Bibek Poudel

University of Tennessee at Knoxville, University of Memphis

Papers

Total Citations

H-Index

About

Bibek Poudel is an emerging researcher at the intersection of autonomous systems, traffic control, and evolutionary computation. His work focuses primarily on mixed traffic environments — road networks where human-driven and robotic vehicles coexist — and he has made notable strides in applying reinforcement learning to address one of transportation's most persistent challenges: congestion. His most-cited work, "Mixed Traffic Control and Coordination from Pixels" (2024, 11 citations), explores vision-based control strategies for autonomous vehicles operating alongside human drivers, pushing the boundaries of perception-driven decision-making. Complementing this, his CARL framework (2024, 7 citations) introduces congestion-aware reinforcement learning that accounts for the complexity and diversity of human driving behavior, enabling more realistic simulation and robust validation of robotic vehicle policies. Beyond traffic systems, Poudel has demonstrated breadth by contributing to evolutionary algorithm research, with his work on Quality-Diversity optimization (2023, 5 citations) addressing the fundamental challenge of escaping local optima through diverse, high-quality solution populations. Though early in his career, Poudel's research portfolio reflects a sophisticated, systems-level thinker whose contributions are gaining meaningful traction across robotics, transportation, and optimization communities.