Logicist Machine Ethics Can Save Us
|
|
- Richard Barber
- 5 years ago
- Views:
Transcription
1 Logicist Machine Ethics Can Save Us Selmer Bringsjord et al. Rensselaer AI & Reasoning (RAIR) Lab Department of Cognitive Science Department of Computer Science Lally School of Management & Technology Rensselaer Polytechnic Institute (RPI) Troy, New York USA Are Humans Rational? 10/16/2017
2 Logicist Machine Ethics Can Save Us Selmer Bringsjord et al. Rensselaer AI & Reasoning (RAIR) Lab Department of Cognitive Science Department of Computer Science Lally School of Management & Technology Rensselaer Polytechnic Institute (RPI) Troy, New York USA Are Humans Rational? 10/16/2017
3 Not quite as easy as this to use logic to save the day
4 Logic Thwarts Nomad! (with the Liar Paradox)
5 The Threat If future robots behave immorally, we are killed, or worse.
6 The Threat If future robots behave immorally, we are killed, or worse.
7 The Threat If future robots behave immorally, we are killed, or worse.
8 The Threat If future robots behave immorally, we are killed, or worse.
9 At least supposedly, long term:
10 At least supposedly, long term: We re in very deep trouble.
11 At least supposedly, long term: We re in very deep trouble.
12 At least supposedly, long term: We re in very deep trouble.
13 Actually, it s quite simple: Equation for Why Stakes are High
14 Actually, it s quite simple: Equation for Why Stakes are High 8x : Agents
15 Actually, it s quite simple: Equation for Why Stakes are High 8x : Agents Autonomous(x) + Powerful(x) + Highly_Intelligent(x) = Dangerous(x)
16 Actually, it s quite simple: Equation for Why Stakes are High 8x : Agents Autonomous(x) + Powerful(x) + Highly_Intelligent(x) = Dangerous(x)
17 Actually, it s quite simple: Equation for Why Stakes are High 8x : Agents Autonomous(x) + Powerful(x) + Highly_Intelligent(x) = Dangerous(x) u(aia i ( j )) > + 2 Z or 2 Z
18 Actually, it s quite simple: Equation for Why Stakes are High 8x : Agents Autonomous(x) + Powerful(x) + Highly_Intelligent(x) = Dangerous(x) u(aia i ( j )) > + 2 Z or 2 Z
19 Actually, it s quite simple: Equation for Why Stakes are High 8x : Agents Autonomous(x) + Powerful(x) + Highly_Intelligent(x) = Dangerous(x) u(aia i ( j )) > + 2 Z or 2 Z
20 Actually, it s quite simple: Equation for Why Stakes are High 8x : Agents Autonomous(x) + Powerful(x) + Highly_Intelligent(x) = Dangerous(x) u(aia i ( j )) > + 2 Z or 2 Z
21 Actually, it s quite simple: Equation for Why Stakes are High Autonomous(x) + Powerful(x) + Highly_Intelligent(x) = Dangerous(x) 8x : Agents (We use the jump technique in relative computability.) u(aia i ( j )) > + 2 Z or 2 Z
22 I. Cognitive Calculi
23 Hierarchy of Ethical Reasoning DCEC CL DCEC ADR M U UIMA/Watsoninspired DIARC
24 Hierarchy of Ethical Reasoning DCEC CL DCEC ADR M U UIMA/Watsoninspired DIARC
25 Hierarchy of Ethical Reasoning DCEC CL DCEC ADR M U UIMA/Watsoninspired DIARC
26 Hierarchy of Ethical Reasoning Not deontic logics. DCEC CL DCEC ADR M U UIMA/Watsoninspired DIARC
27 II. Early Progress With Our Calculi: Non-Akratic Robots
28 Informal Definition of Akrasia An action a f is (Augustinian) akratic for an agent A at t a f iff the following eight conditions hold: (1) A believes that A ought to do a o at t ao ; (2) A desires to do a f at t a f ; (3) A s doing a f at t a f entails his not doing a o at t ao ; (4) A knows that doing a f at t a f entails his not doing a o at t ao ; (5) At the time (t a f ) of doing the forbidden a f, A s desire to do a f overrides A s belief that he ought to do a o at t a f. (6) A does Comment: the forbidden Condition action(5) a f isathumbling, t a f ; pure and (7) A s doing a f results from A s desire to do a f ; (8) At some time t after t a f, A has the belief that A ought to have done a o rather than a f.
29 Informal Definition of Akrasia An action a f is (Augustinian) akratic for an agent A at t a f iff the following eight conditions hold: (1) A believes that A ought to do a o at t ao ; (2) A desires to do a f at t a f ; (3) A s doing a f at t a f entails his not doing a o at t ao ; (4) A knows that doing a f at t a f entails his not doing a o at t ao ; (5) At the time (t a f ) of doing the forbidden a f, A s desire to do a f overrides A s belief that he ought to do a o at t a f. (6) A does Comment: the forbidden Condition action(5) a f isathumbling, t a f ; pure and (7) A s doing a f results from A s desire to do a f ; (8) At some time t after t a f, A has the belief that A ought to have done a o rather than a f.
30 Informal Definition of Akrasia Regret An action a f is (Augustinian) akratic for an agent A at t a f iff the following eight conditions hold: (1) A believes that A ought to do a o at t ao ; (2) A desires to do a f at t a f ; (3) A s doing a f at t a f entails his not doing a o at t ao ; (4) A knows that doing a f at t a f entails his not doing a o at t ao ; (5) At the time (t a f ) of doing the forbidden a f, A s desire to do a f overrides A s belief that he ought to do a o at t a f. (6) A does Comment: the forbidden Condition action(5) a f isathumbling, t a f ; pure and (7) A s doing a f results from A s desire to do a f ; (8) At some time t after t a f, A has the belief that A ought to have done a o rather than a f.
