Abolfazl Lavaei is a PhD candidate in the Department of Electrical and Computer Engineering at Technical University of Munich (TUM) since November, 2016. He is also a Munich Aerospace Doctoral Scholarship Holder under the research group of Autonomous Flight. Prior to joining the HCS Group, he has received the M.Sc. degree in Aerospace Engineering with a major in Flight Dynamics and Control from University of Tehran. He has worked on various areas of Control Theory such as Optimal Control, Robust Tracking, System Identification, and Motion Planning as well as their applications in mechanical systems. For his Master’s work, he has received the “Best Graduate Student Award” in all fields of study in Faculty of New Sciences and Technologies at University of Tehran with the GPA of 20/20. He is also the recipient of several prestigious PhD scholarships from different top-ranked universities. During his PhD studies, he has been working on “Compositional (In)Finite Abstractions for Automated Verification and Synthesis of Large-Scale Interconnected Stochastic Systems”. More specifically, his current research focuses on developing the abstraction-based synthesis techniques for complex networks in an automated fashion in order to enable them to make their own decisions without direct human involvement (e.g. Autonomous Driving). He is a scholar of Munich Aerospace Research Group as well as DLR Graduate Program.
Autonomy is certainly one of the main themes of the 21st-century technology. In the near future, we expect to see fully autonomous vehicles, aircrafts, and robots, all of which should be able to make their own decisions without direct human involvement. Although this technology theme provides many potential advantages, e.g., fewer traffic collisions, reduced traffic congestion, increased roadway capacity, relief of vehicle occupants from driving, and so forth, guaranteeing safety and reliability of such networks in a formal as well as time/cost-effective way is the main challenging objective in the study of those systems. My research is to investigate this complex objective by providing an automated (push-button) controller synthesis approach for such complex networks in a formal fashion without requiring any costly and exhaustive post facto testing and validation.
In this respect, we first compositionally drive infinite abstractions (model order reductions) of such complex networks. We then construct finite abstractions (a.k.a. finite Markov decision processes) from the reduced-order versions of the original models. By leveraging those constructed finite abstractions and computational tools developed for discrete-event systems and games on automata, one can compositionally synthesize controllers in an automated as well as formal fashion satisfying rich complex specifications, difficult (if not impossible) to enforce with classical control design approaches. Finally, we refine the controller back (via an interface map) to the original models with guaranteed error bounds on the probabilistic output trajectories. Unfortunately, almost all the existing techniques on the construction of finite-state models suffer severely from the curse of dimensionality: the number of symbolic states grows exponentially with its dimensionality. Hence, this prevents us to provide automated synthesis for large-scale systems which is the case in many safety-critical applications such as autonomous driving. Therefore, the main goal of my research is to develop the compositional efficient (real-time) techniques for automated verification and synthesis of large-scale complex stochastic systems.
Bachelor & Master Thesis Opening
Please contact me if you are interested in doing your Bachelor or Master thesis under my supervision. The current openings revolve around "Implementation of Controller Synthesis" in C++/Python with application to "Autonomous Driving". If you have also your own idea for a thesis topic related to autonomous driving, feel free to contact me.
Honors and Awards
• Recipient of Munich Aerospace Doctoral Scholarship, Hybrid Control Systems Group, Department of Electrical and Computer Engineering, Technical University of Munich (TUM), Germany, 2016.
• Recipient of University of Auckland Doctoral Scholarship, Department of Electrical and Computer Engineering, University of Auckland, New Zealand, 2016.
• Recipient of Concordia International Award of Excellence, Department of Electrical and Computer Engineering, Concordia University, Canada, 2016.
• Admitted by EDEE Doctoral Program Committee, Department of Electrical Engineering, École Polytechnique Fédérale De Lausanne (EPFL), Switzerland, 2016.
• Admitted by Doctoral Program Committee, Department of Mechanical Engineering, University of Melbourne, Australia, 2016.
• Recipient of Departmental Prestigious Doctoral Fellowship, Department of Mechanical and Aerospace Engineering (Jacobs School of Engineering), University of California at San Diego (UCSD), United States, 2015.
• Best Graduate Student Award in all fields of study at Faculty of New Sciences and Technologies, University of Tehran, 2015.
