Intelligent embedded systems for automotive, drones, home appliances, and cross-industry integration
Next-generation operating systems powered by artificial intelligence
Traditional operating systems are evolving into intelligent platforms that can learn, adapt, and optimize themselves. Our research focuses on creating AI-native operating systems that redefine what embedded systems can achieve.
Driving the future of intelligent vehicles
Real-time perception, decision-making, and control systems for self-driving vehicles. Our OS handles sensor fusion, path planning, and safety-critical operations.
Predictive maintenance systems that anticipate failures before they occur, reducing downtime and improving vehicle safety.
Vehicle-to-everything communication protocols enabling intelligent traffic management and cooperative driving systems.
Autonomous aerial intelligence
Our drone OS research focuses on creating fully autonomous unmanned aerial vehicles capable of complex missions without human intervention.
Intelligent living through embedded AI
Appliances that learn user preferences and adapt their operation accordingly.
AI-driven energy management reducing consumption while maintaining comfort.
Self-diagnosing systems that alert users before failures occur.
Interoperable systems that work together for a unified smart home experience.
Connecting diverse systems for unified intelligence
Our crossover industrial integration research explores how AI operating systems can bridge different industries, creating synergies and enabling new capabilities.
Exploring the future of AI in operating systems
As AI becomes more capable, the traditional app paradigm may evolve. We explore how AI agents could replace discrete applications, providing seamless, intent-based computing where the OS understands and fulfills user needs directly.
Our research investigates autonomous learning mechanisms that enable operating systems to improve over time without explicit programming. These self-learning capabilities allow systems to adapt to changing environments and user needs.
We critically examine the boundaries of AI in real-world systems: computational constraints, power limitations, safety concerns, explainability requirements, and ethical considerations that shape practical deployments.