Safety Intelligence and Legal Machine Language: Do We Need the Three Laws of Robotics?

Weng, Yueh-Hsuan; Chen, Chien‐Hsun; Sun, Ching Cherng

doi:10.5772/6057

Cited by 8 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There has been some initial work toward integrating AGIs with existing legal and social frameworks, such as considering questions of their legal position [31,62,132,174,252,296,297] and moral rights [62,125,175,260,261,291].…”

Section: Integrate With Societymentioning

confidence: 99%

“…Although the three laws are widely known and have inspired numerous imitations, several of Asimovʼs own stories were written to illustrate the fact that the laws contained numerous problems. They have also drawn heavy critique from others [23,75,76,120,180,201,224,282,295,296] and are not considered a viable approach for safe AI. Among their chief shortcomings is the fact that they are too ambiguous to implement and, if defined with complete accuracy, contradict each other in many situations.…”

Section: Top-down Safe Agimentioning

confidence: 99%

“…Legal machine language. Weng et al [296,297] propose a 'legal machine language' which could be used to formally specify actions which the AGI is allowed or disallowed to do. Governments could then enact laws written in legal machine language, allowing them to be programmed into robots.…”

Section: Motivational Weaknessesmentioning

confidence: 99%

See 2 more Smart Citations

Responses to catastrophic AGI risk: a survey

Sotala

Yampolskiy

2014

Phys. Scr.

View full text Add to dashboard Cite

Many researchers have argued that humanity will create artificial general intelligence (AGI) within the next twenty to one hundred years. It has been suggested that AGI may inflict serious damage to human well-being on a global scale ('catastrophic risk'). After summarizing the arguments for why AGI may pose such a risk, we review the fieldʼs proposed responses to AGI risk. We consider societal proposals, proposals for external constraints on AGI behaviors and proposals for creating AGIs that are safe due to their internal design.

show abstract

Section: Integrate With Societymentioning

confidence: 99%

Section: Top-down Safe Agimentioning

confidence: 99%

See 1 more Smart Citation

Responses to catastrophic AGI risk: a survey

Sotala

Yampolskiy

2014

Phys. Scr.

View full text Add to dashboard Cite

show abstract

“…Technical relinquishment or AI appears to be not technically possible Not many argue for a global AI ban as it is unfeasible under current conditions [23] and would likely only help bad actors [24]. One could imagine that global legal regulation could ban the creation of self-improving agents.…”

Section: "No Ai" Solutionsmentioning

confidence: 99%

Global Solutions vs. Local Solutions for the AI Safety Problem

Turchin¹,

Denkenberger

Green

2019

BDCC

View full text Add to dashboard Cite

There are two types of artificial general intelligence (AGI) safety solutions: global and local. Most previously suggested solutions are local: they explain how to align or “box” a specific AI (Artificial Intelligence), but do not explain how to prevent the creation of dangerous AI in other places. Global solutions are those that ensure any AI on Earth is not dangerous. The number of suggested global solutions is much smaller than the number of proposed local solutions. Global solutions can be divided into four groups: 1. No AI: AGI technology is banned or its use is otherwise prevented; 2. One AI: the first superintelligent AI is used to prevent the creation of any others; 3. Net of AIs as AI police: a balance is created between many AIs, so they evolve as a net and can prevent any rogue AI from taking over the world; 4. Humans inside AI: humans are augmented or part of AI. We explore many ideas, both old and new, regarding global solutions for AI safety. They include changing the number of AI teams, different forms of “AI Nanny” (non-self-improving global control AI system able to prevent creation of dangerous AIs), selling AI safety solutions, and sending messages to future AI. Not every local solution scales to a global solution or does it ethically and safely. The choice of the best local solution should include understanding of the ways in which it will be scaled up. Human-AI teams or a superintelligent AI Service as suggested by Drexler may be examples of such ethically scalable local solutions, but the final choice depends on some unknown variables such as the speed of AI progress.

show abstract

“…Asimov's laws presented a simple, comprehensive, and logically organized structure of inference for moral judgment of robots with their users. [6][7][8] However, the application of these laws to specific situations posed certain limitations and contradictions 9,10 ; for instance, in cases wherein a person maliciously attacks or injuriously orders a robot, it cannot protect itself by pushing the person away or denying to follow the order. This study aims to understand and improve Asimov's Three Laws for practical applications, particularly for home service.…”

Section: Introductionmentioning

confidence: 99%

Application of modified Asimov’s laws to the agent of home service robot using state, operator, and result (Soar)

Dang

Jun

Shin

et al. 2018

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

This study aims to interpret and apply Asimov's Three Laws of Robotics to home service robots. An agent is developed herein with the ability to focus its attention on human beings' health, particularly the elderly and the diseased, by delivering food. The agent is developed on a cognitive agent architecture, state, operator, and result (Soar), to enable effective reasoning and decision-making skills. This study deals with basic home care services, such as food delivery and emergency response; therefore, common food care and emergency rules are newly proposed based on the priority values that correspond to a family's circumstances and/or emergency levels. Asimov's Three Laws are modified to aid the home service robot to follow a predetermined order in selecting a food item or recommending an alternative food item suitable for its user's prevailing health condition. Experimental results confirm that reasoning and decision-making of the proposed agent are logically and ethically valid for a home service robot and ensure compliance with both the original and modified Asimov's Three Laws.

show abstract

Safety Intelligence and Legal Machine Language: Do We Need the Three Laws of Robotics?

Cited by 8 publications

References 37 publications

Responses to catastrophic AGI risk: a survey

Responses to catastrophic AGI risk: a survey

Global Solutions vs. Local Solutions for the AI Safety Problem

Application of modified Asimov’s laws to the agent of home service robot using state, operator, and result (Soar)

Contact Info

Product

Resources

About