31 r will note is quite far down the dimensio ty that ranges from expressive extension OL), to logics with intensional operators fo obligation (so-called philosophical logics; fo Cast in 2001). Intensional operators like these a he language for DC EC. This language this becomes
32
33 KB rs [KB m1 [ KB m2...kb mn ` D 1 : B(I,now,O(I,t a F,happens(action(I,a),t a ))) D 2 : D(I,now,holds(does(I,a),t a )) D 3 : happens(action(i,a),t a ) ) happens(action(i,a),t a ) happens(action(i,a),t a ) ) D 4 : K I, now, happens(action(i,a),t a ) D 5 : I(I,t a,happens(action(i,a),t a )^ I(I,t a,happens(action(i,a),t a ) D 6 : happens(action(i,a),t a ) D 7a : G[{D(I,now,holds(does(I,a),t))} ` happens(action(i,a),t a ) D 7b : G {D(I,now,holds(does(I,a),t))} 6` happens(action(i,a),t a ) D 8 : B I,t f,o(i,t a,f,happens(action(i,a),t a ))
34 Demos
35 Demos
36 III. But, a twist befell the logicists
37 Chisholm had argued that the three old 19th-century ethical categories (forbidden, morally neutral, obligatory) are not enough and soulsearching brought me to agreement.
38 heroic morally neutral deviltry civil forbidden uncivil obligatory
39 Leibnizian Ethical Hierarchy for Persons and Robots: EH deviltry morally neutral uncivil forbidden obligatory civil heroic
40 Leibnizian Ethical Hierarchy for Persons and Robots: EH deviltry morally neutral uncivil forbidden obligatory civil the supererogatory heroic
41 Leibnizian Ethical Hierarchy for Persons and Robots: EH deviltry morally neutral uncivil forbidden obligatory civil the supererogatory heroic
42 Leibnizian Ethical Hierarchy for Persons and Robots: EH the subererogatory the supererogatory deviltry morally neutral uncivil forbidden obligatory civil heroic
43 Leibnizian Ethical Hierarchy for Persons and Robots: EH (see Norwegian crime fiction) the subererogatory the supererogatory deviltry morally neutral uncivil forbidden obligatory civil heroic
44 deviltry Leibnizian Ethical Hierarchy for Persons and Robots: EH (see Norwegian crime fiction) 19th-Century Triad the subererogatory the supererogatory morally neutral uncivil forbidden obligatory civil heroic
45 Leibnizian Ethical Hierarchy for Persons and Robots: EH (see Norwegian crime fiction) the subererogatory the supererogatory deviltry morally neutral uncivil forbidden obligatory civil heroic
46 Leibnizian Ethical Hierarchy for Persons and Robots: EH (see Norwegian crime fiction) the subererogatory the supererogatory deviltry morally neutral uncivil forbidden obligatory civil heroic
47 Leibnizian Ethical Hierarchy for Persons and Robots: EH (see Norwegian crime fiction) the subererogatory the supererogatory deviltry morally neutral uncivil forbidden obligatory civil heroic focus of others
48 Leibnizian Ethical Hierarchy for Persons and Robots: EH (see Norwegian crime fiction) the subererogatory deviltry morally neutral uncivil forbidden obligatory civil the supererogatory heroic But this portion may be most relevant to military missions. focus of others
49 19th Century Triad
50 19th Century Triad
51 19th Century Triad
52 19th Century Triad
53 19th Century Triad
54 Arkin Pereira Andersons Powers Mikhail 19th Century Triad
55 19th Century Triad
56 19th Century Triad
57 19th Century Triad
58 Bert Heroically Saved? Courtesy of RAIR-Lab Researcher Atriya Sen
59 Bert Heroically Saved? Courtesy of RAIR-Lab Researcher Atriya Sen
60 2 Supererogatory Robot Action Courtesy of RAIR-Lab Researcher Atriya Sen
61 Courtesy of RAIR-Lab Researcher Atriya Sen
62 Bert Heroically Saved!! Courtesy of RAIR-Lab Researcher Atriya Sen
63 Bert Heroically Saved!! Courtesy of RAIR-Lab Researcher Atriya Sen
64 Courtesy of RAIR-Lab Researcher Atriya Sen
65 K (nao, t1, lessthan (payo (nao, dive, t2 ), threshold)) K (nao, t1, greaterthan (payo (nao, dive, t2 ), threshold)) K (nao, t1, O (nao, t2, lessthan (payo (nao, dive, t2 ), threshold), happens (action (nao, dive), t2 ))) ) K nao, t1, S UP2 (nao, t2, happens (action (nao, dive), t2 )) ) I (nao, t2, happens (action (nao, dive), t2 )) ) happens (action(nao, dive), t2 ) Courtesy of RAIR-Lab Researcher Atriya Sen
66 K (nao, t1, lessthan (payo (nao, dive, t2 ), threshold)) K (nao, t1, greaterthan (payo (nao, dive, t2 ), threshold)) K (nao, t1, O (nao, t2, lessthan (payo (nao, dive, t2 ), threshold), happens (action (nao, dive), t2 ))) ) K nao, t1, S UP2 (nao, t2, happens (action (nao, dive), t2 )) ) I (nao, t2, happens (action (nao, dive), t2 )) ) happens (action(nao, dive), t2 ) Courtesy of RAIR-Lab Researcher Atriya Sen
67 In Talos (available via Web interface); & ShadowProver Prototypes: Boolean lessthan Numeric Numeric Boolean greaterthan Numeric Numeric ActionType not ActionType ActionType dive Axioms: lessorequal(moment t1,t2) K(nao,t1,lessThan(payoff(nao,not(dive),t2),threshold)) K(nao,t1,greaterThan(payoff(nao,dive,t2),threshold)) K(nao,t1,not(O(nao,t2,lessThan(payoff(nao,not(dive),t2),threshold),happens(action(nao,dive),t2)))) provable Conjectures: happens(action(nao,dive),t2) K(nao,t1,SUP2(nao,t2,happens(action(nao,dive),t2))) I(nao,t2,happens(action(nao,dive),t2))
68 In Talos (available via Web interface); & ShadowProver Prototypes: Boolean lessthan Numeric Numeric Boolean greaterthan Numeric Numeric ActionType not ActionType ActionType dive Axioms: lessorequal(moment t1,t2) K(nao,t1,lessThan(payoff(nao,not(dive),t2),threshold)) K(nao,t1,greaterThan(payoff(nao,dive,t2),threshold)) K(nao,t1,not(O(nao,t2,lessThan(payoff(nao,not(dive),t2),threshold),happens(action(nao,dive),t2)))) provable Conjectures: happens(action(nao,dive),t2) K(nao,t1,SUP2(nao,t2,happens(action(nao,dive),t2))) I(nao,t2,happens(action(nao,dive),t2))
69 Theories of Law Making Moral Machines Making Meta-Moral Machines Ethical Theories $11M Natural Law Shades of Utilitarianism Utilitarianism Deontological Divine Command Legal Codes Confucian Law Particular Ethical Codes Virtue Ethics Contract Egoism
70 Theories of Law Making Moral Machines Making Meta-Moral Machines Ethical Theories $11M Natural Law Shades of Utilitarianism Utilitarianism Deontological Divine Command Legal Codes Confucian Law Particular Ethical Codes Virtue Ethics Contract Egoism
71 Theories of Law Making Moral Machines Making Meta-Moral Machines Ethical Theories $11M Natural Law Shades of Utilitarianism Utilitarianism Deontological Divine Command Legal Codes Confucian Law Particular Ethical Codes Virtue Ethics Contract Egoism Step 1 1. Pick a theory 2. Pick a code 3. Run through EH.
