Agentic AI for Robot Teams
Researchers at Johns Hopkins Applied Physics Laboratory are advancing agentic AI to enable autonomy, coordination, and adaptability in collaborative robotic teams.

Agentic AI for Robot Teams">
The quest for artificial intelligence that can think and act autonomously has taken a significant step forward, thanks to recent efforts at the Johns Hopkins Applied Physics Laboratory. The laboratory has been working to advance agentic AI for collaborative robotic teams, tackling the complex challenges of enabling autonomy, coordination, and adaptability across diverse systems. At the heart of this endeavor is a scalable architecture designed to support agentic behaviors in multi-robot environments.
This architecture aims to empower robots to operate independently, yet work together seamlessly as a cohesive unit. A key component of this approach is the use of Large Language Model (LLM)-based AI agents, which are being explored for their potential to bring about a new level of intelligence and adaptability to robotic teams. The research team has made significant progress in applying LLM-based AI agents to robotic teams, with impressive demonstrations of the approach running on hardware with a heterogeneous team of robots.
These experiments have not only showcased the potential of agentic AI but also highlighted the challenges that come with developing and integrating this technology. According to the researchers, one of the critical lessons learned from this work is the importance of developing a robust and scalable architecture that can support the complex interactions between robots. The team has also identified key areas for future research and development, including improving the adaptability and autonomy of robotic teams.
The presentation on this research provides a comprehensive overview of the approach, including an introduction to LLM-based AI agents, demonstrations of the technology in action, and practical lessons learned from the development process. For those interested in learning more, a free whitepaper is available, offering a deeper dive into the findings and future directions of this exciting research area. As the field of agentic AI continues to evolve, the work being done at Johns Hopkins Applied Physics Laboratory is paving the way for a new generation of autonomous robotic teams that can collaborate, adapt, and thrive in complex environments.
Source: IEEE Spectrum