artificial moral agent (amas) prospects and approaches for building computer systems and robots...

33
Artificial Moral Agent (AMAs) Prospects and Approaches for Building Computer Systems and Robots Capable of Making Moral Decisions Wendell Wallach [email protected] Yale University Institution for Social and Policy Studies Interdisciplinary Center for Bioethics December 10, 2006

Upload: darcy-johns

Post on 01-Jan-2016

217 views

Category:

Documents


0 download

TRANSCRIPT

Artificial Moral Agent (AMAs)Prospects and Approaches for Building Computer

Systems and Robots Capable of Making Moral Decisions

Wendell [email protected]

Yale University Institution for Social and Policy StudiesInterdisciplinary Center for Bioethics

December 10, 2006

A New Field of Inquiry

Machine Morality Machine Ethics

Computational Ethics Artificial Morality

Friendly AI

Implementation of moral decision-making facilities in artificial agents

Necessitated by autonomous systems making choices

Mappingthe Field

Questions• Do we need artificial moral agents

(AMAs)

•When? For what?

• Do we want computers making ethical decisions?

• Whose morality or what morality?

• How can we make ethics computable?

•What role should ethical theory play in defining the control architecture for systems sensitive to moral considerations in their choices and actions?

• Top-down imposition of ethical theory

• Bottom-up building of systems that aim at goals or standards which may or may not be specified in explicit theoretical terms

Top-Down Theories

•Two main contenders

•Utilitarian - Greatest good of the greatest number - “Only compute!”

•Duties (Deontology) - Respect for rational agents - “Consistent Deontic Logic”

Frame ProblemBOTH have a version of

the frame problem -- computation load due

to requirements of:

Psychological knowledge

Knowledge of effects of actions in the world

Estimating sufficiency of

initial information

• Evolution

• Game Theorists and Evolutionary Psychologist

• “Emergent morality” – The emergence of values in evolutionary terms

• AI Engineering -- exploit “self-organizing” feature of evolved systems

• Alife

• Genetic Algorithms

• Evolutionary Robotics

• Development and Learning

• Associative Learning Platforms

• Behavior Based Robotics

• Simulating Moral Development – Piaget, Kohlberg, Gilligan, etc

• Fine Tuning a System

Bottom Up Approaches

Distinction•Humans -- Biochemical,

•Instinctual, Emotion Platform

•Higher Order Faculties Emerged

•Computers -- Logical Platform

•Calculated Morality

• Does the ability of computers to process large quantities of information, and analyze the potential results from many courses of action, suggest that computers will be superior to humans in making judgments? (Allen, 2002)

•Absence of emotions or base motivations (dubious

• Is the absence of a nervous system subject to emotional “highjackings” a moral advantage? (sexual jealousy)

• Base motivations (greed)

Possible AdvantagesPossible Advantages

•Complex Faculty

•Emotions

•Stoicism vs. Moral Intelligence

•Embodiment

•Learning from Experience

•Sociability

•Understanding and Consciousness

•Theory of Mind

Supra-rational Faculties and Social Mechanisms

Role of Emotions in Moral Decision-Making Machines

Both beneficial and dysfunctional

• AMAs can be reasonable without being subject to dysfunctional emotional highjackings

• Will require some affective intelligence

• Ability to recognize emotional states of others

Will humans feel comfortable with machine sensitive to their emotional states?

Appreciation for both the verbal and non-verbal aspects of human communication.

May be necessary for the acceptance by humans of AMAs.

Sociability Sociability

•A robotic systems learning from interaction with its environment and humans, not the mere application of reasoning.

Embodied Intelligence Embodied Intelligence v Moral Reasoningv Moral Reasoning

Consciousness, Theory of Mind

Breaking down complex mental activities or social mechanisms into faculties which are themselves composites of lower level skills

• Igor Alexander –Five Axioms – Consciousness/Machine Consciousness

• Brian Scassellati – Theory of Mind

Reassembly

• Do we have working theories?

Will advances in evolutionary robotics facilitate integration?

•Between AMA’s and humans.

•Training agents to work together in pursuit of a shared goal, e.g. RoboSoccer

•The development of interface standards that will allow agents to interact and cooperate with other classes of artificial entities.

CooperatioCooperationn

Facilitating Trust in Machines

Will artificial agents need to emulate the full array of human faculties to function as adequate moral agents and to instill trust in their actions?