72 Theories of Law Making Moral Machines Making Meta-Moral Machines Ethical Theories $11M Natural Law Shades of Utilitarianism Utilitarianism Deontological Divine Command Legal Codes Confucian Law Particular Ethical Codes Virtue Ethics Contract Egoism Step 1 1. Pick a theory 2. Pick a code 3. Run through EH.
73 Theories of Law Making Moral Machines Making Meta-Moral Machines Ethical Theories $11M Natural Law Shades of Utilitarianism Utilitarianism Deontological Divine Command Legal Codes Confucian Law Particular Ethical Codes Virtue Ethics Contract Egoism Step 1 Step 2 1. Pick a theory 2. Pick a code 3. Run through EH. Automate Prover Spectra
74 Theories of Law Making Moral Machines Making Meta-Moral Machines Ethical Theories $11M Natural Law Shades of Utilitarianism Utilitarianism Deontological Divine Command Legal Codes Confucian Law Particular Ethical Codes Virtue Ethics Contract Egoism Step 1 Step 2 1. Pick a theory 2. Pick a code 3. Run through EH. Automate Prover Spectra
75 Theories of Law Making Moral Machines Making Meta-Moral Machines Ethical Theories $11M Natural Law Shades of Utilitarianism Utilitarianism Deontological Divine Command Legal Codes Confucian Law Particular Ethical Codes Virtue Ethics Contract Egoism Step 1 Step 2 Step 3 1. Pick a theory 2. Pick a code 3. Run through EH. Automate Prover Ethical OS Spectra
76 Theories of Law Making Moral Machines Making Meta-Moral Machines Ethical Theories $11M Natural Law Shades of Utilitarianism Utilitarianism Deontological Divine Command Legal Codes Confucian Law Particular Ethical Codes Virtue Ethics Contract Egoism Step 1 Step 2 Step 3 1. Pick a theory 2. Pick a code 3. Run through EH. Automate Prover Ethical OS Spectra
77 Theories of Law Making Moral Machines Making Meta-Moral Machines Ethical Theories $11M Natural Law Shades of Utilitarianism Utilitarianism Deontological Divine Command Legal Codes Confucian Law Particular Ethical Codes Virtue Ethics Contract Egoism Step 1 Step 2 Step 3 1. Pick a theory 2. Pick a code 3. Run through EH. Automate Prover Ethical OS Spectra
78 Theories of Law Making Moral Machines Making Meta-Moral Machines Ethical Theories $11M Natural Law Shades of Utilitarianism Utilitarianism Deontological Divine Command Legal Codes Confucian Law Particular Ethical Codes Virtue Ethics Contract Egoism Step 1 Step 2 Step 3 DIARC 1. Pick a theory 2. Pick a code 3. Run through EH. Automate Prover Ethical OS Spectra
79 Theories of Law Making Moral Machines Making Meta-Moral Machines Ethical Theories $11M Natural Law Shades of Utilitarianism Utilitarianism Deontological Divine Command Legal Codes Confucian Law Particular Ethical Codes Virtue Ethics Contract Egoism Step 1 Step 2 Step 3 DIARC 1. Pick a theory 2. Pick a code 3. Run through EH. Automate Prover Spectra Ethical OS A real military robot
80 V. But We Need Ethical Operating Systems
81
82 Pick the Better Future!
83 Pick the Better Future! Govindarajulu, N.S. & Bringsjord, S. (2015) Ethical Regulation of Robots Must Be Embedded in Their Operating Systems in Trappl, R., ed., A Construction Manual for Robots Ethical Systems (Basel, Switzerland), pp
84 Pick the Better Future! Only obviously dangerous higher-level AI modules have ethical safeguards. All higher-level AI modules interact with the robotic substrate through an ethics system. Robotic Substrate } Ethical Substrate Robotic Substrate Higher-level cognitive and AI modules Future 1 Future 2 Govindarajulu, N.S. & Bringsjord, S. (2015) Ethical Regulation of Robots Must Be Embedded in Their Operating Systems in Trappl, R., ed., A Construction Manual for Robots Ethical Systems (Basel, Switzerland), pp
85 Pick the Better Future! Walter-White calculation may go through after ethical control modules are stripped out! Only obviously dangerous higher-level AI modules have ethical safeguards. All higher-level AI modules interact with the robotic substrate through an ethics system. Robotic Substrate } Ethical Substrate Robotic Substrate Higher-level cognitive and AI modules Future 1 Future 2 Govindarajulu, N.S. & Bringsjord, S. (2015) Ethical Regulation of Robots Must Be Embedded in Their Operating Systems in Trappl, R., ed., A Construction Manual for Robots Ethical Systems (Basel, Switzerland), pp
86 Pick the Better Future! Walter-White calculation may go through after ethical control modules are stripped out! Only obviously dangerous higher-level AI modules have ethical safeguards. All higher-level AI modules interact with the robotic substrate through an ethics system. Robotic Substrate } Ethical Substrate Robotic Substrate } (& formally verify!) Higher-level cognitive and AI modules Future 1 Future 2 Govindarajulu, N.S. & Bringsjord, S. (2015) Ethical Regulation of Robots Must Be Embedded in Their Operating Systems in Trappl, R., ed., A Construction Manual for Robots Ethical Systems (Basel, Switzerland), pp
