Reliable Machine learning for wireless embodied intelligence

Advanced machine learning (ML) models are increasingly deployed in task-critical industrial scenarios, e.g., smart factory, autonomous vehicle/drone/robot networks, with embodied intelligence through wireless interface that integrate computer vision, pattern recognition, sensing, communications and mobile computing. Wireless environment is non-stationary with spatial-temporal varying channels, information feedback distortion, and hardware impairments. These factors make embodied intelligence more challenging, bringing risks such as unpredictable outage during mobility events, unsafe robots navigation due to misspecified models, and corrupted multi-agent coordination due to misaligned scheduling policy. This workshop invites researchers and industry practitioners to present novel theory, performance analysis, and architectural insights that advance deployment-time reliability guarantees of embodied intelligence inwireless networks.

To facilitate multi-disciplinary insights across the reliability bottlenecks of embodied AI over wireless systems, where learning, sensing, communication, and automatic control are coupled, this workshop seeks contributions that not only advance theoretical reliability but also demonstrate the corresponding applications to build safer, more robust, and more efficient embodied AI in wireless communications.

‍Topics of interest include, but are not limited to, the following categories:‍

• Theoretical foundations of reliable embodied AI in wireless networks
• Game theory and robustness in embodied multi-agent wireless networks
• Reliability analysis in over-the-air federated/distributed agentic AI
• Uncertainty quantification for embodied AI agents in wireless networks
• ML models calibration for embodied AI agents in wireless networks
• Generalization theory for embodied AI in dynamic wireless environments
• Distributionally robust learning and worst-case guarantee for wireless embodied intelligence
• Statistical reliability for wireless embodied AI decision, motion, and cooperation
• Reliability of multi-modal wireless foundation models at mobile agents
• Reliable ML for emerging technologies, e.g., UAV/HAP coordination, robotics networking, autonomous vehicles, integrated sensing andcommunications
• Embodied AI benchmarks and testbeds on reliability in wireless systems
• Architectural designs for reliable embodied AI in wireless systems