Indoor vs Outdoor: Water, air, ground Autonomy depends on the need:

Transcription

1 I and Robotics Whatis a robot? Different types of robots. utonomy What do you find on an autonomous robot? Planning and Robotics STRIPS onjunctive goals Horisontal architecture Subsumption architecture The Future: Social robots. What does the word ``Robot mean? Robot = Forced labor Robota = Drudgery (tungt arbete) iologically Engineered no mechanical parts! oined by hech writers Josef and Karel Čapek Three laws of robotics by simov. robot... may not injure a human being, or through inaction, allow a human being to come to harm. must obey orders given it by human beings, expect where that would conflict with the first law. must protect its own existence expect where that would conflict with the first or second law. Different types of Robots Indoor, outdoor. Water, air, ground (wheels, tracks or leggs). Degrees of autonomy: Shared (industrial robot) Semi (human intervenes occasionally) Full (can operate without human intervention) Indoor vs Outdoor: Water, air, ground utonomy depends on the need: Shared: uilt a car in a factory. ll the cars must be exactly the same. Semi: Sending robot to Mars. 30 min delay for the radio signals Earth Mars. Full: Vacuum clean a house. void the cat, etc. aran ürüklü 1

2 What do you find on an autonomous robot? Sensing (Sense) omputing (Plan) Motion (ct) Material covered until know is mainly under Plan Sensing Encoders on the wheel axes (to measure traveled distance) /W or color camera to ``see objects and calculate distances to them. Sonars/lasers to measure distance to objects. rtificial noses (and other specialized sensors) find the land mine or truffle in wine and cheese production omputing using Ordinary processors. Signal processors. Transputers. Motion Wheels, tracks, vings or leggs for motion rms for manipulating the objects. it depens on the task and the budget. Vision may require a fast processor. Planning and Robotics What is planning? form of search? What is planning? form of search? Different techniques/theories. Planning and robotics. Search: fs, Dfs are based on state-space. state specifies all the relevant as well as irrelevant facts. Operators(state_in, state_out) apply to a fully specified state. Memory consumtion is huge. aran ürüklü 2

3 Planning is more efficient compared to Search Planning is search in the formula space State: at(baran,home) has(baran,bananas) Operators: buy(bananas) results in has(baran,bananas) Formal definition of planning Planning involves choosing a plan by considering alternative plans and reasoning about their consequences. Planning... Does not case about irrelevant facts. Like at(baran,home) above Interested in the path from the start to goal. STRIPS - STanford Research Institute Problem Solver Example: lock Stacking Problem ction: move(x,y,z) move block X from top of Y to top of Z Precondition: on(x,y) cleartop(z) cleartop(x) Effects dditions : on(x,z) cleartop(y) Effects Deletions : on(x,y) cleartop(z) move(x,y,z) ction: move(x,y,z) X =, Y =, Z = Precondition: on(,) cleartop() cleartop() Effects dditions : on(,) cleartop() Effects Deletions : on(,) cleartop() STRIPS={objects, initial_facts, operators} objects = {,,, table} initial_ facts = {on(,table), free(),...} goal = {on(,), free(), on(,), on(,table)} operators = {oper1(pre,add,del), oper2(pre,add,del),...} ``pre is a list of precondition (facts). ``add is a list of facts to be added. ``del is a list of facts to be deleted. The STRIPS ssumption World is deterministic No exogenous actions the world does not change (evolve). all changes are described by the operators. aran ürüklü 3

4 onjunctive goals Goal = on(,) free() on(,) on(,table) the order of achievements of sub goals does not matter. Not true in many real life problems. Initial state Sussman nomaly chive first: on(, ) an we achive on(,)? or achive first: on(, ) an we achive on(,)? onclusion goal Order of achievements of sub goals does matter. Partially Ordered Plan Wake up Left sock Right sock Left shoe Right shoe Finish Planning and Robotics (some history) Planning first! ( ) Focus on generating plans STRIPS formalism ssumeideal conditions ut the world is not perfect. ction first! ( ) Rodney rooks at MIT Focus on execution of plans in dynamic enviroments. Somebody must makes plans. rooks Outrage (1985) The horisontal architecture (see belov) is a composition of many steps and it takes too long to generate an action. rooks alternative to the horisotal architecture The vertical subsumption architecture. Higher leves have higher priority. Short way from sensors to action. sensors perception modeling planning task execution motor control actuators sensors reason about behaviors identify objects built maps of the envoriment wander around actuators avoid objects aran ürüklü 4

5 The vertical subsumption architecture Everything is behavior No need to model the enviroment. Remember we are interested in action not in planning. ehaviors with higher priorities inhibits whose with lower priorities. ut how to decide the priorities between behaviors? Subsumption example behavior 3 inhibition behavior 2 sensors behavior 1 s s actuators behavior 1: wander around behavior 2: catch the mouse behavior 3: eat the mouse The Future: Social robots. Kısmet s design is more like the cortex of a primate then a simple planning architecture. Kısmet (rooks) og (rooks) oco (rooks) aran ürüklü 5