Counterfactual Assessment and Valuation for Awareness Architecture
The CAVAA project aims to develop a computational architecture for awareness in biological and technological systems, enhancing user experience through explainability and adaptability in various applications.
Projectdetails
Introduction
The Counterfactual Assessment and Valuation for Awareness Architecture (CAVAA) project proposes that awareness serves survival in a world governed by hidden states. This awareness is crucial for dealing with the invisible, from unexplored environments to social interactions that depend on the internal states of agents and moral norms.
Concept of Awareness
Awareness reflects a virtual world, a hybrid of perceptual evidence, memory states, and inferred unobservables, extended in space and time. The CAVAA project aims to realize a theory of awareness instantiated as an integrated computational architecture and its components to explain awareness in biological systems and engineer it in technological ones.
Computational Components
The project will realize underlying computational components of:
- Perception
- Memory
- Virtualization
- Simulation
- Integration
These components will be embodied in robots and artificial agents, validated across a range of use cases involving the interaction between multiple humans and artificial agents. This will be done using accepted measures and behavioral correlates of awareness.
Use Cases
Use cases will address:
- Robot foraging
- Social robotics
- Computer game benchmarks
- Human-generated decision trees in a health coach
These benchmarks will focus on resolving trade-offs, such as between search efficiency and robustness, and assess the acceptance of human users of aware technology.
Ethics Framework
CAVAA's awareness engineering is accompanied by an ethics framework towards human users and aware artifacts in the broader spectrum of trustworthy AI. This framework considers:
- Shared ontologies
- Intention complementarity
- Behavioral matching
- Empathy
- Relevance of outcomes
- Reciprocity
- Counterfactuals and projections towards new future scenarios
- Prediction of the impact of choices
User Experience
CAVAA will deliver a better user experience because of its explainability, adaptability, and legibility. The integrated framework redefines how we look at the relationship between humans, other species, and smart technologies because it makes the invisible visible.
Financiële details & Tijdlijn
Financiële details
Subsidiebedrag | € 3.132.460 |
Totale projectbegroting | € 3.132.460 |
Tijdlijn
Startdatum | 1-10-2022 |
Einddatum | 30-9-2026 |
Subsidiejaar | 2022 |
Partners & Locaties
Projectpartners
- STICHTING RADBOUD UNIVERSITEITpenvoerder
- ETHNIKO KENTRO EREVNAS KAI TECHNOLOGIKIS ANAPTYXIS
- TECHNISCHE UNIVERSITAET CHEMNITZ
- SORBONNE UNIVERSITE
- EODYNE SYSTEMS SL
- ROBOTNIK AUTOMATION SL
- UPPSALA UNIVERSITET
- TP21 GMBH
- CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE CNRS
- THE UNIVERSITY OF SHEFFIELD
- THE CHANCELLOR, MASTERS AND SCHOLARS OF THE UNIVERSITY OF OXFORD
Land(en)
Vergelijkbare projecten binnen EIC Pathfinder
Project | Regeling | Bedrag | Jaar | Actie |
---|---|---|---|---|
Value-Aware Artificial IntelligenceThe VALAWAI project aims to develop a toolbox for Value-Aware AI that integrates moral consciousness to enhance ethical decision-making in social media, robotics, and medical protocols. | EIC Pathfinder | € 3.926.432 | 2022 | Details |
Improving social competences of virtual agents through artificial consciousness based on the Attention Schema TheoryASTOUND aims to develop an AI architecture for artificial consciousness using Attention Schema Theory to enhance social interaction and natural language understanding in machines. | EIC Pathfinder | € 3.330.897 | 2022 | Details |
Context-aware adaptive visualizations for critical decision makingSYMBIOTIK aims to enhance decision-making in critical scenarios through an AI-driven, human-InfoVis interaction framework that fosters awareness and emotional intelligence. | EIC Pathfinder | € 4.485.655 | 2022 | Details |
Emergent awareness from minimal collectivesEMERGE aims to develop a framework for collaborative awareness in minimal artificial agents, enabling complex cooperative behaviors without shared language or pre-defined protocols. | EIC Pathfinder | € 2.839.511 | 2022 | Details |
Symbolic logic framework for situational awareness in mixed autonomySymAware aims to develop a comprehensive framework for situational awareness in multi-agent systems, enhancing collaboration and safety between autonomous agents and humans through advanced reasoning and risk assessment. | EIC Pathfinder | € 3.980.291 | 2022 | Details |
Value-Aware Artificial Intelligence
The VALAWAI project aims to develop a toolbox for Value-Aware AI that integrates moral consciousness to enhance ethical decision-making in social media, robotics, and medical protocols.
