Agent-Oriented Techniques for Programming Robots Hans-Dieter Burkhard Humboldt University Berlin.

Agent-Oriented Techniques for Programming Robots

Hans-Dieter BurkhardHumboldt University Berlin

H.D.Burkhard, HU BerlinAOT for Programming Robots, Durres, Sept. 10, 2008 2

What is an Agent?

Someone who acts autonomously on behalf of others

• Sales agent• Insurance agent• Undercover agent• .....

Software Agents

• Assistance Systems• Search engines• ChatterBots• …

Open Systems

Definition (Hewitt)

• Continuous availability• Extensibility • Decentralized control • Asynchronous work• Inconsistent information • Arm length relationships

Consider: P2P

Agents arrived with open systems

What is an Agent?

A program that acts autonomously on behalf of its user

Further Attributes:Intelligent, social, reactive, proactive, adaptive, …

An agent is a long running program, where the work can be meaningfully described as autonomous completion of orders or goals while interacting with the environment.

AI as research on intelligent agents.

(cf. Textbook Russell/Norvig: Artificial Intelligence)

Agents (Autonomous Systems) in Real World

• Natural language understanding• Image interpretation• Driver assistance systems• Traffic control • Space discovery• Autonomous robots:

– Service robots– Rescue robots– Entertainment robots– Industrial robots– Agricultural robots– …

Autonomous Systems in Real World

Robot soccer as testbed

(How to build and program soccer robots?)

Annual world championships and conference

Long term goal: Play like FIFA champion in 2050

Robot “Vision” from Team Osaka

Chess vs. Soccer

Chess:• Static• 3 Minutes per move• Single action• Single player• Information:

• reliable• complete

1997: Deep Blue wins against human champion Kasparov

Soccer:• Dynamic• Milliseconds• Sequences of actions• Team• Information:

• unreliable• incomplete

Robot“Nao” from Aldebaran

RoboCup

Melbourne 2000 Bremen 2006

Service Robots

Alternatives:

- from the refrigerator

- from the cellar

- from the neighbor

- from the shop

- from the internet

Which alternative to choose?

What else is needed (glass, …)?

Willie, bring me a beer

Robot Needs a World Model

Facts about the world– maps, positions of objects, descriptions, …

Methods for processing sensory inputs– language processing, image processing

Methods for integrating sensory data– new world model from old model and new sensory data

Memory of environment:Part of state in the program

there was a beer in the refrigerator

World Model

Problems:

Environment is only partially observable

Observations are insecure and noisy

Scene interpretation with Bayesian methods, e.g. Probability to be at location s given an observation z: P(s|z) = P(z|s)·P(s) / P(z)

World Model

World model need not be true knowledge,

only belief of the agent.Someone took the beer from

the refrigerator!

Plans may fail.Need methods for revision.

Memory of Commitments

Tasks/Goals: Desired world states

Plans (Sequence of actions)

Rationality: Agents should only pursue

goals/plans that can be achieved

Why did I go to the refrigerator

Commitments:Part of state in the program

Goal Oriented Agents

Deliberation: Select goal to achieve

e.g. by calculating utilities

Means-ends reasoning: Planning method

e.g. by search in the action space

Rationality. Needs measures of success/quality/benefits.

“Bounded rationality”:Success w.r.t. to available resources (information, time, …)

Utility Estimations

Different options oAchievable by different plans pWith different results r

Value of result r : v(r)Probability for achieving r using plan p: (r | p) Utility of plan p (expectation) : u(p) = r result of p (r | p) · v(r)Utility of option o: u(o) = Max{ u(p) | p plan for o }

Decision process (used for simulated soccer player ATH98):Estimate utilities for options oSelect best option o as goal gBuild plan p for g

Rationality (Realism) Goals must be feasible

Selection process:

1. Rough estimation (utilities)

2. In case of error in means-ends reasoning (planning)

Revision of goal selection

Refinement of GoalsRefinement as iterated decision-process:

Long term goal intermediate goals ...

intermediate goals actions

Analogy: Stack of procedure calls

Least commitment: Specification only as far as necessary.

