Emerging Frontiers in Physical and Embodied Artificial Intelligence
Published 31 October, 2025
Recent advances in Physical and Embodied Artificial Intelligence are transforming the relationship between computation, perception, and action. By integrating artificial intelligence with robotics, materials science, control theory, neuroscience, and human-computer interaction, researchers are creating intelligent systems that can sense, reason, and adapt within the physical world. These systems range from soft and bio-inspired robots to intelligent materials, autonomous machines, and cyber-physical infrastructures that blend digital cognition with physical embodiment.
The growing convergence of these disciplines marks a shift toward AI that moves, interacts, and learns through physical experience. Achieving this vision requires innovation in perception, motion planning, learning algorithms, control architectures, and interactive intelligence. Key challenges include enabling adaptive and energy-efficient behavior, interpretability of embodied actions, and alignment between human and machine capabilities across diverse environments and tasks.
This special issue aims to highlight cutting-edge research and cross-disciplinary perspectives that advance Physical and Embodied AI, from theoretical models to real-world systems. We welcome contributions from artificial intelligence, robotics, mechatronics, materials engineering, cognitive science, neuroscience, and computer vision. Papers may present new algorithms, architectures, control systems, physical prototypes, data-driven models, or comprehensive reviews that promote understanding and innovation in embodied intelligence.
Through this special issue, we seek to foster collaboration between researchers and practitioners developing the next generation of AI systems that seamlessly integrate computation, perception, and physical interaction.
Topics include, but are not limited to:
- Embodied and physical intelligence architectures and design principles
- Cognitive robotics and adaptive learning for real-world interaction
- Physical sensing, tactile perception, and multimodal fusion
- Human-machine collaboration, co-adaptation, and shared control
- Soft robotics, bio-inspired actuation, and intelligent materials
- Neuromorphic computing and energy-efficient control for Physical AI
- Digital twins, simulation, and model-based reasoning for physical systems
- Collective intelligence in swarms, morphable, or modular robots
- AI-driven manufacturing, logistics, and autonomous infrastructure
- Physical AI in healthcare, rehabilitation, and assistive technologies
- Cross-domain integration of materials, sensors, and learning algorithms
- Ethical, societal, and regulatory considerations of embodied intelligence
- Benchmark datasets, performance evaluation, and reproducible research
Submission instructions:
Please read the Guide for Authors before submitting. All articles should be submitted online .
Timeline:
- Submission deadline: March 15, 2026
- Acceptance deadline: April 30, 2026
- Publication Date: July 31, 2026
Guest Editors:
Wei Xiang
Distinguished Professor, School of Computing, Engineering and Mathematical Sciences, La Trobe University, Australia
Email: w.xiang@latrobe.edu.au
Di Wu
Senior Lecturer, School of Computing, Engineering and Mathematical Sciences, La Trobe University, Australia
Email: d.wu@latrobe.edu.au
Dr. Di Wu is a Senior Lecturer at the School of Computing, Engineering and Mathematical Sciences, Deputy Director of Cisco – La Trobe Centre for Artificial Intelligence and Internet of Things, and also a member of the Australian Centre for Artificial Intelligence in Medical Innovation (ACAMI) at La Trobe University, Melbourne Australia. Before that, he was a Senior Lecturer at the School of Mathematics, Physics, and Computing, the University of Southern Queensland (UniSQ), Queensland, Australia. Prior to that, he was a Lecturer at the same School. Prior to that, he was a Research Fellow at the Australian Institute for Machine Learning (AIML) and School of Computer Science, University of Adelaide, Adelaide, Australia. Previous to this, he was an Associate Research Fellow, Artificial Intelligence at Deakin Blockchain Innovation Lab, School of Information Technology, Deakin University, Melbourne, Australia, and worked as a Postdoc Fellow at the School of Computer Science, University of Technology Sydney (UTS), Sydney, Australia. He has more than 10 years of experience in research & development and academia. He has substantial industry experience in large project management, software development, and large system maintenance experience while working on various projects at China Telecom (Global 500), Shanghai. His research area focuses on applying federated learning, AI security and privacy, and trustworthy AI. He has published papers in high-quality refereed books, conferences, and journals, including top-tier venues such as ICLR, KDD, USENIX Security, IJCAI, WWW, TDSC, TKDE, ToN etc. He also serves as an associate editor in NLPJ and a reviewer for many high-quality academic conferences and journals, such as NeurIPS, ICLR, ICCV, KDD, AAAI, ACM MM, CoRL, TMC, TNNLS, TETCI, PR, etc.
Atul Sajjanhar
Senior Lecturer, School of Information Technology, Deakin University, Australia
Email: atul.sajjanhar@deakin.edu.au
Atul Sajjanhar is currently a Senior Lecturer in the School of Information Technology, Deakin University, Australia. He received Master of Computing and PhD degrees from Monash University, Australia. He has held positions in the Institute of Infocomm Research, Singapore and The University of Southern Queensland, Australia. His research areas are in deep learning and pattern recognition. He has participated in several industry-funded projects.
Jun Bai
Research Fellow, School of Computer Science, McGill University, Canada
Email: jun.bai@mcgill.ca
Dr. Jun Bai is a research fellow in the School of Computer Science at McGill University, Montreal, Canada. He received his Ph.D. in Information Technology from Deakin University, Australia, in 2024. His research focuses on trustworthy and privacy-preserving federated learning, distributed AI for healthcare, and generative learning. Dr. Bai has published in premier venues such as ICLR, ACM SIGKDD, ACM Computing Surveys, npj Digital Medicine, and IEEE Transactions on Fuzzy Systems, among others. He also serves as a active reviewer for leading journals and conferences including NeurIPS, ICLR, ICML, AAAI, CVPR, KDD, and IEEE TKDE, contributing to the advancement of trustworthy and responsible artificial intelligence research.
Jing Xu
Research Fellow, CISPA Helmholtz Center for Information Security, Germany
Email: jing.xu@cispa.de
Dr. Jing Xu is a Postdoctoral Researcher at the CISPA Helmholtz Center for Information Security, Germany, and obtained her PhD in Computer Science from Delft University of Technology (TU Delft), the Netherlands. Her research lies at the intersection of machine learning, security, and privacy, with a particular focus on trustworthy and privacy-preserving machine learning.
