Towards Value-Aware AI

Get in Touch

Value-Aware Artificial Intelligence

Values guide, justify, and explain behaviour. Ensuring AI systems are aligned with human values has been raised as a core problem for AI.
By putting moral considerations at the core of the AI system itself, we contribute to making AI more trustworthy.

Objectives

VALAWAI aims at developing value-aware AI systems; that is, AI systems that are able to understand and abide by a value system and explain its own behaviour or understand the behaviour of others in terms of a value system.

NEUROSCIENCE
Develop quantitative measures of levels of awareness based on neuroscience.

ARTIFICIAL INTELLIGENCE
Implement a general operational model for artificial awareness.

VALUE-AWARE AI TOOLS
Prototype, engineer and release a toolbox for value-aware AI.

Societal Impact

VALAWAI will apply Value-Aware AI to three challenging application domains in domains very much need a moral dimension and adding value-awareness would therefore offer a clear and strong added value for their users.

Given their societal impact, these application domains have a high potential for innovation.

SOCIAL MEDIA
Protect individual users and our society from malicious media content.

SOCIAL ROBOTS
Make social robots more trustworthy.

SOCIAL DECISSION-MAKING
Deal more confidently with moral dilemmas in critical situations.

The Consortium
Partners

VALAWAI is a multidisciplinary project using neuroscience, robotics, computer science, and engineering.