Maintaining Multiple Goals: BDI-Approach

Belief (world model)

Desire (desirable future world states)

Intentions (world states to be achieved)

Desires may be in conflict

Intentions must not be in conflict (rationality)

Mental states based on models of human acting (especially w.r.t. bounded rationality)

M.E. Bratman: Intentions, Plans, and Practical Reason, Harvard University Press, Massachusetts, 1987.

Adaptation vs. Stability

Conflicts between old intentions

and potential new intentions (desires)

Adaptation: select always best intentions

Stability: continue old intentions

Advantages of stability:

Reliability (important for cooperation)

Reduce overhead for changes

Avoid oscillations

Disadvantages of stability:

Stick too long on unsatisfactory behavior (fanatism)

There is a beeron the table!

BDI: Screen of Admissibility

Bratman’s solution

for conflicts between old and potential new intentions:

Old intentions restrict admissibility of new intentions,

i.e. set a filter for

- additional intentions- for refinement of intentions

Efficiency:

Reduce repeated evaluation of adopted intentions.

Bounded Rationality

BDI Agents

BDI architectures widely used

Implementation in different variations

Often only in simplified manner

desire = goal

intention = plan

without parallel intentions

Putting Together: Sense-think-act Cycle

Logical ordering of intern processing of the agent

1. Sense („input“) + perception (interpretation, world model)

2. Think (“decision”: evaluation, planning)

3. Act („output“)

thinkact

Sense-think-act Cycle

Synchronisation (sequential)

thinkact

output

Synchronisation (concurrent)

thinkact

output

Synchronisation problems

thinkact

output

?For complicated deliberation processes

Different Deliberation Times

Layered architectures with different deliberation cycles, e.g.- Immediate reactions (avoid obstacles)- Short term planning- Long term planning

AIBO: 30 images per second125 motor commands per second

Structures: Layered Architectures

Synchronization

Conflicts

Concurrency

Layer n

Layer 2

Layer 1

. . . . . .

AgentEnvironment

Layered Architectures with Mediator

Layer n

Layer 2

Layer 1

. . . . . .

AgentEnvironment

Mediator

1-Pass-Architecture

Layer n

Layer 2

Layer 1

. . . . . .

AgentEnvironment

2-Pass-Architecture

Layer n

Layer 2

Layer 1

. . . . . .

AgentEnvironment

How to Deal with Dynamic World

Changing situations

Changing expectations

Unexpected situations (e.g. obstacles)

Changing plans

Conflict handling by BDI-approach

Least Commitment: Deliberate as far as necessary

Double pass architecture (DPA)

Plans may fail.Need methods for revision.

Option Hierarchies

Servebeer

Get bottle

Get glass

Open bottle

Fill glass

Bring Glass

fromRefr.

fromShop

Go toRefr.

OpenRefr.

TakeBottle

GetMoney

GotoShop

BuyBottle

Gohome

“And-branches”- all suboptions have to be achieved

“Or-branches” (Alternatives)- one suboption has to be achieved

. . . . . .

. . . . . . . . . . . .

. . .. . . . . .. . . . . . . . .

. . . . . . . . .

Intention Tree

Servebeer

Get bottle

Get glass

Open bottle

Fill glass

Bring Glass

fromRefr.

fromShop

Go toRefr.

OpenRefr.

TakeBottle

GetMoney

GotoShop

BuyBottle

Gohome

Options may be in

different states, e.g.

- intended

- active

- done

. . . . . . . . .

. . . . . .

. . . . . . . . .

. . . . . .

Intention Tree

Servebeer

Get bottle

Get glass

Open bottle

Fill glass

Bring Glass

fromRefr.

Go toRefr.

OpenRefr.

TakeBottle

Options may be in

- intended

- active

- done. . . . . .

. . . . . .

Activation Path

Servebeer

Get bottle

Get glass

Open bottle

Fill glass

Bring Glass

fromRefr.

Go toRefr.

OpenRefr.

TakeBottle

Options may be in

- intended

- active

- done

Part of intention tree

. . . . . .

