2 Organization -SPA -global Strips The Hierarchical Paradigm • Describe the Hierarchical Paradigm in terms of the 3 robot primitives and its organization of sensing • Name and evaluate one representative Hierarchical architecture in terms of: support for modularity, niche targetability, ease of portability to other domains, robustness -Shakey Rep. Arch. • Solve a simple navigation problem using STRIPS (hint: work through Sec. 2.2.2) -evaluation -NHC • Understand precondition, closed world assumption, open world, frame problem -RCA Summary • List two advantages and disadvantages of the Hierarchical Paradigm Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 1 2 Hierarchical Paradigm… • Top-down: – Plan, plan, plan • Control-theoretic: – must measure error in order to control device • Planning means: – dependence on world models Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 2 2 Organization Organization SENSE -SPA PLAN ACT -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA World model: 1. A priori rep 2. Sensed info 3. Cognitive Summary Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 3 2 Organization Shakey • First AI robot -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA • Built by SRI (Stanford Research Institute) for DARPA 1967-9 • Used Strips as main algorithm for controlling what to do Summary Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 4 2 Strips: Means-ends analysis “Go to Stanford AI Lab” Organization -SPA -global INITIAL STATE: Tampa, Florida (0,0) GOAL STATE: Stanford, California (1000,200) Strips -Shakey Difference: 1020 miles Rep. Arch. -evaluation -NHC -RCA Summary Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 5 2 Difference Table Distance (difference) Organization -SPA mode of transportation (OPERATOR) d>=200 miles FLY 100<d<200 TRAIN d<=100 DRIVE d<1 WALK -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA mode=difference_table(INITIAL STATE, GOAL STATE, difference) Summary Introduction to AI Robotics (MIT Press) 1. Look up what to do: FLY 2. Not at SAIL, so repeat 3. Look up what to do: DRIVE Chapter 2: The Hierarchical Paradigm 6 2 Preconditions difference Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary OPERATOR PRECONDITIONS d>=200 miles FLY 100<d<200 TRAIN d<=100 DRIVE (rental) at airport DRIVE (personal car) at home d<1 WALK How do I know if I’m at the airport or at home? Now must keep up with the state of the world Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 7 2 Maintaining State of the World: Add and Delete Lists distance Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary d>=200 miles 100<d<2 00 d<=100 d<1 Introduction to AI Robotics (MIT Press) OPERATOR PRECONDITIONS FLY ADD-LIST DELETELIST at city Y at airport at city X at city Y at train station TRAIN DRIVE (rental) at airport DRIVE (personal) at home at city X WALK Chapter 2: The Hierarchical Paradigm 8 2 Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary Class Exercise distance OPERATOR PRECONDITIONS d<=200 miles FLY 100<d<2 00 TRAIN d<=100 DRIVE (rental) at airport DRIVE (personal) at home d<1 ADD-LIST DELETELIST at city Y at airport at city X at city Y at train station at city X WALK • Write down the world model, the operator applied, the change in world state, etc. to go from Tampa to Stanford Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 9 2 Strips Summary • Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary • • Designer must set up – World model representation – Difference table with operators, preconditions, add & delete lists – Difference evaluator Strips assumes closed world – Closed world: world model contains everything needed for robot (implication is that it doesn’t change) – Open world: world is dynamic and world model may not be complete Strips suffers from frame problem – Frame problem: representation grows too large to reasonably operate over Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 10 2 Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary Architecture • provides a principled way of organizing a control system. However, in addition to providing structure, it imposes constraints on the way the control problem can be solved [Mataric] • describes a set of architectural components and how they interact [Dean & Wellman] • Types of architectures [Levis, George Mason University] – operational architecture: describes what the systems does, not how it does it – systems architecture: describes how a system works in terms on major subsystems – technical architecture: implementation details Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 11 2 Nested Hierarchical Controller (Meystel) Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 12 2 NHC Planner Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 13 2 RCS (Albus) • the hierarchy • how the hierarchy works for navigation • how it is implemented – nodes and modules – planning time periods Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 14 2 RCS (Albus) • hierarchy with node structure at each level – have operator interface (in theory) • nodes consist of – – – – Sensory Processing World Model Behavior Generation Value Judgment • top-down, plan for a particular horizon – control theoretic Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 15 2 Examples of RCS Apps Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 16 2 Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary Evaluating an Architecture • support for modularity: does it show good software engineering principles? • niche targetability: how well does it work for the intended application? • ease of portability to other domains: how well would it work for other applications or other robots? • robustness: where is the system vulnerable, and how does it try to reduce that vulnerability? Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 17 2 Evaluating NHC & RCS • support for modularity: Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary – decomposition by functionality • niche targetability: – good, both have been used for apps like vehicle guidance, mining equipment • ease of portability to other domains: – unclear, not sure if code could be reused—lots of rewriting on previous apps • robustness: – RCS simulates plans in advance, but not sure what it would do with sensor or mechanical failures, etc. Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 18 2 Advantages & Disadvantages of Hierarchies Advantage of Hierarchal Paradigm Orders the relationship between Sensing, Planning and Acting • Natural way to organize • Not basically rigid (it’s sort of flexible) • Not basically inefficient (sort of organized) – not the same as centralized planning – priorities and goals are clear, therefore efficient Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 19 2 Advantages & Disadvantages of Hierarchies Disadvantages of Hierarchal Paradigm • Planning bottleneck by updating cycle of the world model and the planning. - Sensing and planning algorithm were extremely slow. • Eliminating of stimulus response (urgent actions) - sensing and acting is disconnect. • Frame problem -> Strips • For Particular applications -> NHC • Never handled Uncertainty - semantics, sensor noise, actuator errors, action completion. Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 20 2 Nodes are made from Modules xd is from “above” sensors transform into x* uff applies rule actions G is feedback (transition rules) u=uff+G(xd-x*) u is control action x* is predicted world state xd is desired world state uff is the feedforward control plan Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 21 2 Nodes are made from Modules xd is from “above” sensors transform into x* G is feedback actions uff applies rule (transition rules) if BALL, move toward centroid if NOT BALL, turn clockwise (feedback determines how fast) Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 22 2 Nodes are made from Modules xd is from “above” sensors transform into x* G is feedback actions uff applies rule (transition rules) when to stop? how far is far enough? what about noise/fuzzy ball? … sensor noise, actuator error, rigid models if BALL, move toward centroid if NOT BALL, turn clockwise (feedback determines how fast) Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 23 2 Demo III XUV http://museum.nist.gov/exhibits/timeline/item.cfm?itemId=38 Experimental Unmanned Vehicle in action at Ft. Indiantown Gap. Photo courtesy of the Army Research Labs. Nov. 2001 Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 24 2 RCS-4 Levels 7 6 Battalion Platoon 2-24h 5m-2h 5 Section 1-10m 4 Individual Vehicle 5-50s 3 Subsystem Level 200-500ms 2 Primitive Level 50-500ms 1 Servo Level 5-50ms Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 25 2 Each Level has a RCS Node Engineering of Mind, Albus & Mystel, 2001 Sensory Processing, World Modeling, Behavior Generation, Value Judgment Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 26 2 Implementation View: Nodes are Recursive Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 27 Demo III Control Hierarchy 2 Section 10m PLANNER vehicle1 vehicle2 Vehicle 1m VEHICLE PLANNER communications plan AM plan RSTA plan Subsystem 5s COMMS PLANNER message list Primitive 500ms Servo 50ms AM PLANNER Driver Plan Gaze plan DRIVER PLANNER Velocity Plan RSTA PLANNER gaze plan GAZE PLANNER Stereo Gaze Plan LADAR Gaze Plan VELOCITY PLANNER F Wheels R Wheels F Steer R Steer F Wheel R Wheel Introduction to AI Robotics (MIT Press) F Steer F Steer Chapter 2: The Hierarchical Paradigm 28 2 RCS XUV Example Vehicle Level: AM Plan (A1…A10) Primitive Level: Driver Plan (D1…D10) Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 29 2 t=0.5 Primitive Level: Driver Plan extends to A2 Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 30 2 t=1 s Obstacle Detected Primitive Level: Driver Plan new waypoints Vehicle Level: detects too large a variation Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 31 2 t=1 s Vehicle Level Planner Opt 1 Vehicle Level: new AM Plan Primitive Level: new Driver Plan Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 32 2 t=3 More obstacle is seen… fail upwards again Vehicle Level: new AM Plan Primitive Level: new Driver Plan Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 33 2 t=4.5s Vehicle Level: new AM Plan skip A1, go to A2 Primitive Level: new Driver Plan Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 34 2 t=6 s Vehicle Level: new AM Plan skip old A2 Primitive Level: new Driver Plan Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 35 Exercise: Adapt to Rescue Robots? 2 Section 10m PLANNER vehicle1 vehicle2 Vehicle 1m VEHICLE PLANNER communications plan AM plan RSTA plan Subsystem 5s COMMS PLANNER message list Primitive 500ms Servo 50ms AM PLANNER Driver Plan Gaze plan DRIVER PLANNER Velocity Plan RSTA PLANNER gaze plan GAZE PLANNER Stereo Gaze Plan LADAR Gaze Plan VELOCITY PLANNER F Wheels R Wheels F Steer R Steer F Wheel R Wheel Introduction to AI Robotics (MIT Press) F Steer F Steer Chapter 2: The Hierarchical Paradigm 36 2 Organization -SPA Hierarchical Review • Describe the hierarchical paradigm in terms of the three robot primitives • Describe sensing in the hierarchical paradigm -global Strips -Shakey Rep. Arch. -evaluation -NHC • • • • What is STRIPS? What is the closed world assumption? What are preconditions? What is the frame problem? -RCA Summary • What are two representative architectures? • What is the NHC decomposition? Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm 37