Goal-Guided Neural Cellular Automata: Learning to Control Self-Organising Systems
This addresses the challenge of controlling self-organizing systems for researchers in computational biology and AI, though it is incremental as it builds on existing NCA methods.
The paper tackles the problem of uncontrollability in Neural Cellular Automata (NCAs) during growth by introducing Goal-Guided Neural Cellular Automata (GoalNCA), which uses goal encodings to dynamically control cell behavior, enabling continual behavior changes and generalization to unseen scenarios while maintaining task performance even with partial goal information.
Inspired by cellular growth and self-organization, Neural Cellular Automata (NCAs) have been capable of "growing" artificial cells into images, 3D structures, and even functional machines. NCAs are flexible and robust computational systems but -- similarly to many other self-organizing systems -- inherently uncontrollable during and after their growth process. We present an approach to control these type of systems called Goal-Guided Neural Cellular Automata (GoalNCA), which leverages goal encodings to control cell behavior dynamically at every step of cellular growth. This approach enables the NCA to continually change behavior, and in some cases, generalize its behavior to unseen scenarios. We also demonstrate the robustness of the NCA with its ability to preserve task performance, even when only a portion of cells receive goal information.