Summary
Creating machines that truly experience sensations like humans is hard. This paper introduces a step-by-step design that puts together three important ideas needed for such experiences: a machine needs to be aware of its environment and senses, imagine the world internally, and match its predictions with what really happens. The authors show how these parts can work together using existing computing elements, and they suggest ways to test if the whole system works as intended. They also propose that simple self-awareness might come from connecting actions with their effects, leading to different behaviors like curiosity or avoidance when surprises happen.
What this means in practice
- •For robotics engineers: design robots with integrated perception, prediction, and coherence to create basic self-awareness and adaptive behaviors.
- •For game ai developers: implement NPC behaviors that change based on surprise and positive or negative outcomes using a unified sensing and simulation pipeline.
A position paper. It proposes an approach and reports no results.
Authors
Tetiana Grinberg, Katrina Schleisman, Patryk Laurent, Bogdan Udrea, Minda Myers, Brian Aufderheide, Luis El Srouji, Doyle Groves, Kevin Schmidt
Abstract
A key challenge in machine consciousness research is translating theoretical models into computational-level implementations. In this paper, we address this challenge by proposing a five-layer implementation architecture for the S3Q (Simulated, Situated, Structurally Coherent) theory of consciousness. Rather than introducing novel formalisms, the architecture composes published computational primitives into a single pipeline. S3Q identifies three jointly necessary conditions for qualia: (1) grounded sensorimotor situatedness, (2) internal simulation via a world model, and (3) structural coherence between predictions and observations. No existing computational system implements all three simultaneously. We map each S3Q tenet to specific, compatible computational machinery and specify how these components interface within a single representation pipeline that operates on continuous, differentiable, per-object slot vectors, along with a developmental bootstrap sequence and falsifiable predictions for the composed system that no subset of the architecture produces in isolation. The model suggests that a basic sense of "self" develops by linking actions to their outcomes, and that behavior falls into three patterns (hesitation, curiosity, or avoidance) depending on how unexpected an outcome is and whether it is experienced as positive or negative. Each prediction is individually falsifiable, providing the field with a testable framework to advance our understanding of machine consciousness.