Bridging Intelligence and Instinct: A New Control Paradigm for Autonomous Robots

TL;DR

This paper introduces a layered control architecture for autonomous robots that integrates large language model-based AI agents with innate robotic instincts, aiming to improve safety, reliability, and versatility in autonomous operations.

Contribution

It proposes a novel layered framework inspired by biological systems, combining AI agent intelligence with robotic instincts to address unpredictability and hallucinations in LLM-driven robotics.

Findings

Enhanced safety and robustness demonstrated in mobile robot case study

Significant reduction in hallucination-related errors in autonomous decision-making

Improved adaptability of robots in diverse environments

Abstract

As the advent of artificial general intelligence (AGI) progresses at a breathtaking pace, the application of large language models (LLMs) as AI Agents in robotics remains in its nascent stage. A significant concern that hampers the seamless integration of these AI Agents into robotics is the unpredictability of the content they generate, a phenomena known as ``hallucination''. Drawing inspiration from biological neural systems, we propose a novel, layered architecture for autonomous robotics, bridging AI agent intelligence and robot instinct. In this context, we define Robot Instinct as the innate or learned set of responses and priorities in an autonomous robotic system that ensures survival-essential tasks, such as safety assurance and obstacle avoidance, are carried out in a timely and effective manner. This paradigm harmoniously combines the intelligence of LLMs with the instinct of robotic behaviors, contributing to a more safe and versatile autonomous robotic system. As a case study, we illustrate this paradigm within the context of a mobile robot, demonstrating its potential to significantly enhance autonomous robotics and enabling a future where robots can operate independently and safely across diverse environments.