Empowerment As Replacement for the Three Laws of Robotics
This academic paper proposes replacing Asimov's Three Laws of Robotics with the information-theoretic concept of empowerment as a generic heuristic for robot behavior. The authors demonstrate through proof-of-principle scenarios how robot empowerment, human empowerment, and transfer empowerment can operationalize concepts such as self-preservation, safety, and compliance. The framework allows autonomous robots to generate appropriate behaviors without relying on explicit natural language rule comprehension or external reward structures.
Summary and content fields are drawn from the document text and are pending editorial review.
Who issued it
Who it governs
AI and robotics researchers seeking formal, information-theoretic approaches to robot safety and behavioral motivation.
What the document contains
The paper addresses the theoretical foundations of using empowerment as an alternative to Asimov's Three Laws of Robotics, detailing three distinct empowerment perspectives (robot empowerment, human empowerment, and transfer empowerment) supported by simulation scenarios.
The document does not provide legislative text, enforceable standards, or ready-to-use software implementations for commercial robotic systems.
- Natural language rules like Asimov's Three Laws are difficult for modern robots to implement due to semantic ambiguity and lack of natural language understanding.
- Empowerment is an information-theoretic measure quantifying how much control an agent has over its perceptible world.
- Maximizing robot empowerment provides an operational heuristic for robot self-preservation and reliability.
- Maximizing human empowerment from the robot's perspective incentivizes the robot to protect human agency and avoid obstruction.
- Human-to-robot transfer empowerment establishes operational proximity and enables reliable robot reactions to human actions.
· Introduction · Empowerment · Empowerment Perspectives · Discussion
How it scores
Each score is backed by a quote verified against the document text. Editorial review has not yet confirmed them.
Accountability
0/5Clear responsibility for AI outcomes
N/A
screening score · 2026-10-23
Fairness
0/5Non-discrimination and equitable treatment
N/A
screening score · 2026-10-23
Human Dignity
1/5Respect for the inherent worth of persons
Seligman (1975) argues that humans who are forced to be in a state where one’s actions appear to have random outcomes or no outcome variation at all suffer mental health problems.
2. Empowerment
screening score · 2026-10-23
Human Oversight
3/5Humans remain in control of consequential decisions
A robot must obey the orders given to it by human beings, except where such orders would conflict with the First Law.
1. Introduction
screening score · 2026-10-23
Privacy
0/5Protection of personal data and private life
N/A
screening score · 2026-10-23
Transparency
0/5Openness about how AI systems work and are used
N/A
screening score · 2026-10-23
Enforcement
0/5Consequences and compliance mechanisms with real force
N/A
screening score · 2026-10-23