Bridging Intelligence and Instinct: A New Control Paradigm for Autonomous Robots (2307.10690v2)
Abstract: As the advent of artificial general intelligence (AGI) progresses at a breathtaking pace, the application of 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.
- Control barrier functions: Theory and applications. In 2019 18th European control conference (ECC), pages 3420–3431. IEEE, 2019.
- A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity. arXiv preprint arXiv:2302.04023, 2023.
- Rodney Brooks. A robust layered control system for a mobile robot. IEEE journal on robotics and automation, 2(1):14–23, 1986.
- Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712, 2023.
- On three-layer architectures. Artificial intelligence and mobile robots, 195:210, 1998.
- Feedback control of a cassie bipedal robot: Walking, standing, and riding a segway. In 2019 American Control Conference (ACC), pages 4559–4566. IEEE, 2019.
- Control of a quadrotor with reinforcement learning. IEEE Robotics and Automation Letters, 2(4):2096–2103, 2017.
- Large language models are zero-shot reasoners. Advances in neural information processing systems, 35:22199–22213, 2022.
- Chapter 23 Cognitive Robotics, volume 3 of Foundations of Artificial Intelligence, page 869–886. Elsevier, 2008.
- Reinforcement learning for robust parameterized locomotion control of bipedal robots. In 2021 IEEE International Conference on Robotics and Automation (ICRA), pages 2811–2817. IEEE, 2021.
- Taskmatrix. ai: Completing tasks by connecting foundation models with millions of apis. arXiv preprint arXiv:2303.16434, 2023.
- Llm as a robotic brain: Unifying egocentric memory and control. arXiv preprint arXiv:2304.09349, 2023.
- Y Nakajima. Task-driven autonomous agent utilizing gpt-4, pinecone, and langchain for diverse applications. See https://yoheinakajima. com/task-driven-autonomous-agent-utilizing-gpt-4-pinecone-and-langchain-for-diverse-applications (accessed 18 April 2023), 2023.
- Safety-critical control for dynamical bipedal walking with precise footstep placement. IFAC-PapersOnLine, 48(27):147–154, 2015.
- OpenAI. Gpt-4 technical report, 2023.
- George Saridis. Intelligent robotic control. IEEE Transactions on Automatic Control, 28(5):547–557, 1983.
- Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface. arXiv preprint arXiv:2303.17580, 2023.
- Reflexion: an autonomous agent with dynamic memory and self-reflection. arXiv preprint arXiv:2303.11366, 2023.
- Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023.
- Chatgpt for robotics: Design principles and model abilities. Microsoft Auton. Syst. Robot. Res, 2:20, 2023.
Collections
Sign up for free to add this paper to one or more collections.