• The First Graduate Student Nationwide who managed to receive a two-year Master of Science degree in two semesters (one academic-year) with the full GPA (20 out of 20), 2014.
• A. Lavaei, S. Soudjani, and M. Zamani, “Compositional (In)Finite Abstractions for Large-Scale Interconnected Stochastic Systems”. Submitted for publication, 2018. [Preprint]
• A. Lavaei, S. Soudjani, and M. Zamani, “Compositional Abstractions of General Markov Decision Processes by Approximate Probabilistic Relations”. Submitted for publication, 2018.
• A. Lavaei, S. Soudjani, and M. Zamani, “Compositional Synthesis of not Necessarily Stabilizable Stochastic Systems via Finite Abstractions”. Submitted for publication, 2018.
• A. Lavaei, S. Soudjani, and M. Zamani, “Compositional Construction of Infinite Abstractions for Networks of Stochastic Control Systems”. Submitted for publication, 2018. [Preprint]
• A. Lavaei, S. Soudjani, and M. Zamani, “Compositional Synthesis of Finite Abstractions for Continuous-Space Stochastic Control Systems: A Small-Gain Approach”, in Proceedings of the 6th IFAC Conference on Analysis and Design of Hybrid Systems (ADHS), vol. 51, no. 16, pp. 265-270, 2018.
• A. Lavaei, S. Soudjani, and M. Zamani, “Compositional Synthesis of Interconnected Stochastic Control Systems based on Finite MDPs”, in Proceedings of the 21st ACM International Conference on Hybrid Systems: Computation and Control (HSCC), pp. 273-274, 2018.
• A. Lavaei, S. Soudjani, and M. Zamani, “From Dissipativity Theory to Compositional Construction of Finite Markov Decision Processes”, in Proceedings of the 21st ACM International Conference on Hybrid Systems: Computation and Control (HSCC), pp. 21-30, 2018. [Preprint]
• A. Lavaei, S. Soudjani, R. Majumdar, and M. Zamani, “Compositional Abstractions of Interconnected Discrete-Time Stochastic Control Systems”, in Proceedings of the 56th IEEE Conference on Decision and Control (CDC), pp. 3551-3556, 2017. [Preprint]
• A. Lavaei, and M.A. Atashgah, “Optimal 3D Trajectory Generation in Delivering Missions under Urban Constraints for a Flying Robot”, Intelligent Service Robotics, vol. 10, no. 3, pp. 241-256, 2017.
• Kosari, Amirreza, H. Maghsoudi, and A. Lavaei, “Path Generation for Flying Robots in Mountainous Regions”, International Journal of Micro Air Vehicles, vol. 9, no. 1, pp. 44-60, 2017.
• M.A. Atashgah, H. Gazerpour, A. Lavaei, and Y. Zarei, “An Active Time-optimal Control for Space Debris Deorbiting via Geomagnetic Field”, Celestial Mechanics and Dynamical Astronomy, vol. 128, no. 2-3, pp. 343-360, 2017.
• M.A. Atashgah, M.R. Torkamani, and A. Lavaei, “Robust Positioning, Preliminary Orbit Determination, and Trajectory Prediction of Space Debris using In-Space Iterative-Bearing-Only Observations”, The Journal of Navigation, vol. 70, no. 4, pp. 789-809, 2017.
• A. Lavaei, and M.A. Atashgah, “Three-Dimensional Constrained Optimal Motion Planning for a Six-Degree-of-Freedom Quadrotor for Urban Traffic Purposes”, Modares Mechanical Engineering, Vol. 15, No. 5, pp. 13-24, 2015.
• A. Kosari, H. Maghsoudi, A. Lavaei, and R. Ahmadi, “Optimal Online Trajectory Generation for a Flying Robot for Terrain Following Purposes using Neural Network”, Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering, vol. 229, no. 6, pp. 1124-1141, 2014.
• July 11-13, 2018: 6th IFAC Conference on Analysis and Design of Hybrid Systems (ADHS), Oxford, United Kingdom.
• April 11-13, 2018: 21st ACM International Conference on Hybrid Systems: Computation and Control (HSCC), Porto, Portugal.
• December 12-15, 2017: 56th IEEE Conference on Decision and Control (CDC), Melbourne, Australia.