Combining Fast and Slow Thinking for Human-like and Efficient Navigation in Constrained Environments
This work addresses the need for more adaptable and efficient AI navigation systems, though it appears incremental by building on existing cognitive theories.
The paper tackles the problem of AI systems lacking human-like decision-making capabilities by proposing an architecture based on fast and slow solvers with a metacognitive component, applied to navigation in constrained environments, showing that combining these modalities improves decision quality, resource consumption, and efficiency as the system evolves from slow to fast thinking.
Current AI systems lack several important human capabilities, such as adaptability, generalizability, self-control, consistency, common sense, and causal reasoning. We believe that existing cognitive theories of human decision making, such as the thinking fast and slow theory, can provide insights on how to advance AI systems towards some of these capabilities. In this paper, we propose a general architecture that is based on fast/slow solvers and a metacognitive component. We then present experimental results on the behavior of an instance of this architecture, for AI systems that make decisions about navigating in a constrained environment. We show how combining the fast and slow decision modalities allows the system to evolve over time and gradually pass from slow to fast thinking with enough experience, and that this greatly helps in decision quality, resource consumption, and efficiency.