CS 561, Lecture 2Administrative Issues• Please send an email to [email protected] so that you can be on the class mailing list: [email protected]• Please when sending homework-related emails use Subject: HW: question about …• Quamrul Tipu: Office hours: Fridays, 2-4pm, SAL-211• Seokkyung Sung: Office hours: Weds, 10am-12pm, SAL-229•Web page: http://iLab.usc.edu(and follow the links)http://www-scf.usc.edu/~csci561a/CS 561, Lecture 2Last time: A driving example: Beobots• Goal: build robots that can operate in unconstrained environments and that can solve a wide variety of tasks.• We have:• Lots of CPU power• Prototype robotics platform• Visual system to find interesting objects in the world• Visual system to recognize/identify some of these objects• Visual system to know the type of scenery the robot is in• We need to:• Build an internal representation of the world• Understand what the user wants• Act upon user requests / solve user problemsCS 561, Lecture 2Beowulf + Robot =“Beobot”CS 561, Lecture 2PrototypeStripped-down version of proposedgeneral system, for simplifiedgoal: drive around USC olympictrack, avoiding obstaclesOperates at 30fps on quad-CPUBeobot;Layout & saliency very robust;Object recognition often confusedby background clutter.CS 561, Lecture 2Major issues• How to represent knowledge about the world?• How to react to new perceived events?• How to integrate new percepts to past experience?• How to understand the user?• How to optimize balance between user goals & environment constraints?• How to use reasoning to decide on the best course of action?• How to communicate back with the user?• How to plan ahead?• How to learn from experience?CS 561, Lecture 2GeneralarchitectureCS 561, Lecture 2Khan & McLeod, 2000OntologyCS 561, Lecture 2The task-relevance mapScalar topographic map, with higher values at more relevant locationsNavalpakkam & Itti, BMCV’02CS 561, Lecture 2More formally: how do we do it?- Use ontology to describe categories, objects and relationships:Either with unary predicates, e.g., Human(John),Or with reified categories, e.g., John ∈ Humans,And with rules that express relationships or properties,e.g., ∀x Human(x) Þ SinglePiece(x) ∧ Mobile(x) ∧ Deformable(x)- Use ontology to expand concepts to related concepts:E.g., parsing question yields “LookFor(catching)”Assume a category HandActions and a taxonomy defined bycatching ∈ HandActions, grasping ∈ HandActions, etc.We can expand “LookFor(catching)” to looking for other actions in the category where catching belongs through a simple expansion rule:∀a,b,c a ∈ c ∧ b ∈ c ∧ LookFor(a) Þ LookFor(b)CS 561, Lecture 2Last Time: Acting Humanly: The Full Turing Test• Alan Turing's 1950 article Computing Machinery and Intelligencediscussed conditions for considering a machine to be intelligent• “Can machines think?” ←→ “Can machines behave intelligently?”• The Turing test (The Imitation Game): Operational definition of intelligence.• Computer needs to posses:Natural language processing, Knowledge representation, Automated reasoning, and Machine learning•Problem:1) Turing test is not reproducible, constructive, and amenable to mathematic analysis. 2) What about physical interaction with interrogator and environment?• Total Turing Test: Requires physical interaction and needs perception and actuation.CS 561, Lecture 2Last time: The Turing Testhttp://www.ai.mit.edu/projects/infolab/http://aimovie.warnerbros.comCS 561, Lecture 2Last time: The Turing Testhttp://www.ai.mit.edu/projects/infolab/http://aimovie.warnerbros.comCS 561, Lecture 2Last time: The Turing Testhttp://www.ai.mit.edu/projects/infolab/http://aimovie.warnerbros.comCS 561, Lecture 2Last time: The Turing Testhttp://www.ai.mit.edu/projects/infolab/http://aimovie.warnerbros.comCS 561, Lecture 2Last time: The Turing Testhttp://www.ai.mit.edu/projects/infolab/http://aimovie.warnerbros.comCS 561, Lecture 2This time: Outline• Intelligent Agents (IA)• Environment types• IA Behavior•IA Structure•IA TypesCS 561, Lecture 2What is an (Intelligent) Agent?• An over-used, over-loaded, and misused term.• Anything that can be viewed asperceiving its environmentthrough sensors and acting upon that environment through its effectors to maximize progress towards its goals.• PAGE (Percepts, Actions, Goals, Environment)• Task-specific & specialized: well-defined goalsand environment• The notion of an agent is meant to be a tool for analyzing systems, not an absolute characterization that divides the world into agents and non-agents. Much like, e.g., object-oriented vs. imperative program design approaches.CS 561, Lecture 2Intelligent Agents and Artificial Intelligence• Human mind as network of thousands or millions of agents all working in parallel. To produce real artificial intelligence, this school holds, we should build computer systems that also contain many agents and systems for arbitrating among the agents' competing results. • Distributed decision-making and control• Challenges:• Action selection: What next actionto choose• Conflict resolutionsensorseffectorsAgencyCS 561, Lecture 2Agent TypesWe can split agent research into two main strands:• Distributed Artificial Intelligence (DAI) –Multi-Agent Systems (MAS) (1980 – 1990)• Much broader notion of "agent" (1990’s – present)• interface, reactive, mobile, informationCS 561, Lecture 2A Windshield Wiper AgentHow do we design a agent that can wipe the windshields when needed?•Goals? •Percepts ?•Sensors?• Effectors ?•Actions ?• Environment ?CS 561, Lecture 2A Windshield Wiper Agent (Cont’d)• Goals: To keep windshields clean and maintain good visibility• Percepts: Raining, Dirty• Sensors: Camera (moist sensor)• Effectors: Wipers (left, right, back)• Actions: Off, Slow, Medium, Fast• Environment: US inner city, freeways, highways, weather …CS 561, Lecture 2Towards Autonomous Vehicleshttp://iLab.usc.eduhttp://beobots.orgCS 561, Lecture 2Interacting AgentsCollision Avoidance Agent (CAA)• Goals: Avoid running into obstacles•Percepts ?•Sensors?• Effectors ?•Actions ?• Environment: FreewayLane Keeping Agent (LKA)• Goals: Stay in current lane•Percepts ?•Sensors?• Effectors ?•Actions ?• Environment: FreewayCS 561, Lecture 2Interacting AgentsCollision Avoidance Agent (CAA)• Goals: Avoid running
View Full Document
Unlocking...