Mohamad Imam Firdaus

Papers

Total Citations

H-Index

About

Mohamad Imam Firdaus is a researcher at the forefront of hardware-accelerated reinforcement learning, with a focus on embedded systems and robotics. His work bridges the gap between advanced machine learning algorithms and practical, real-time control applications. Firdaus’s major contribution is the development of efficient, FPGA-based accelerators that enable Q-Learning and other reinforcement learning models to operate with low latency and high energy efficiency, a critical need for autonomous systems. His most cited paper, “MazeCov-Q: An Efficient Maze-Based Reinforcement Learning Accelerator for Coverage” (2023, 5 citations), introduces a novel hardware design that optimizes coverage path planning, demonstrating how RL can be deployed without labeled data for tasks like robotic navigation. In his earlier work, “Control System for Mobile Robot using FPGA-Based Q-Learning Accelerator” (2022, 3 citations), he solved the key challenge of converting RL actions into precise motor control signals, making these algorithms viable for physical robots. With a growing citation impact, Firdaus’s research is paving the way for smarter, more autonomous robots in industries from logistics to energy, showcasing how hardware-software co-design can unlock the full potential of unsupervised learning in the physical world.