Embedded systems play a critical role in enabling intelligent mobility technologies to operate reliably within real-world platforms that have limited power, memory, and computational resources.
Our laboratory conducts research on embedded AI systems for autonomous driving and intelligent vehicles, covering real-time sensor data processing, on-device neural network inference, and low-power system deployment.
Through hardware-aware AI optimization and efficient computing technologies, we aim to bridge the gap between advanced algorithms and practical embedded platforms for next-generation mobility systems.
Research Competitiveness
We develop embedded AI technologies that enable complex autonomous driving algorithms to operate efficiently on low-power edge devices and AI accelerators.
Our research covers real-time processing of high-dimensional sensor data, allowing intelligent vehicles to understand and respond to dynamic driving environments within strict system constraints.
In addition, we investigate energy-efficient neural network architectures and hardware-aware deployment strategies to reduce computational cost while maintaining reliable system performance.
Through these efforts, we aim to establish scalable embedded system technologies that support the practical deployment of intelligent mobility applications beyond high-performance server or GPU-based environments.