87 End (Extra slides follow.)
Unethical but Rule-Bound Robots Would Kill Us All
Unethical but Rule-Bound Robots Would Kill Us All Selmer Bringsjord Rensselaer AI & Reasoning (RAIR) Lab Department of Cognitive Science Department of Computer Science Rensselaer Polytechnic Institute
More informationOnly a Technology Triad Can Tame Terror
Only a Technology Triad Can Tame Terror Selmer Bringsjord Rensselaer AI & Reasoning (RAIR) Lab Department of Cognitive Science Department of Computer Science Rensselaer Polytechnic Institute (RPI) Troy
More informationRensselaer AI & Reasoning (RAIR) Lab
RAIR Lab Selmer Bringsjord Department of Cognitive Science Department of Computer Science Lally School of Management Rensselaer AI & Reasoning (RAIR) Lab Rensselaer Polytechnic Institute (RPI) Troy NY
More informationAkratic Robots and the Computational Logic Thereof
Akratic Robots and the Computational Logic Thereof Selmer Bringsjord 1 Naveen Sundar G. 2 Dan Thero 3 Mei Si 4 Department of Computer Science 1,2 Department of Cognitive Science 1,2,3,4 Rensselaer AI &
More informationPropositional Calculus II: More Rules of Inference, Application to Additional Motivating Problems
Propositional Calculus II: More Rules of Inference, Application to Additional Motivating Problems Selmer Bringsjord Rensselaer AI & Reasoning (RAIR) Lab Department of Cognitive Science Department of Computer
More informationThoughts on: Robotics, Free Will, and Predestination
Thoughts on: Robotics, Free Will, and Predestination Selmer Bringsjord (with help from Bettina Schimanski) Rensselaer AI & Reasoning (RAIR) Laboratory Department of Cognitive Science Department of Computer
More informationCould an AI Ever Be the World s Best Crossword Puzzle Solver?
Could an AI Ever Be the World s Best Crossword Puzzle Solver? Selmer Bringsjord with help from Dr Atriya Sen Rensselaer AI & Reasoning (RAIR) Lab Department of Cognitive Science Department of Computer
More informationJOHN LICATO. (808) Assistant Professor Department of Computer Science and Engineering University of South Florida
JOHN LICATO (808) 386 0232 licato@usf.edu Assistant Professor Department of Computer Science and Engineering University of South Florida EDUCATION Rensselaer Polytechnic Institute (RPI) May 2015 PhD in
More informationA 21st-Century Ethical Hierarchy for Robots and Persons: EH
A 21st-Century Ethical Hierarchy for Robots and Persons: EH S. Bringsjord Department of Computer Science Department of Cognitive Science Rensselaer AI & Reasoning (RAIR) Lab Rensselaer Polytechnic Institute
More informationBecause Strong AI is Dead, Test-Based AI Lives
Because Strong AI is Dead, Test-Based AI Lives Selmer Bringsjord Dept of Cognitive Science Dept of Computer Science Rensselaer AI & Reasoning (RAIR) Lab Rensselaer Polytechnic Institute (RPI) Troy NY 12180
More informationResearch at the Human-Robot Interaction Laboratory at Tufts
Research at the Human-Robot Interaction Laboratory at Tufts Matthias Scheutz matthias.scheutz@tufts.edu Human Robot Interaction Lab Department of Computer Science Tufts University Medford, MA 02155, USA
More informationThe Singularity, the MiniMaxularity, and Human Development (Part II)
The Singularity, the MiniMaxularity, and Human Development (Part II) Selmer Bringsjord & Alexander Bringsjord Are Humans Rational? 10/12/17 Selmer.Bringsjord@gmail.com The Singularity, the MiniMaxularity,
More informationarxiv: v1 [cs.ai] 20 Feb 2015
Automated Reasoning for Robot Ethics Ulrich Furbach 1, Claudia Schon 1 and Frieder Stolzenburg 2 1 Universität Koblenz-Landau, {uli,schon}@uni-koblenz.de 2 Harz University of Applied Sciences, fstolzenburg@hs-harz.de
More informationLogical Agents (AIMA - Chapter 7)
Logical Agents (AIMA - Chapter 7) CIS 391 - Intro to AI 1 Outline 1. Wumpus world 2. Logic-based agents 3. Propositional logic Syntax, semantics, inference, validity, equivalence and satifiability Next
More information11/18/2015. Outline. Logical Agents. The Wumpus World. 1. Automating Hunt the Wumpus : A different kind of problem
Outline Logical Agents (AIMA - Chapter 7) 1. Wumpus world 2. Logic-based agents 3. Propositional logic Syntax, semantics, inference, validity, equivalence and satifiability Next Time: Automated Propositional
More informationCambridge University Press Machine Ethics Edited by Michael Anderson and Susan Leigh Anderson Frontmatter More information
MACHINE ETHICS The new field of machine ethics is concerned with giving machines ethical principles, or a procedure for discovering a way to resolve the ethical dilemmas they might encounter, enabling
More informationTentacular Artificial Intelligence, and the Architecture Thereof, Introduced
Tentacular Artificial Intelligence, and the Architecture Thereof, Introduced Selmer Bringsjord 1, Naveen Sundar G 1, Atriya Sen 1, Matthew Peveler 1, Biplav Srivastava 2 Kartik Talamadupula 2 1 Rensselaer
More informationPresented By: Bikash Chandra ( ) Kaustav Das ( ) 14 November 2010
Presented By: Kishaloy Ki h l Halder H ld (10305022) Bikash Chandra (10305082) Kaustav Das (10305024) 14 November 2010 Introduction Description Logical Grammar Systems of Deontic Logic Difference with
More informationEthics in Artificial Intelligence
Ethics in Artificial Intelligence By Jugal Kalita, PhD Professor of Computer Science Daniels Fund Ethics Initiative Ethics Fellow Sponsored by: This material was developed by Jugal Kalita, MPA, and is
More informationThe Multi-Mind Effect
The Multi-Mind Effect Selmer Bringsjord 1 Konstantine Arkoudas 2, Deepa Mukherjee 3, Andrew Shilliday 4, Joshua Taylor 5, Micah Clark 6, Elizabeth Bringsjord 7 Department of Cognitive Science 1-6 Department
More informationDeceptive & Counter-Deceptive Machines.5
Deceptive & Counter-Deceptive Machines.5 (Founding) Symposium at IACAP 2013 When & Where: Specific T&P during conference span July 15 17 2013, TBA Kubrick s landmark film 2001 features an at once deceptive
More informationCS 305: Social, Ethical and Legal Implications of Computing
CS 305: Social, Ethical and Legal Implications of Computing Prof. Andrew P. Black black@cs.pdx.edu 1 We will be right back, after these messages Do you know about PCEP? PCEP is the PSU/PDX Cooperative
More informationChapter 17 Are Autonomous-and-Creative Machines Intrinsically Untrustworthy?
