Edge AI enables AI models to run directly on local devices, bringing computation closer to data sources for faster, more efficient decision-making. Therefore, it is critical for modern robotics, where rapid and robust decision-making is essential. In applications such as high-speed drones and industrial robots operating in extreme conditions, on-device processing ensures real-time control and reliability. Moreover, as service robots become increasingly integrated into daily and personal environments, preserving user privacy during data processing is paramount. While recent advances in AI and deep learning have significantly enhanced robotic capabilities in perception, decision-making, and control, relying solely on cloud-based processing can introduce delays and compromise privacy. Leveraging edge AI enables decentralized, real-time computation that meets the demanding requirements of today's robotic applications.

The challenges in edge AI cannot be addressed solely by the robotics community, as it demands an interdisciplinary approach. The ever-growing scale of deep learning models, combined with emerging security risks and privacy concerns, pose significant challenges for deploying edge AI in robotic systems. These challenges extend beyond traditional robotics, encompassing critical issues in algorithm design, software infrastructure, communication protocols, and hardware architecture. A robust edge AI system for robots requires the integration of efficient algorithms, reliable software support, secure communication, and advanced hardware. Consequently, successful implementation calls for collaborative research across robotics, machine learning, security, computer engineering, and circuit design.

The Research Topic aims to encourage papers from diverse fields to jointly advance the integration of edge AI for robotics, by combining the application-driven insights from robotics with innovative technology solutions. Target research in the Topic will explore the latest edge AI applications in robotics and examine emerging technologies that address the challenges of real-world deployments. Moreover, the Research Topic will identify critical issues, such as resource constraints, security vulnerabilities, communication challenges, robustness, and adaptability, and outline promising interdisciplinary research directions to overcome these hurdles.

We encourage submissions to topics including, but not limited to, the following:
1. Emerging edge AI applications for robotics
2. Emerging edge AI hardware technology for robotics
3. Large-scale foundation models on the edge for embodied AI
4. Efficient robot learning on the edge and federated robot learning
5. Edge privacy and security for robotics
6. Bio-inspired robots, neurorobotics, and neuromorphic intelligence
7. Robotics systems in the edge-cloud continuum

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:
Brief Research Report
Data Report
Editorial
General Commentary
Hypothesis and Theory
Methods
Mini Review
Opinion
Original Research
Perspective
Policy and Practice Reviews
Review
Systematic Review
Technology and Code

This Research Topic is related to the workshop of the same name at the 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) conference, taking place in Hangzhou, China on the 24th of October 2025. Any contributions that were previously published as conference proceedings should be extended to include at least 30% original content.

Are you interested in contributing a manuscript to this Research Topic?

Edge AI for Robotics: Emerging Technologies and Applications