Plan Fails

Servebeer

Get bottle

Get glass

Open bottle

Fill glass

Bring Glass

fromRefr.

Go toRefr.

OpenRefr.

TakeBottle

Need for re-deliberation:

Look for alternativesNo Beer inside

Repair: Intention Tree

Servebeer

Get bottle

Get glass

Open bottle

Fill glass

Bring Glass

fromRefr.

fromShop

Go toRefr.

OpenRefr.

TakeBottle

GetMoney

GotoShop

BuyBottle

Gohome

Re-deliberation

not by chronological

backtracking

. . . . . .

. . . . . . . . .

. . . . . .

. . . . . . . . .

Double Pass Architecture (DPA)

2 Passes:- Deliberation determines intention tree

modification if necessary (re-deliberation)

- Executor works over intention tree

maintains activity pass (top-down processing)

controls actuators

Advantages over stack oriented approaches:

Procedure stack has access only to last recent call

Implementations: XABSL, DPA

Still: Classical Approach (“Dualism”)

Robot = Agent (Brain) augmented by Sensors + Actuators

EnvironmentS

Agent(program)

Input Output

Limitations for Complex Actuators

Vehicles have simpler actuation than legged robots

Vehicles:• Accelerate• Drive• Turn• Stop

Legged robots:• Coordination of limbs• Complex kinematics• Stability maintenance (even in stop state)

Machine LearningUse „trial and error“.

•Evolutionary algorithms•Reinforcement learning•Case based reasoning•Neural networks

http://www.robocup.de/AT-Humboldt/simloid-evo.shtml?de

Proprioception: Feeling the own Body

Biologically Inspired Robotics

Emergent behavior using situatedness in physical world

Intelligence emerges by “clever connections”

New insights for Artificial Intelligence:Intelligence needs a body for experiencing the real world.

Many sensors

Local processing

Coupling with actuators

Neural Networks

Acceleration Sensors at our RobotsAcceleration Sensors at our Robots

Accelboards: Accelboards: • real time (10ms cycle)• C/Assembler program• local processing

Recent Experiments

Local control by Recurrent Neural NetworkNetworks developed by evolution

See you at RoboCup 2009 in Graz!

Thank you!

Agent-Oriented Techniques for Programming Robots Hans-Dieter Burkhard Humboldt University Berlin.

Documents

Transcript of Agent-Oriented Techniques for Programming Robots Hans-Dieter Burkhard Humboldt University Berlin.

The New Worldview of the Physicist Burkhard Heimheim-theory.com › wp-content › uploads › 2016 › 03 › I-v...Burkhard Heim's exceptional talents Burkhard Heim was born the

Instituto Humboldt

Humboldt, Travels

Burkhard Heim Mass Formula

Burkhard Martens - Thermal Flying

Humboldt Geographic

Humboldt River Chronology - Nevadawater.nv.gov/mapping/chronologies/humboldt/hrc-pt2.pdfupper reaches of the Humboldt River Basin in the Ruby ... and also submerged the Humboldt River

Lauren Burkhard

Burkhard Schmidt for the LHCb Collaboration

Humboldt kosmos

Burkhard Rost (Columbia New York) Evolution teaches to predict protein structure and function Burkhard Rost CUBIC Columbia University rost@columbia.edu.

Dieter rams

Dieter Kirschke

D-Burkhard Korn - SLWeiss Per Due Liuti

1 How to get the best paper award Hans-Dieter Burkhard Humboldt University Berlin.

Emis prof burkhard 2010

Burkhard Tönshoff, MD, PhD University Children’s Hospital ...pochka.org/files/conference/2016/Burkhard Toenshoff... · Human papilloma virus (HPV) in immunocompromised patients

Intelligent Techniques for Data Integration and Decision Support in the Medical Domain Mirjana Ivanović, Hans-Dieter Burkhard.

2. Introduction to Modelling and Animation · © 2007 Burkhard Wuensche burkhard Slide 2© 2008 Burkhard Wuensche burkhard Slide 2

Humboldt issuu