WHAT HAS BEEN ENGINEERED SO FAR

•Not Much

• The Gap Between Possibility or Hype and reality

•DUTY - pro or con •- Asimov’s “three laws of robotics” and machine metaethics – Susan Anderson•- Deontological machine ethics – Tom Powers•- Toward ethical robots via mechanized deontic logic – Arkoudas, Bringsjord & Bello

•UTILITY - pro or con•- There is no ‘I’ in ‘robot’: utilitarians and utilitarian robots – Christopher Grau•- Utilibot: an autonomous robot based on utilitarianism – Christopher Cloos

•CASE-DRIVEN MODELS•- Towards machine ethics: Implementing two theories – Anderson, Anderson & Armen•- How AI can help us to better understand moral cognition – Marcello Guarini•- Lessons in machine ethics from two computational models – Bruce McLaren

•DEMOS•- MedEthEx (Anderson & Anderson)•- Ethical ANNS (Guarini)•- Sirocco (McLaren)

AAAI Machine Ethics Symposium, Fall 2005

•CHALLENGES AND OVERVIEWS•- The nature and importance of machine ethics – Jim Moor•- A robust view of machine ethics – Steve Torrance•- Technological artifacts as moral carriers and mediators – Lorenzo Magnani•- Machine morality: bottom-up and top-down approaches – Allen & Wallach•- What could statistics do for ethics? – Rzepka & Araki•- Ethical machines: the future can heed us – Selmer Bringsjord•- Social and scientific implications of patents in AI – Brian O’Connell•- Thoughts concerning the legal status of a non-biological machine – David Calverly•- Ethical robot as grand challenge – James Gips

AAAI Machine Ethics Symposium

Other Key Players

• “Beyond AI: Creating the Conscience of the Machine” -- Josh Storrs Hall

• “Artificial Morality” -- Peter Danielson

• Friendly AI -- Eliezer Yudkowsky

• Moral Agency for Mindless Machines --Luciano Floridi and J.W. Sanders

• Agents for Ethical Assistance -- Catriona Kennedy

• Thousands of additional researchers

LIDA Cognitive Cycle Stan Franklin & Bernie Baars (GWT)

Competition for Consciousness

Long-term Working Memory

Declarative Memory(Sparse Distributed

Memory)

Transient EpisodicMemory

(Sparse Distributed Memory)

Working MemoryPreconscious Buffers

(Workspace)

Attention Codelets

Sensory-MotorMemory

(Subsumption Net)

External Stimulus

Internal Stimulus

Perceptual Associative Memory

(Slip Net)

Procedural Memory(Scheme Net)

Action Selection

(Behavior Net)

2Percept

3Cue

3Cue

3Local Associations

3Local Associations

3Copy Over

4Look At

4Coalitions

4Winning Coalition

5ConsciousBroadcast6,7

Instantiate, bind,activate schemes

8Action Selected

Attentional Learning

Episodic LearningPerceptual Learning

Procedural Learning

Interpret

Interpret

Pre-afference

Consolidation1Perception

Codelets

ConsciousBroadcast

8

Action &Object

8SMA

(SubsumptionNetwork)

9Action Taken

Effectors

Sensors &PrimitiveFeatureDetectors

8

Object

•Moral Agency

• For Mindless Systems? (Floridi and Sanders)

• Criteria and Tests for Evaluation

• Moral Turing Test? (Allen et al., 2000)

• Rights and Responsibilities

•Controls

• Punishment

• Monitor Development

• Control Reproduction

• Futuristic Fears

• Relinquishment

Related Concerns

•Who is responsible when an AMA fails to meet legal and ethical guidelines?

•What recourse is available for punishing the AMA when it acts immorally or illegally?

• DOES IT MAKE SENSE TO PUNISH

• A ROBOT?

Legal ResponsibilityLegal Responsibility

•Which avenues of research in the development of artificial agents hold potential dangers that we can foresee, and how will we address these dangers?

•Which of these dangers can be managed in the design of the systems and which dangers may require the relinquishment of further research?

•What areas of concern will need regulation and oversight, and how might this be managed in a manner that does not interfere with scientific progress?

DangersDangers

•The capacity for a system to learn and to change its programming in the process of learning without violating basic moral tenets.

•The prospect that self-healing systems will alter their programming and behavior in an undesirable manner.

Self-Adapting and Self-Adapting and Self-Healing Self-Healing

SystemsSystems

•Design strategies for building-in restraints on the behavior of artificial agents.

•Limitations on the reliability and safety of existing design strategies.

Design Strategies for Design Strategies for Restraining AMAsRestraining AMAs

•If there are clear limits in our ability to develop or manage AMAs, then it will be incumbent upon us to recognize those limits so that we can turn our attention away from a false reliance on autonomous systems and toward more human intervention in the decision-making process of computers and robots.

• Eventually we will need AMA’s which maintain the dynamic and flexible morality of bottom-up systems that accommodate diverse inputs, while subjecting the evaluation of choices and actions to top-down principles that represent ideals we strive to meet.

Hybrids

• Professor Colin Allen, Philosophy Dept.,

University of Indiana

• Dr. Iva Smit, E&E Consultants,

Netterden, Netherlands

Thanks To My Thanks To My ColleaguesColleagues