1 / 11

Reasoning

Attention Subsystem. Persistent Plans. Persistent Plans. Persistent Plans. Planner. Plan Execution. 3D Reconstruction. Plan Recognition. Reasoning. Scenes. Episodic Memory.

johnemiller
Download Presentation

Reasoning

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Attention Subsystem Persistent Plans Persistent Plans Persistent Plans Planner Plan Execution 3D Reconstruction PlanRecognition Reasoning Scenes Episodic Memory Scene Based ReasoningCognitive ArchitectureFrank Bergmann, fraber@fraber.deBrian Fenton, brian.fenton@gmail.comhttp://tinycog.sourceforge.net/

  2. Attention Subsystem Persistent Plans Persistent Plans Persistent Plans Planner Plan Execution 3D Reconstruction PlanRecognition Reasoning Scenes Episodic Memory Problems Addressed & Approach Problems Addressed • We propose an integrated architecture for implementing a number of “self-models”. • We provide a model for talking about modalities (auxiliary verbs) without the use of higher-order or modal logics. Approach • Use Thomas Metzinger’s “Self-Model Theory of Subjectivity” as a kind of requirement statement. • Extend/generalize existing knowledge representation and reasoning formalisms to accommodate self-models. Implementation Status • Plays “Towers of Hanoi” • Working on a “Stone age prey/hunter” sandbox • http://tinycog.sourceforge.net/

  3. Physical Planning Social Internal Different Levels of Self-Models • Physical Volume Self-Model “This is the room I’m in, this is my leg.“Identify the 3D volume of the robot representing SBR and model its capabilities • Capabilities Self-Model „I am good at this.“Performance statistics of task decompositions • Planning Self-Model „I usually hit the goal in 30% of all cases.“Performance statistics of plans performed • Intention Self-Model ”I currently try to do this.“Introspection into the goals currently pursued • Goal Self-Model “I would like to be to do this.“Introspection into active “Persistent Goals” • Social Self-Model “Other group members respect me.“Role of self in group activities. • Behavioral Self-Model “I usually react like this.“Episodic Memory recordings of past SBR actions • Emotional Self-Model “I am happy to hear the news.”Introspection into current emotions and historic model of emotions • Historical Self-Model “I used to do a lot of this.”Episodic Memory recorded SBR past actions. • Terminological Self-Model “I know that a penguin is not a bird.”Export the Description Logic TBox into a 2d scene diagram. • Flow of Mental Events Self-Model “I just had an idea how to solve plan X”Short-term memory of “mental events”

  4. Attention Subsystem Persistent Plans Persistent Plans Persistent Plans Planner Plan Execution 3D Reconstruction PlanRecognition Reasoning Scenes Episodic Memory Scene Based Reasoning “Core” Architecture • 20+ subsystems • Explained at http://tinycog.sourceforge.net 3 2 1

  5. Scene Based Reasoning “Core” Architecture Scene Task/Action • We use “Scenes” as a unified representation of internal and world states and as “situations” for the planner. • 3D Scene Graph level – suitable for 3D reconstruction and low-level planning. Reasoning using physics simulation.Reasoning using “diagram reasoning”. • Semantic Network level – “1st Mind”, provides “concepts” and “roles” as an abstraction from object and their attributes.Reasoning using Description Logic reasoning • 2D Graph level – suitable to represent 2D maps, meta-representations of internal data-structure. • “Situation” level – Scenes act as world states and internal states to the planner, adding “dynamics” „Plan“ 1 Goal Start Eat Dinner CleanUp ObtainFood Eat Get pizzafrom Fridge . . . . . . . . . . . . . . . SBR „Core“ Planner 3 Reasoning 2 „Scenes“ 1 „Scene“ Table1 Human1 Type: Table Color: green Position: ... Size: 1 x 1 ... in-front-of Type: Human Gender: malePosition: ... ...

  6. Scene Based Reasoning “Core” Architecture Scene Task/Action • We use “Scenes” as a unified representation of internal and world states and as “situations” for the planner. • Reasoning is performed by several specialized subsystems. • We use Description Logic as a “First Mind” convenient “knowledge assembler“ to classify objects and their attributes into concepts and roles, but not for “higher-level” reasoning. • 2D graph reasoning is a special type of planning. • “Two Minds”: Planning together with the attention, motivational and “persistent goal” subsystems forms a 2nd reasoning system in addition to DL „Plan“ 1 Goal Start Eat Dinner CleanUp ObtainFood Eat 2 Get pizzafrom Fridge . . . . . . . . . . . . . . . SBR „Core“ Planner 3 Reasoning 2 „Scenes“ 1 „Scene“ Table1 Human1 Type: Table Color: green Position: ... Size: 1 x 1 ... in-front-of Type: Human Gender: malePosition: ... ...

