" Towards super-flexible software that self-heals, self-optimizes, and self-protects "
In the IoT era, software systems are becoming more and more closely related to the physical world. Autonomous agent-based software that can flexibly address various changes in the physical world by self-healing, self-optimizing, and self-protecting is a key enabler. In our laboratory, we are studying techniques for developing “super-flexible software” that can realize various next-generation systems such as IoT, automated driving systems, and smart cities safely and with high quality.
Research topics
We are conducting research related to advanced techniques for autonomous agent software systems that be able to adapt and/or evolve flexibly in response to changes at runtime. Recent research topics include IoT systems and autonomous driving software.
Self-Adaptive Systems
Modern software systems closely interact with external entities (e.g. users, external services, and physical entities), whose changes occur at runtime and are impossible to be completely predicted at development time. How does such a system address the changes in the environment? Self-adaptive system that (1) monitors the changes, (2) analyzes and plans modification of structure and/or behavior of the system to maintain its qualities, and (3) executes the plan during system execution, is known as a promising approach. We are working on models@run.time techniques that utilize models of the system even at runtime by the system to make assured decision about self-adaption at runtime. -> Details
IoT system development
We are working on attractive IoT applications, such as smart space management system, aeroponics systems, and drone/robot systems. We devise techniques to support such software that interacts with physical environments. -> Details
Autonomous driving / intelligent transportation systems
We are working on software techniques to enable safe and comfortable autonomous driving vehicle and intelligent transportation system by applying cutting-edge automation techniques, such as deep reinforcement learning, linear programming, and discrete controller synthesis.
-> Details
International collaboration
We have active collaborations with world-leading research groups in overseas universities and institutes. -> Details
Laboratory Environment
- Laptop PC, display monitor, desk for all student
- IoT devices (Raspberry Pi, Arduino, and various sensors and actuators)
- High performance computational servers
- High performance GPU servers
- 3D printer
- Smart speakers (Google Home)
- Smart lights (Philips Hue Lite)
- Wearable sensors (J!ns MEME)