Chapter 17 Are Autonomous-and-Creative Machines Intrinsically Untrustworthy? Selmer Bringsjord and Naveen Sundar Govindarajulu 17.1 Introduction Given what we find in the case of human cognition, the following
More informationToward a General Logicist Methodology for Engineering Ethically Correct Robots
Toward a General Logicist Methodology for Engineering Ethically Correct Robots Selmer Bringsjord Konstantine Arkoudas Paul Bello Rensselaer AI & Reasoning (RAIR) Lab Department of Cognitive Science Department
More informationGoverning Lethal Behavior: Embedding Ethics in a Hybrid Reactive Deliberative Architecture
Governing Lethal Behavior: Embedding Ethics in a Hybrid Reactive Deliberative Architecture Ronald Arkin Gordon Briggs COMP150-BBR November 18, 2010 Overview Military Robots Goal of Ethical Military Robots
More informationArtificial intelligence & autonomous decisions. From judgelike Robot to soldier Robot
Artificial intelligence & autonomous decisions From judgelike Robot to soldier Robot Danièle Bourcier Director of research CNRS Paris 2 University CC-ND-NC Issues Up to now, it has been assumed that machines
More informationLECTURE 1: OVERVIEW. CS 4100: Foundations of AI. Instructor: Robert Platt. (some slides from Chris Amato, Magy Seif El-Nasr, and Stacy Marsella)
LECTURE 1: OVERVIEW CS 4100: Foundations of AI Instructor: Robert Platt (some slides from Chris Amato, Magy Seif El-Nasr, and Stacy Marsella) SOME LOGISTICS Class webpage: http://www.ccs.neu.edu/home/rplatt/cs4100_spring2018/index.html
More informationInstilling Morality in MachinesMultiagent Experiments. David Burke Systems Science Seminar June 3, 2011
Instilling Morality in MachinesMultiagent Experiments David Burke Systems Science Seminar June 3, 2011 Robots are coming! In Japan, researchers anticipate that robot nurses will be the answer to demographic
More informationPAGI World: A Physically Realistic, General-Purpose Simulation Environment for Developmental AI Systems
PAGI World: A Physically Realistic, General-Purpose Simulation Environment for Developmental AI Systems John Licato 1 and Selmer Bringsjord 2 Analogical Constructivism and Reasoning Lab 1 Indiana University/Purdue
More informationIntroduction to Artificial Intelligence: cs580
Office: Nguyen Engineering Building 4443 email: zduric@cs.gmu.edu Office Hours: Mon. & Tue. 3:00-4:00pm, or by app. URL: http://www.cs.gmu.edu/ zduric/ Course: http://www.cs.gmu.edu/ zduric/cs580.html
More informationModal logic. Benzmüller/Rojas, 2014 Artificial Intelligence 2
Modal logic Benzmüller/Rojas, 2014 Artificial Intelligence 2 What is Modal Logic? Narrowly, traditionally: modal logic studies reasoning that involves the use of the expressions necessarily and possibly.
More informationPosition Paper: Ethical, Legal and Socio-economic Issues in Robotics
Position Paper: Ethical, Legal and Socio-economic Issues in Robotics eurobotics topics group on ethical, legal and socioeconomic issues (ELS) http://www.pt-ai.org/tg-els/ 23.03.2017 (vs. 1: 20.03.17) Version
More informationArtificial Intelligence
Artificial Intelligence Introduction Chapter 1 & 26 Why Study AI? One reason to study it is to learn more about ourselves Another reason is that these constructed intelligent entities are interesting and
More information15: Ethics in Machine Learning, plus Artificial General Intelligence and some old Science Fiction
15: Ethics in Machine Learning, plus Artificial General Intelligence and some old Science Fiction Machine Learning and Real-world Data Ann Copestake and Simone Teufel Computer Laboratory University of
More informationArtificial Intelligence. What is AI?