Improving social competences of virtual agents through artificial consciousness based on the Attention Schema Theory
ASTOUND aims to develop an AI architecture for artificial consciousness using Attention Schema Theory to enhance social interaction and natural language understanding in machines.
Context-aware adaptive visualizations for critical decision making
SYMBIOTIK aims to enhance decision-making in critical scenarios through an AI-driven, human-InfoVis interaction framework that fosters awareness and emotional intelligence.
Emergent awareness from minimal collectives
EMERGE aims to develop a framework for collaborative awareness in minimal artificial agents, enabling complex cooperative behaviors without shared language or pre-defined protocols.
Symbolic logic framework for situational awareness in mixed autonomy
SymAware aims to develop a comprehensive framework for situational awareness in multi-agent systems, enhancing collaboration and safety between autonomous agents and humans through advanced reasoning and risk assessment.
Vergelijkbare projecten uit andere regelingen
Project | Regeling | Bedrag | Jaar | Actie |
---|---|---|---|---|
Autonomous Robots with Common SenseThis project aims to develop an 'Artificial Physical Awareness' autopilot system for autonomous robots, enabling them to operate safely and effectively despite failures by understanding their limitations. | ERC Consolid... | € 1.996.040 | 2024 | Details |
Contextual Radio Cues for Enhancing Decision Making in Networks of Autonomous AgentsThe CUE-GO project aims to enhance autonomous agents' decision-making by utilizing contextual radio cues for improved navigation, localization, and collaboration in social environments. | ERC Starting... | € 1.055.314 | 2025 | Details |
Causal Argumentative Learning AssistantCArLA aims to create a transparent and interactive platform for causal discovery in AI, enhancing understanding and trust in high-stakes domains like healthcare and finance. | ERC Proof of... | € 150.000 | 2025 | Details |
Identification and change of passive value markers in the laboratory and naturalistic environmentsPassiveValueMarkers aims to uncover automatic, passive valuation processes through neuroimaging and gaze analysis, enhancing understanding of value formation and informing interventions for valuation disorders. | ERC Consolid... | € 2.000.000 | 2023 | Details |
Towards an Artificial Cognitive ScienceThis project aims to establish a new field of artificial cognitive science by applying cognitive psychology to enhance the learning and decision-making of advanced AI models. | ERC Starting... | € 1.496.000 | 2024 | Details |
Autonomous Robots with Common Sense
This project aims to develop an 'Artificial Physical Awareness' autopilot system for autonomous robots, enabling them to operate safely and effectively despite failures by understanding their limitations.
Contextual Radio Cues for Enhancing Decision Making in Networks of Autonomous Agents
The CUE-GO project aims to enhance autonomous agents' decision-making by utilizing contextual radio cues for improved navigation, localization, and collaboration in social environments.
Causal Argumentative Learning Assistant
CArLA aims to create a transparent and interactive platform for causal discovery in AI, enhancing understanding and trust in high-stakes domains like healthcare and finance.
Identification and change of passive value markers in the laboratory and naturalistic environments
PassiveValueMarkers aims to uncover automatic, passive valuation processes through neuroimaging and gaze analysis, enhancing understanding of value formation and informing interventions for valuation disorders.
Towards an Artificial Cognitive Science
This project aims to establish a new field of artificial cognitive science by applying cognitive psychology to enhance the learning and decision-making of advanced AI models.