DrWibowo Hardjawana

My research focuses on developing AI-native wireless communication systems that embed artificial intelligence directly into the physical (PHY) and medium access control (MAC) layers. Unlike conventional systems that rely on fixed models and handcrafted algorithms, AI-native networks learn and adapt to complex and dynamic environments in real time.

At the physical layer, I design learning-based signal processing methods—such as neural receivers, data-driven modulation, and adaptive channel estimation—to improve robustness and efficiency. At the MAC layer, I develop AI-driven resource allocation techniques using reinforcement learning and graph neural networks for dynamic spectrum access, power control, and user scheduling.

The goal is to build self-optimising wireless networks capable of jointly managing signal processing and resource allocation without explicit modelling assumptions. Over the next five years, my work will focus on developing end-to-end AI-based PHY/MAC architectures and demonstrating their performance on software-defined radio testbeds. This research aims to transform wireless systems from rule-based designs into intelligent networks that learn to communicate.