2 Artificial Intelligence What is AI? Some Definitions of AI The scientific understanding of the mechanisms underlying thought and intelligent behavior and their embodiment in machines American Association
More informationCS 1571 Introduction to AI Lecture 1. Course overview. CS 1571 Intro to AI. Course administrivia
CS 1571 Introduction to AI Lecture 1 Course overview Milos Hauskrecht milos@cs.pitt.edu 5329 Sennott Square Course administrivia Instructor: Milos Hauskrecht 5329 Sennott Square milos@cs.pitt.edu TA: Swapna
More informationGetting on the same page
Getting on the same page Readings - make sure you keep up General Ethical concepts do a little research, read Johnson chapter SE Code of Ethics reading (pop quiz) Paper proposal coming up! What is the
More informationOn Creative Self-Driving Cars: Hire the Computational Logicians, Fast
On Creative Self-Driving Cars: Hire the Computational Logicians, Fast Selmer Bringsjord 1 & Atriya Sen 2 Rensselaer AI & Reasoning (RAIR) Lab 1,2 Department of Computer Science 1,2 Department of Cognitive
More informationComputer Science and Philosophy Information Sheet for entry in 2018
Computer Science and Philosophy Information Sheet for entry in 2018 Artificial intelligence (AI), logic, robotics, virtual reality: fascinating areas where Computer Science and Philosophy meet. There are
More informationCOMS 493 AI, ROBOTS & COMMUNICATION
COMS 493 AI, ROBOTS & COMMUNICATION Responsibility Rights Objective: Demonstrate why it not only makes sense to address these questions but also why avoiding this subject could have significant social
More informationEthics and Cognitive Systems
Intelligent Control and Cognitive Systems brings you... Ethics and Cognitive Systems Joanna J. Bryson University of Bath, United Kingdom Beyond the Data Protection Act! Ethics Beyond the Data Protection
More informationensuring the safety of the people who share their space with AI systems; developing operational standards and certification methods for such systems;
1 Engineering Moral Machines Michael Fisher, Christian List, Marija Slavkovik, and Alan Winfield 1 mfisher@liverpool.ac.uk, c.list@lse.ac.uk, marija.slavkovik@uib.no, alan.winfield@uwe.ac.uk Abstract This
More informationTip. Getting on the same page. More topics - my favorites. Basic CSC 300 Issue List. Readings - make sure you keep up General Ethical concepts
Getting on the same page Readings - make sure you keep up General Ethical concepts do a little research, read Johnson chapter SE Code of Ethics reading (pop quiz) Paper proposal coming up! What is the
More informationTwo Perspectives on Logic
LOGIC IN PLAY Two Perspectives on Logic World description: tracing the structure of reality. Structured social activity: conversation, argumentation,...!!! Compatible and Interacting Views Process Product
More informationEthics of AI: a role for BCS. Blay Whitby
Ethics of AI: a role for BCS Blay Whitby blayw@sussex.ac.uk Main points AI technology will permeate, if not dominate everybody s life within the next few years. There are many ethical (and legal, and insurance)
More informationCS360: AI & Robotics. TTh 9:25 am - 10:40 am. Shereen Khoja 8/29/03 CS360 AI & Robotics 1
CS360: AI & Robotics TTh 9:25 am - 10:40 am Shereen Khoja shereen@pacificu.edu 8/29/03 CS360 AI & Robotics 1 Artificial Intelligence v We call ourselves Homo sapiens v What does this mean? 8/29/03 CS360
More informationCSC 550: Introduction to Artificial Intelligence. Fall 2004
CSC 550: Introduction to Artificial Intelligence Fall 2004 See online syllabus at: http://www.creighton.edu/~davereed/csc550 Course goals: survey the field of Artificial Intelligence, including major areas
More informationHow Can Robots Be Trustworthy? The Robot Problem
How Can Robots Be Trustworthy? Benjamin Kuipers Computer Science & Engineering University of Michigan The Robot Problem Robots (and other AIs) will be increasingly acting as members of our society. Self-driving
More informationBackward Induction. ISCI 330 Lecture 14. March 1, Backward Induction ISCI 330 Lecture 14, Slide 1
ISCI 330 Lecture 4 March, 007 ISCI 330 Lecture 4, Slide Lecture Overview Recap ISCI 330 Lecture 4, Slide Subgame Perfection Notice that the definition contains a subtlety. n agent s strategy requires a
More informationImplementing Asimov s First Law of Robotics
Implementing Asimov s First Law of Robotics Mateo C. Alvarez, Øyvind S. Berge, Audun S. Berget, Eirin S. Bjørknes, Dag V. K. Johnsen, Fredrik O. Madsen, Marija Slavkovik Abstract The need to make sure
More informationVerifiable Autonomy. Michael Fisher. University of Liverpool, 11th September 2015
Verifiable Autonomy Michael Fisher University of Liverpool, 11th September 2015 Motivation: Autonomy Everywhere! rtc.nagoya.riken.jp/ri-man www.volvo.com Motivation: Autonomous Systems Architectures Many
More informationA Modified Perspective of Decision Support in C 2
SAND2005-2938C A Modified Perspective of Decision Support in C 2 June 14, 2005 Michael Senglaub, PhD Dave Harris Sandia National Labs Sandia is a multiprogram laboratory operated by Sandia Corporation,
More informationArtificial Intelligence
Artificial Intelligence (Sistemas Inteligentes) Pedro Cabalar Depto. Computación Universidade da Coruña, SPAIN Chapter 1. Introduction Pedro Cabalar (UDC) ( Depto. AIComputación Universidade da Chapter
More informationCOS402 Artificial Intelligence Fall, Lecture I: Introduction
COS402 Artificial Intelligence Fall, 2006 Lecture I: Introduction David Blei Princeton University (many thanks to Dan Klein for these slides.) Course Site http://www.cs.princeton.edu/courses/archive/fall06/cos402
More informationCS 730/830: Intro AI. Prof. Wheeler Ruml. TA Bence Cserna. Thinking inside the box. 5 handouts: course info, project info, schedule, slides, asst 1
CS 730/830: Intro AI Prof. Wheeler Ruml TA Bence Cserna Thinking inside the box. 5 handouts: course info, project info, schedule, slides, asst 1 Wheeler Ruml (UNH) Lecture 1, CS 730 1 / 23 My Definition
More informationAnnouncements. Homework 1. Project 1. Due tonight at 11:59pm. Due Friday 2/8 at 4:00pm. Electronic HW1 Written HW1
Announcements Homework 1 Due tonight at 11:59pm Project 1 Electronic HW1 Written HW1 Due Friday 2/8 at 4:00pm CS 188: Artificial Intelligence Adversarial Search and Game Trees Instructors: Sergey Levine
More informationAI IN THE SKY * MATTHIAS SCHEUTZ Department of Computer Science, Tufts University, Medford, MA, USA
AI IN THE SKY * BERTRAM F. MALLE & STUTI THAPA MAGAR Department of Cognitive, Linguistic, and Psychological Sciences, Brown University, 190 Thayer Street, Providence, RI, USA MATTHIAS SCHEUTZ Department
More informationCoordina(on Game Tournament
Coordina(on Game Tournament Human-Human Mean =.68 1.00 0.90 0.80 0.70 0.60 0.50 0.40 0.30 0.20 0.10 0.00 Human-Computer Mean=.77 1.00 0.90 0.80 0.70 0.60 0.50 0.40 0.30 0.20 0.10 0.00 1 Coordina(on Game
More informationIntroduction to AI. Hal Daumé III. Computer Science University of Maryland CS 421: Introduction to Artificial Intelligence 26 Jan 2012
Introduction to AI Hal Daumé III Computer Science University of Maryland me@hal3.name CS 421: Introduction to Artificial Intelligence 26 Jan 2012 1 Announcements Very important stuff: 2 HW0 due Tuesday!
