ Relations ■ AI Today ■ Robots Today This class Problems in AI Search Boston Dynamics LS3: follow me. Wheeler Ruml (UNH) Lecture 1, CS 730 – 9 / 23
Robots Today: Beautiful Hardware What is AI? ■ My Definition ■ Robots ■ Intelligence ■ The Goal ■ Relations ■ AI Today ■ Robots Today This class Problems in AI Search Kiva Systems: bring inventory to pickers. Wheeler Ruml (UNH) Lecture 1, CS 730 – 9 / 23
Robots Today: Beautiful Hardware What is AI? ■ My Definition ■ Robots ■ Intelligence ■ The Goal ■ Relations ■ AI Today ■ Robots Today This class Problems in AI Search KAIST Hubo: winner of the 2015 DRC. Wheeler Ruml (UNH) Lecture 1, CS 730 – 9 / 23
Robots Today: Beautiful Hardware What is AI? ■ My Definition ■ Robots ■ Intelligence ■ The Goal ■ Relations ■ AI Today ■ Robots Today This class Problems in AI Search Willow Garage PR2: 22 degrees of freedom. Wheeler Ruml (UNH) Lecture 1, CS 730 – 9 / 23
Robots Today: Beautiful Hardware What is AI? ■ My Definition ■ Robots ■ Intelligence ■ The Goal ■ Relations ■ AI Today ■ Robots Today This class Problems in AI Search Yamaha RMax at Link¨ oping University: autonomous. Wheeler Ruml (UNH) Lecture 1, CS 730 – 9 / 23
Robots Today: Beautiful Hardware What is AI? ■ My Definition ■ Robots ■ Intelligence ■ The Goal ■ Relations ■ AI Today ■ Robots Today This class Problems in AI Search Google Self-Driving Car: over 1.8M miles, 13 minor accidents. Wheeler Ruml (UNH) Lecture 1, CS 730 – 9 / 23
What is AI? This class ■ The AI View ■ An AI Agent ■ Schedule ■ Course Mechanics Problems in AI Search This class Wheeler Ruml (UNH) Lecture 1, CS 730 – 10 / 23
The AI View of An Agent What is AI? This class ■ The AI View ■ An AI Agent ■ Schedule ■ Course Mechanics Problems in AI Search Wheeler Ruml (UNH) Lecture 1, CS 730 – 11 / 23
The AI View of An Agent What is AI? This class ■ The AI View ■ An AI Agent ■ Schedule ■ Course Mechanics Problems in AI Search percepts → → actions Wheeler Ruml (UNH) Lecture 1, CS 730 – 11 / 23
An AI Agent What is AI? This class agent ■ The AI View ■ An AI Agent ■ Schedule ■ Course Mechanics Problems in AI Search actions sensing world Wheeler Ruml (UNH) Lecture 1, CS 730 – 12 / 23
An AI Agent What is AI? This class agent ■ The AI View ■ An AI Agent ■ Schedule ■ Course Mechanics Problems in AI Search world model actions planner sensing world Wheeler Ruml (UNH) Lecture 1, CS 730 – 12 / 23
An AI Agent What is AI? This class agent ■ The AI View ■ An AI Agent ■ Schedule ■ Course Mechanics Problems in AI Search world model actions planner sensing search world Wheeler Ruml (UNH) Lecture 1, CS 730 – 12 / 23
Schedule 1. planning: vacuum tasks, hovercraft motion, puzzle What is AI? state-space search This class ■ The AI View constraint satisfaction ■ An AI Agent combinatorial optimization ■ Schedule ■ Course Mechanics 2. KR: theorem provers Problems in AI propositional logic Search first-order logic 3. more planning: general planner, probabilistic planner domain-independent planning Markov decision processes 4. perception: digits, shapes, localization supervised and unsupervised learning hidden Markov models See also: Intro to mobile Robotics, Intro to Machine Learning Not: NLP, cognitive modeling, philosophy Wheeler Ruml (UNH) Lecture 1, CS 730 – 13 / 23
Course Mechanics General information ■ What is AI? Schedule ■ This class ■ The AI View Project ■ ■ An AI Agent Asst 1 ■ ■ Schedule ■ Course Mechanics Names ■ Problems in AI Search Wheeler Ruml (UNH) Lecture 1, CS 730 – 14 / 23
What is AI? This class Problems in AI ■ Agent Designs ■ Examples ■ Environments Search Problems in AI Wheeler Ruml (UNH) Lecture 1, CS 730 – 15 / 23
Agent Designs Agent ⇔ Environment What is AI? This class Perception: vision, state estimation Problems in AI Planning: low/high-level, on/off-line, incremental/repair ■ Agent Designs ■ Examples Acting: dispatching, monitoring, diagnosis ■ Environments Search Reflex: sensors → effectors Reflex with state: sensors + state → effectors + new state Goal-based: reason from goals to means Utility-based: use quantitative measure of happiness Wheeler Ruml (UNH) Lecture 1, CS 730 – 16 / 23
What kind of agent? 1. Thermostat What is AI? 2. autonomous armed drone This class 3. Mail delivery robot Problems in AI ■ Agent Designs 4. Medical diagnosis system ■ Examples ■ Environments Search Wheeler Ruml (UNH) Lecture 1, CS 730 – 17 / 23
Recommend
More recommend
