Max Robotics — Global Service Robot Directory + US Certification

About

Mahmoud Akl is a leading researcher at the intersection of neurorobotics and brain-inspired learning, pioneering methods that bridge biological neural computation with robotic control. His work centers on developing energy-efficient, biologically-plausible learning algorithms—particularly spiking neural networks (SNNs) and reward-modulated spike-timing-dependent plasticity (R-STDP)—for real-world robotic applications. Akl’s most cited paper (78 citations) introduces an end-to-end SNN learning framework based on R-STDP for lane-keeping vehicles, demonstrating how brain-inspired models can achieve robust control with limited computational resources. He further advanced the field by showing how dopamine-modulated STDP enables robotic arms to learn target-reaching movements through trial and error, mimicking human motor babbling. His 2022 work on fine-tuning deep reinforcement learning policies with R-STDP addresses the critical sim-to-real transfer problem, offering a practical solution for deploying simulated policies on physical robots. Akl has also contributed to the Human Brain Project’s Neurorobotics Platform, enabling researchers worldwide to connect spiking neural networks to virtual and real robots via high-performance computing. His research uniquely combines computational neuroscience, reinforcement learning, and robotics, paving the way for autonomous systems that learn and adapt with the efficiency of the brain.