Presentation is loading. Please wait.

Presentation is loading. Please wait.

2 The Hierarchical Paradigm Describe the Hierarchical Paradigm in terms of the 3 robot primitives and its organization of sensing Name and evaluate one.

Similar presentations


Presentation on theme: "2 The Hierarchical Paradigm Describe the Hierarchical Paradigm in terms of the 3 robot primitives and its organization of sensing Name and evaluate one."— Presentation transcript:

1 2 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 Solve a simple navigation problem using STRIPS (hint: work through Sec. 2.2.2) Understand precondition, closed world assumption, open world, frame problem List two advantages and disadvantages of the Hierarchical Paradigm Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm1 Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary

2 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 Paradigm2

3 2 Organization Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm3 PLANSENSEACT World model: 1.A priori rep 2.Sensed info 3.Cognitive Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary

4 2 Shakey First AI robot Built by SRI (Stanford Research Institute) for DARPA 1967-9 Used Strips as main algorithm for controlling what to do Introduction to AI Robotics (MIT Press)Chapter 2: The Hierarchical Paradigm4 Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary

5 2 Strips: Means-ends analysis Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm5 INITIAL STATE:Tampa, Florida (0,0) GOAL STATE:Stanford, California (1000,200) Difference:1020 miles “Go to Stanford AI Lab” Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary

6 2 Difference Table Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm6 d>=200 milesFLY 100<d<200TRAIN d<=100DRIVE Distance (difference) mode of transportation (OPERATOR) d<1WALK mode=difference_table(INITIAL STATE, GOAL STATE, difference) 1.Look up what to do: FLY 2.Not at SAIL, so repeat 3.Look up what to do: DRIVE Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary

7 2 Preconditions Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm7 d>=200 milesFLY 100<d<200TRAIN d<=100DRIVE (rental) DRIVE (personal car) difference OPERATOR d<1WALK How do I know if I’m at the airport or at home? Now must keep up with the state of the world at airport at home PRECONDITIONS Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary

8 2 Maintaining State of the World: Add and Delete Lists Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm8 d>=200 miles FLY 100<d<2 00 TRAIN d<=100DRIVE (rental) at airport DRIVE (personal) at home distanceOPERATORPRE- CONDITIONS d<1WALK at city Y at airport at city Y at train station ADD-LIST at city X DELETE- LIST Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary

9 2 Class Exercise 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 Paradigm9 d<=200 miles FLY 100<d<2 00 TRAIN d<=100DRIVE (rental) at airport DRIVE (personal) at home distanceOPERATORPRE- CONDITIONS d<1WALK at city Y at airport at city Y at train station ADD-LIST at city X DELETE- LIST Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary

10 2 Strips 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 Paradigm10 Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary

11 2 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 Paradigm11 Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary

12 2 Nested Hierarchical Controller (Meystel) Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm12 Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary

13 2 NHC Planner Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm13 Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary

14 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 Paradigm14

15 2 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 Paradigm15 RCS (Albus)

16 2 Examples of RCS Apps Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm16 Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary

17 2 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 Paradigm17 Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary

18 2 Evaluating NHC & RCS support for modularity: – 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 Paradigm18 Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary

19 2 Advantages & Disadvantages of Hierarchies 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 Paradigm19 Advantage of Hierarchal Paradigm Orders the relationship between Sensing, Planning and Acting

20 2 Advantages & Disadvantages of Hierarchies 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 Paradigm20 Disadvantages of Hierarchal Paradigm

21 2 Nodes are made from Modules Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm21 uff applies rule (transition rules) sensors actions 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 transform into x* G is feedback xd is from “above”

22 2 Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm22 uff applies rule (transition rules) sensors actions if BALL, move toward centroid if NOT BALL, turn clockwise (feedback determines how fast) transform into x* G is feedbackxd is from “above” Nodes are made from Modules

23 2 Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm23 uff applies rule (transition rules) sensors actions if BALL, move toward centroid if NOT BALL, turn clockwise (feedback determines how fast) transform into x* G is feedbackxd is from “above” when to stop? how far is far enough? what about noise/fuzzy ball? … sensor noise, actuator error, rigid models Nodes are made from Modules

24 2 Demo III XUV Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm24 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

25 2 RCS-4 Levels Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm25 7Battalion2-24h 6Platoon5m-2h 5Section1-10m 4Individual Vehicle5-50s 3Subsystem Level200-500ms 2Primitive Level50-500ms 1Servo Level5-50ms

26 2 Each Level has a RCS Node Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm26 Sensory Processing, World Modeling, Behavior Generation, Value Judgment Sensory Processing, World Modeling, Behavior Generation, Value Judgment Engineering of Mind, Albus & Mystel, 2001

27 2 Implementation View: Nodes are Recursive Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm27

28 2 Demo III Control Hierarchy Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm28 PLANNER vehicle1 vehicle2 VEHICLE PLANNER communications plan AM plan RSTA plan AM PLANNER Driver Plan Gaze plan COMMS PLANNER message list RSTA PLANNER gaze plan DRIVER PLANNER Velocity Plan GAZE PLANNER Stereo Gaze Plan LADAR Gaze Plan VELOCITY PLANNER F Wheels R Wheels F Steer R Steer F WheelR WheelF Steer Servo 50ms Primitive 500ms Subsystem 5s Vehicle 1m Section 10m

29 2 RCS XUV Example Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm29 Vehicle Level: AM Plan (A1…A10) Primitive Level: Driver Plan (D1…D10)

30 2 t=0.5 Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm30 Primitive Level: Driver Plan extends to A2

31 2 t=1 s Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm31 Obstacle Detected Primitive Level: Driver Plan new waypoints Vehicle Level: detects too large a variation

32 2 t=1 s Vehicle Level Planner Opt 1 Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm32 Vehicle Level: new AM Plan Primitive Level: new Driver Plan

33 2 t=3 Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm33 More obstacle is seen… fail upwards again Vehicle Level: new AM Plan Primitive Level: new Driver Plan

34 2 t=4.5s Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm34 Vehicle Level: new AM Plan skip A1, go to A2 Primitive Level: new Driver Plan

35 2 t=6 s Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm35 Vehicle Level: new AM Plan skip old A2 Primitive Level: new Driver Plan

36 2 Exercise: Adapt to Rescue Robots? Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm36 PLANNER vehicle1 vehicle2 VEHICLE PLANNER communications plan AM plan RSTA plan AM PLANNER Driver Plan Gaze plan COMMS PLANNER message list RSTA PLANNER gaze plan DRIVER PLANNER Velocity Plan GAZE PLANNER Stereo Gaze Plan LADAR Gaze Plan VELOCITY PLANNER F Wheels R Wheels F Steer R Steer F WheelR WheelF Steer Servo 50ms Primitive 500ms Subsystem 5s Vehicle 1m Section 10m

37 2 Hierarchical Review Describe the hierarchical paradigm in terms of the three robot primitives Describe sensing in the hierarchical paradigm What is STRIPS? What is the closed world assumption? What are preconditions? What is the frame problem? What are two representative architectures? What is the NHC decomposition? Introduction to AI Robotics (MIT Press) Chapter 2: The Hierarchical Paradigm37 Organization -SPA -global Strips -Shakey Rep. Arch. -evaluation -NHC -RCA Summary


Download ppt "2 The Hierarchical Paradigm Describe the Hierarchical Paradigm in terms of the 3 robot primitives and its organization of sensing Name and evaluate one."

Similar presentations


Ads by Google