I am a researcher with a strong theoretical basis in artificial intelligence. Specifically, reinforcement learning, combinatorial search, multiagent route assignment, game theory, flow and convex optimization, and multiagent modeling and simulation. I gained vast knowledge and experience in utilizing my theoretical foundations towards traffic management and traffic optimization application. Nonetheless, I view myself as part of the AI community where my work is highly cited. I strive to further the impact of my applicable expertise for solving real-life problems while simultaneously continuing to make theoretical advances that justify the proposed solutions.
Autonomous Traffic Management
Network Flow Optimization
Autonomous driving capabilities are becoming increasingly common on vehicles. Such capabilities present opportunities for developing safer, cleaner and more efficient road networks. Looking towards a future where traffic is composed of vehicles with different levels of autonomousy, we are developing efficient reservation based intersection management protocols. By relying on the fine and accurate control of connected and autonomous vehicles along with communication capabilities, intersection managements protocols coordinate such vehicles simultaneously across intersections.
Road pricing as a tool for congestion management has a long history in the transportation world, being first suggested nearly a century ago. Recent advances in connected and automated vehicle technology offer unprecedented flexibility and scope for implementing these tolls. In principle, tolls can be charged on many or all network links, and changed frequently in response to real-time observations of traffic conditions. Toll values and traffic conditions can then be communicated to vehicles which instantly change routes in response, with minimal to no intervention needed on behalf of drivers, who might only indicate some measure of the trip urgency or other proxy for value of time before departing. Even before autonomous driving technology reaches full penetration, communication capabilities and automated route selection software (as can be found on modern cell phones) may be sufficient to implement such a scheme.
In the multiagent pathfinding problem we are given a graph and a set of agents, each agent must be assigned a path leading from its initial location to its destination such that it will not collide with obstacles or other moving agents. MAPF can model many real-world problems such as video games, traffic control, robotics, aviation, automated warehouses and more. See (Yu and LaValle 2016) for a comprehensive survey.
Guni Sharon is an assistant professor in the department of computer science and engineering (CSE) at Texas A&M University. He received his doctoral, master’s and bachelor’s degrees in information systems engineering from Ben-Gurion University. Sharon’s current work focuses on developing and applying artificial intelligence techniques for optimizing transportation networks. Prior to joining Texas A&M, he was a postdoc in the computer science department at University of Texas at Austin. He is the recipient of the Outstanding Paper Award from the Association for the Advancement of Artificial Intelligence (AAAI). Prof. Sharon's complete curriculum vitae is avilable in its Full version, as a One page, or as a One page + publications
Texas A&M University, Computer Science and Engineering. Develop and provide academic courses at the graduate and undergraduate levels. Guide, lead and mentor students during classes and research projects. Create, innovate and implement career-enhancement programs and activities. Serve and support functional activities of departmental committees.
University of Texas at Austin, Computer Science. Member in TxDOT 6838 Project titled “Bringing smart transport to Texans: ensuring the benefits of a connected and autonomous transport system in Texas”. Part of a research collaboration between UT-Austin and Toyota, InfoTechnology Center Co., Ltd. Coordinating and leading a bi-weekly project meeting on traffic management including 2 faculty members, 3 post-docs and 2 Ph.D. students.
Ben-Gurion University, Information Systems Engineering; Dean award for outstanding Ph.D student. Thesis title “Novel Search Techniques for Path Finding in Complex Environment”. Awarded the "Darom" Graduate Research Scholarship.
Ben-Gurion University. Led discussions in a class of up to 30 students. Prepared course material including laboratory experiments, lectures, exams, homework, and practice problems. TA for the following courses: Introduction to Operation Systems, Operations Research, Introduction to A.I., Automata and computability Theory.
Ben-Gurion University, Information Systems Engineering; graduation with Honors. Thesis title “Optimal Multiagent Pathfinding”. Awarded the Harbor Foundation Graduate Research Scholarship.
Ben-Gurion University, Information Systems Engineering; graduation with Honors. Winner of the South African Zionist Federation Scholarship.
Israeli Defense Force; Head of the operations department of an artillery brigade. supervised two soldiers.
Feel free to contact me via email, phone or regular mail.
I will do my best to reply as soon as possible.
Department of Computer Science and Engineering, H. R. Bright Building, 3112 TAMU, 710 Ross St, College Station, TX 77843
guni (at) tamu (dot) edu
+(1) 979 845 5498
© 2017 Modern CV. All rights reserved | Design by W3layouts