  7. Scene Based Reasoning “Core” Architecture Scene Task/Action • We use “Scenes” as a unified representation of internal and world states and as “situations” for the planner. • Reasoning is performed by several specialized subsystems. • The „Planner“ uses Scenes as situations and goals. • “Task decompositions” (HTNs) provide a middle ground between STRIPS style planning and procedural execution and are easy to learn. • Actions may have multiple deterministic outcomes – statistics about actions are collected in the episodic memory. • Physics simulations cover a range of planning capabilities that are difficult to handle using FOL and derivates • A “simulation subsystem” allows for what-if analysis of plans „Plan“ 1 Goal Start Eat Dinner CleanUp ObtainFood Eat 2 Get pizzafrom Fridge . . . . . . . . . . . . . . . SBR „Core“ 3 Planner 3 Reasoning 2 „Scenes“ 1 „Scene“ Table1 Human1 Type: Table Color: green Position: ... Size: 1 x 1 ... in-front-of Type: Human Gender: malePosition: ... ...

  8. Architecture Summary and “Two Minds” • Attention Subsystem controls sensor focus • Persistent Plans for setting plan priorities • Episodic Memory stores plans indexed by content • Plan Recognition allows for 1-shot learning • 20+ subsystems defined at http://tinycog.sourceforge.net Attention Subsystem Persistent Goal Hierarchy Persistent Plans Persistent Plans Planner Plan Execution 3D Reconstruction PlanRecognition Reasoning Scenes Episodic Memory

  9. Self-Models and Self-Referentiality • Physical Volume Self-Model “This is my leg.“Identify the 3D volume of the robot representing SBR and model its capabilities • Capabilities Self-Model „I am good at this.“Performance statistics of task decompositions • Planning Self-Model „I usually hit the goal in 30% of all cases.“Performance statistics of plans performed • Intention Self-Model ”I currently try to do this.“Introspection into the goals currently pursued • Goal Self-Model “I would like to be to do this.“Introspection into active “Persistent Goals” • Social Self-Model “Other group members respect me.“Role of self in group activities. • Behavioral Self-Model “I usually react like this.“Episodic Memory recordings of past SBR actions • Emotional Self-Model “I am happy to hear the news.”Introspection into current emotions and historic model of emotions • Historical Self-Model “I used to do a lot of this.”Episodic Memory recorded SBR past actions. • Terminological Self-Model “I know that a penguin is not a bird.”Export the Description Logic TBox into a 2d scene diagram. • Flow of “Thoughts” Self-Model “I was surprised by this event”Short-term memory (“time-line”) of “mental events”

  10. Goal Start Dinner • hasskin • eats • breathes • moves Animal CleanUp ObtainFood Eat • has wings • can fly • has feathers Bird Get pizzafrom Fridge . . . . . . Fish . . . . . . . . . • has fins • can swim • has gills • can sing • is yellow Canary • !can fly • can swim Penguin Examples of Scenes representing Self-Models: Plan & DL-TBox • Modalities examples: • „My goal is ...“ • „I believe that...“ • Explicit representation of data-structures • No need to use modal or higher order logic • Apply the same reasoning engine as to object-level data

  11. Self-Models and Self-Referentiality Physical • Physical Volume Self-Model “This is my leg.“Identify the 3D volume of the robot representing SBR and model its capabilities • Capabilities Self-Model „I am good at this.“Performance statistics of task decompositions • Planning Self-Model „I usually hit the goal in 30% of all cases.“Performance statistics of plans performed • Intention Self-Model ”I currently try to do this.“Introspection into the goals currently pursued • Goal Self-Model “I would like to be to do this.“Introspection into active “Persistent Goals” • Social Self-Model “Other group members respect me.“Role of self in group activities. • Behavioral Self-Model “I usually react like this.“Episodic Memory recordings of past SBR actions • Emotional Self-Model “I am happy to hear the news.”Introspection into current emotions and historic model of emotions • Historical Self-Model “I used to do a lot of this.”Episodic Memory recorded SBR past actions. • Terminological Self-Model “I know that a penguin is not a bird.”Export the Description Logic TBox into a 2d scene diagram. • Flow of “Thoughts” Self-Model “I was surprised by this event”Short-term memory (“time-line”) of “mental events” Planning Social Internal

More Related