Aseel Smerat

Papers

Total Citations

H-Index

About

Aseel Smerat is a rising researcher at the forefront of autonomous systems and multi-agent coordination, whose work bridges the gap between theoretical control theory and practical robotics. Her research primarily focuses on three interconnected domains: multi-robot exploration, reinforcement learning for navigation, and resilient control of multi-agent systems (MASs) under adversarial conditions. In her most cited work, "Population‐Based Optimization With Decentralized Method" (2025, 5 citations), Smerat tackles the fundamental challenge of real-time task allocation in uncertain environments, introducing a hybrid stochastic optimization approach that enables robot teams to dynamically map unknown spaces without centralized control. This contribution addresses a critical bottleneck in swarm robotics. She further advances autonomous navigation through "Autonomous Robot Navigation System Based on Double Deep Q-Network" (2025), applying reinforcement learning to overcome sparse reward signals—a persistent hurdle in training agents for complex environments. Demonstrating her versatility, Smerat also addresses security and reliability in "Finite-time fuzzy control strategy for nonlinear MASs with actuator faults and deception attacks" (2025), proposing a control framework that ensures system stability even when components fail or are compromised by cyberattacks. Though early in her career, Smerat’s work is already shaping how robots explore, navigate, and cooperate in the real world.