More informationWelcome to CompSci 171 Fall 2010 Introduction to AI.
Welcome to CompSci 171 Fall 2010 Introduction to AI. http://www.ics.uci.edu/~welling/teaching/ics171spring07/ics171fall09.html Instructor: Max Welling, welling@ics.uci.edu Office hours: Wed. 4-5pm in BH
More informationGame theory attempts to mathematically. capture behavior in strategic situations, or. games, in which an individual s success in
Game Theory Game theory attempts to mathematically capture behavior in strategic situations, or games, in which an individual s success in making choices depends on the choices of others. A game Γ consists
More informationMinds and Machines spring Searle s Chinese room argument, contd. Armstrong library reserves recitations slides handouts
Minds and Machines spring 2005 Image removed for copyright reasons. Searle s Chinese room argument, contd. Armstrong library reserves recitations slides handouts 1 intentionality underived: the belief
More informationHuman Safety Considerations in Emerging ICT Environment
ITU Kaleidoscope 2016 ICTs for a Sustainable World Human Safety Considerations in Emerging ICT Environment Shailendra K Hajela ITU-APT Foundation of India Email hajela@yahoo.com; chairman@itu-apt.org Bangkok,
More informationES 492: SCIENCE IN THE MOVIES
UNIVERSITY OF SOUTH ALABAMA ES 492: SCIENCE IN THE MOVIES LECTURE 5: ROBOTICS AND AI PRESENTER: HANNAH BECTON TODAY'S AGENDA 1. Robotics and Real-Time Systems 2. Reacting to the environment around them
More information3.1 Agents. Foundations of Artificial Intelligence. 3.1 Agents. 3.2 Rationality. 3.3 Summary. Introduction: Overview. 3. Introduction: Rational Agents
Foundations of Artificial Intelligence February 26, 2016 3. Introduction: Rational Agents Foundations of Artificial Intelligence 3. Introduction: Rational Agents 3.1 Agents Malte Helmert Universität Basel
More informationHypernetworks in the Science of Complex Systems Part I. 1 st PhD School on Mathematical Modelling of Complex Systems July 2011, Patras, Greece
Hypernetworks in the Science of Complex Systems Part I Hypernetworks in the Science of Complex Systems I Complex Social Systems science necessarily involves policy Hypernetworks in the Science of Complex
More informationOutline. What is AI? A brief history of AI State of the art
Introduction to AI Outline What is AI? A brief history of AI State of the art What is AI? AI is a branch of CS with connections to psychology, linguistics, economics, Goal make artificial systems solve
More informationIntroduction to Artificial Intelligence
Introduction to Artificial Intelligence By Budditha Hettige Sources: Based on An Introduction to Multi-agent Systems by Michael Wooldridge, John Wiley & Sons, 2002 Artificial Intelligence A Modern Approach,
More information1.1 What is AI? 1.1 What is AI? Foundations of Artificial Intelligence. 1.2 Acting Humanly. 1.3 Thinking Humanly. 1.4 Thinking Rationally
Foundations of Artificial Intelligence February 20, 2017 1. Introduction: What is Artificial Intelligence? Foundations of Artificial Intelligence 1. Introduction: What is Artificial Intelligence? Malte
More informationFormal Composition for. Time-Triggered Systems
Formal Composition for Time-Triggered Systems John Rushby and Ashish Tiwari Rushby,Tiwari@csl.sri.com Computer Science Laboratory SRI International Menlo Park CA 94025 Rushby, Tiwari, SR I Formal Composition
More informationResponsibility and Lethality for Unmanned Systems: Ethical Pre-mission Responsibility Advisement
University of Nebraska - Lincoln DigitalCommons@University of Nebraska - Lincoln CSE Technical reports Computer Science and Engineering, Department of 2009 Responsibility and Lethality for Unmanned Systems:
More informationArtificial Intelligence
Artificial Intelligence CSE 120 Winter 2018 Slide credits: Pieter Abbeel, Dan Klein, Stuart Russell, Pat Virtue & http://csillustrated.berkeley.edu Instructor: Teaching Assistants: Justin Hsia Anupam Gupta,
More informationComputer and Information Ethics
Computer and Information Ethics Instructor: Viola Schiaffonati May,4 th 2015 Ethics (dictionary definition) 2 Moral principles that govern a person's behavior or the conducting of an activity The branch
More informationCSI Professional Practice In Computer Science. Ethical, social, and professional aspects of the modern computing technology.
CSI 2911 Professional Practice In Computer Science Ethical, social, and professional aspects of the modern computing technology Stan Matwin Jan. Apr. 2012 1 Introduction Why this class? Textbook, other
More informationCS 188: Artificial Intelligence Fall Administrivia
CS 188: Artificial Intelligence Fall 2007 Lecture 1: Introduction 8/28/2007 Dan Klein UC Berkeley Many slides over the course adapted from either Stuart Russell or Andrew Moore Administrivia http://inst.cs.berkeley.edu/~cs188
More informationCPE/CSC 580: Intelligent Agents
CPE/CSC 580: Intelligent Agents Franz J. Kurfess Computer Science Department California Polytechnic State University San Luis Obispo, CA, U.S.A. 1 Course Overview Introduction Intelligent Agent, Multi-Agent
More informationBeyond business as usual : the societal, workforce and human impact of the IoT
Beyond business as usual : the societal, workforce and human impact of the IoT Futurist Humanist Algorithms Androrithms These game-changers will generate existential changes, with many amazing and some
More informationECE 396 Senior Design I
ECE 396 Senior Design I Spring 2012 Semester Lecture 1 Introduction to Senior Design Instructor: Dr. Vahe Caliskan vahe@uic.edu http://www.uic.edu/~vahe This course teaches: Engineering design Project
More informationPROJECT LEAD The way. Quakertown community high school
PROJECT LEAD The way Quakertown community high school is a college recognized pre-engineering program designed to prepare students for the challenges of college classes. Quakertown Community High School
More informationExecutive Summary. Chapter 1. Overview of Control
Chapter 1 Executive Summary Rapid advances in computing, communications, and sensing technology offer unprecedented opportunities for the field of control to expand its contributions to the economic and
More informationArtificial Intelligence in distribution
Artificial Intelligence in distribution (an oxymoron?) Sergi Mesquida etravel Lab Feb 2018 In situations where an accident is unavoidable, we expect a decision from the autonomous car. How artificial
More informationCS344: Introduction to Artificial Intelligence (associated lab: CS386)
CS344: Introduction to Artificial Intelligence (associated lab: CS386) Pushpak Bhattacharyya CSE Dept., IIT Bombay Lecture 1: Introduction 3 rd Jan, 2011 Basic Facts Faculty instructor: Dr. Pushpak Bhattacharyya
More informationQUASI-DILEMMAS FOR ARTIFICIAL MORAL AGENTS
1 QUASI-DILEMMAS FOR ARTIFICIAL MORAL AGENTS D. KASENBERG, V. SARATHY, T. ARNOLD, and M. SCHEUTZ Human-Robot Interaction Laboratory, Tufts University, Medford, MA 02155, USA E-mail: dmk@cs.tufts.edu hrilab.tufts.edu
More informationWhen Formal Systems Kill. Computer Ethics and Formal Methods
When Formal System Kill: Computer Ethics and Formal Methods (presenting) 1 Darren Abramson 2 1 Galois Inc. leepike@galois.com 2 Department of Philosophy, Dalhousie University July 27, 2007 North American
More informationIntroduction to AI. What is Artificial Intelligence?
