Governing lethal behavior in autonomous robots

Expounding on the results of the author's work with the US Army Research Office, DARPA, the Office of Naval Research, and various defense industry contractors, Governing Lethal Behavior in Autonomous Robots explores how to produce an "artificial conscience" in a new class of robots, humane-oids, which are robots that can potentially perform more ethically than humans in the battlefield. The author examines the philosophical basis, motivation, theory, and design recommendations for the implementation of an ethical control and reasoning system in autonomous robot systems, taking into account the Laws of War and Rules of Engagement.

The book presents robot architectural design recommendations for

Post facto suppression of unethical behavior, Behavioral design that incorporates ethical constraints from the onset, The use of affective functions as an adaptive component in the event of unethical action, and A mechanism that identifies and advises operators regarding their ultimate responsibility for the deployment of autonomous systems.

It also examines why soldiers fail in battle regarding ethical decisions; discusses the opinions of the public, researchers, policymakers, and military personnel on the use of lethality by autonomous systems; provides examples that illustrate autonomous systems' ethical use of force; and includes relevant Laws of War.

Helping ensure that warfare is conducted justly with the advent of autonomous robots, this book shows that the first steps toward creating robots that not only conform to international law but outperform human soldiers in their ethical capacity are within reach in the future. It supplies the motivation, philosophy, formalisms, representational requirements, architectural design criteria, recommendations, and test scenarios to design and construct an autonomous robotic system capable of ethically using lethal force.

Ron Arkin was quoted in a November 2010 New York Times article about robots in the military.

Preface	p. xi
Acknowledgments	p. xix
Chapter 1 Introduction	p. 1
Chapter 2 Trends toward Lethality	p. 7
2.1 Weaponized Unmanned Ground Vehicles	p. 10
2.2 Weaponized Unmanned Aerial Vehicles	p. 21
2.3 Prospects	p. 26
Chapter 3 Human Failings in the Battlefield	p. 29
Chapter 4 Related Philosophical Thought	p. 37
Chapter 5 What People Think: Opinions on Lethal Autonomous Systems	p. 49
5.1 Survey Background	p. 50
5.2 Response	p. 51
5.3 Comparative Results	p. 52
5.4 Discussion	p. 55
Chapter 6 Formalization for Ethical Control	p. 57
6.1 Formal Methods for Describing Behavior	p. 58
6.1.1 Range of Responses: R	p. 58
6.1.2 The Stimulus Domain: S	p. 58
6.1.3 The Behavioral Mapping: ß	p. 60
6.2 Ethical Behavior	p. 62
Chapter 7 Specific Issues for Lethality: What to Represent	p. 69
7.1 What Is Required	p. 70
7.2 Laws of War	p. 71
7.3 Rules of Engagement	p. 81
7.3.1 Standing Rules of Engagement	p. 82
7.3.2 Rules of Engagement (Non-SROE)	p. 84
7.3.3 Rules for the Use of Force	p. 86
7.3.4 ROE for Peace Enforcement Missions	p. 91
Chapter 8 Representational Choices: How to Represent Ethics in a Lethal Robot	p. 93
8.1 Underpinnings	p. 95
8.2 Generalism-Reasoning from Moral Principles	p. 99
8.2.1 Deontic Logic	p. 99
8.2.2 Utilitarian Methods	p. 102
8.2.3 Kantian Rule-Based Methods	p. 103
8.3 Particularism: Case-Based Reasoning	p. 104
8.4 Ethical Decision Making	p. 108
Chapter 9 Architectural Considerations for Governing Lethality	p. 115
9.1 Architectural Requirements	p. 119
Chapter 10 Design Options	p. 125
10.1 Ethical Governor	p. 127
10.2 Ethical Behavioral Control	p. 133
10.3 Ethical Adaptor	p. 138
10.3.1 After-Action Reflection	p. 138
10.3.2 Affective Restriction of Behavior	p. 140
10.4 Responsibility Advisor	p. 143
10.4.1 Command Authorization for a Mission Involving Autonomous Lethal Force	p. 146
10.4.2 Design for Mission Command Authorization	p. 148
10.4.3 The Use of Ethical Overrides	p. 149
10.4.4 Design for Overriding Ethical Control	p. 152
Chapter 11 Example Scenarios for the Ethical Use of Force	p. 155
11.1 Taliban Muster in Cemetery	p. 157
11.2 "Apache Rules the Night"	p. 162
11.3 Korean Demilitarized Zone	p. 167
11.4 Urban Sniper	p. 171
Chapter 12 A Prototype Implementation	p. 177
12.1 Infrastructure	p. 177
12.2 A Prototype Implementation of the Ethical Governor	p. 178
12.2.1 Ethical Constraints	p. 179
12.2.2 Evidential Reasoning	p. 182
12.2.3 Constraint Application	p. 182
12.2.4 Proportionality and Battlefield Carnage	p. 185
12.2.5 Demonstration Scenario Overview	p. 188
12.2.6 Scenario 1-Suppressing Unethical Behavior	p. 190
12.2.7 Scenario 2-Maintaining Ethical Behavior While Minimizing Collateral Damage	p. 192
12.3 Implementing the Responsibility Advisor	p. 196
12.3.1 Establishing Responsibility When Tasking an Autonomous System Capable of Lethal Force	p. 196
12.3.2 Run-Time Responsibility Advising and Operator Overrides	p. 202
12.3.2.1 Continuous Presentation of the Status of the Ethical Governor	p. 203
12.3.2.2 Negative Overrides: Denying Permission to Fire in the Presence of Obligating Constraints	p. 205
12.3.2.3 Positive Overrides: Granting Permission to Fire in the Presence of Forbidding Ethical Constraints	p. 206
12.4 Summary	p. 209
Epilogue	p. 211
References	p. 213
Appendix A Relevant Laws of War	p. 225
Appendix B Acronyms	p. 243
Appendix C Notation	p. 245
Index	p. 247

Available:*

On Order

Summary

Summary

Table of Contents