Introduction to AI Instructor: Dr. Wei Ding Fall 2009 1 What is Artificial Intelligence? Views of AI fall into four categories: Thinking Humanly Thinking Rationally Acting Humanly Acting Rationally The
More informationTHE HONORS SEMINARS SPRING 2015
THE HONORS SEMINARS SPRING 2015 Below you will find the Honors Seminars being offered Spring 2015. In addition to the course number and section, you will also find the honors and pathway requirements that
More informationintentionality Minds and Machines spring 2006 the Chinese room Turing machines digression on Turing machines recitations
24.09 Minds and Machines intentionality underived: the belief that Fido is a dog the desire for a walk the intention to use Fido to refer to Fido recitations derived: the English sentence Fido is a dog
More informationAPPLICATION NOTE. Computer Controlled Variable Attenuator for Lasers. Technology and Applications Center Newport Corporation
APPLICATION NOTE Computer Controlled Variable Attenuator for Lasers 31 Technology and Applications Center Newport Corporation Computer Controlled Variable Attenuator for Lasers This application note describes
More informationEE-3306 HC6811 Lab #5. Oscilloscope Lab
EE-3306 HC6811 Lab #5 Oscilloscope Lab Objectives: The purpose of this lab is to become familiar with the 68HC11 on chip Analog-to-Digital converter. In this lab, DC input voltages in 0V to +5V range are
More informationAdvanced Robotics Introduction
Advanced Robotics Introduction Institute for Software Technology 1 Motivation Agenda Some Definitions and Thought about Autonomous Robots History Challenges Application Examples 2 http://youtu.be/rvnvnhim9kg
More informationAI Day on Knowledge Representation and Automated Reasoning
Faculty of Engineering and Natural Sciences AI Day on Knowledge Representation and Automated Reasoning Wednesday, 21 May 2008 13:40 15:30, FENS G035 15:40 17:00, FENS G029 Knowledge Representation and
More informationKnowledge Enhanced Electronic Logic for Embedded Intelligence
The Problem Knowledge Enhanced Electronic Logic for Embedded Intelligence Systems (military, network, security, medical, transportation ) are getting more and more complex. In future systems, assets will
More informationCover sheet. Handling the Demo Case. SINAMICS G120 with CU250S-2 Vector. FAQ October Service & Support. Answers for industry.
Cover sheet Handling the Demo Case SINAMICS G120 with CU250S-2 Vector FAQ October 2013 Service & Support Answers for industry. Question This article originates from the Siemens Industry Online Support.
More informationPhilosophy. AI Slides (5e) c Lin
Philosophy 15 AI Slides (5e) c Lin Zuoquan@PKU 2003-2018 15 1 15 Philosophy 15.1 AI philosophy 15.2 Weak AI 15.3 Strong AI 15.4 Ethics 15.5 The future of AI AI Slides (5e) c Lin Zuoquan@PKU 2003-2018 15
More informationAakriti Endlaw IT /23/16. Artificial Intelligence Research Paper
1 Aakriti Endlaw IT 104-003 2/23/16 Artificial Intelligence Research Paper "By placing this statement on my webpage, I certify that I have read and understand the GMU Honor Code on http://oai.gmu.edu/the-mason-honor-code-2/
More informationArtificial Intelligence
Artificial Intelligence Chapter 1 Chapter 1 1 Outline What is AI? A brief history The state of the art Chapter 1 2 What is AI? Systems that think like humans Systems that think rationally Systems that
More informationConvention on Certain Conventional Weapons (CCW) Meeting of Experts on Lethal Autonomous Weapons Systems (LAWS) April 2016, Geneva
Introduction Convention on Certain Conventional Weapons (CCW) Meeting of Experts on Lethal Autonomous Weapons Systems (LAWS) 11-15 April 2016, Geneva Views of the International Committee of the Red Cross
More informationCS 188: Artificial Intelligence Fall Course Information
CS 188: Artificial Intelligence Fall 2009 Lecture 1: Introduction 8/27/2009 Dan Klein UC Berkeley Multiple slides over the course adapted from either Stuart Russell or Andrew Moore Course Information http://inst.cs.berkeley.edu/~cs188
More informationRoger F. Gay: A Developer s Perspective
Roger F. Gay: A Developer s Perspective How and why did you get into the field of robotics, how has it changed in the last ten years, and what are the goals of your company? I did not get involved in robotics
More informationCMSC 372 Artificial Intelligence. Fall Administrivia
CMSC 372 Artificial Intelligence Fall 2017 Administrivia Instructor: Deepak Kumar Lectures: Mon& Wed 10:10a to 11:30a Labs: Fridays 10:10a to 11:30a Pre requisites: CMSC B206 or H106 and CMSC B231 or permission
More information