Anastasios Lekkas
Background and activities
I am an associate professor of autonomous systems at the Department of Engineering Cybernetics (ITK), where one of my main goals is to merge Artificial Intelligence (AI) methods with control engineering and develop cyber-physical systems of increased autonomy. My main application areas are surface and underwater marine vehicles. I serve as supervisor for PhD and MSc students and have co-developed a specialization course on autonomous systems.
Moreover, I am project manager for the EXAIGON project, which is funded by the Research Council of Norway (RCN) and aims at developing explainable AI systems for business-critical applications. EXAIGON will run between 2020-24 and has a total budget of 20 MNOK (around $2.2 million), of which 16 MNOK is funded by RCN.
Work Experience
01/2018 - Present: Associate professor of autonomous systems at ITK/NTNU.
12/2016 - 12/2018: EU affairs manager at NTNU Oceans.
12/2016 - 12/2017: Researcher at the Department of Marine Technology, NTNU.
08/2015 - 05/2019: Coordinator of the JPI Oceans action "European Marine Sensor Calibration Network".
02/2015 - 12/2016: Science officer at JPI Oceans Secretariat in Brussels, Belgium.
03/2014 - 01/2015: Postdoctoral researcher at the Centre of Excellence NTNU AMOS (Autonomous Marine Operations and Systems).
08/2009 - 03/2014: PhD candidate at ITK and the Centre of Excellence CeSOS (Centre for Ships and Ocean Structures)
09/2008 - 08/2009: Research associate at the Stochastic Mechanical Signals and Automation laboratory, University of Patras, Greece.
Education
2014: PhD in Engineering Cybernetics, NTNU, Norway.
2008: Diploma (5-year study) in Mechanical and Aeronautical Engineering, University of Patras, Greece.
Supervision
PhD Students
Main Supervisor:
- Andreas Bell Martinsen (2018-21) - Reinforcement learning methods for guidance, navigation and control of marine vehicles.
- Libo Xue (2018-21): AI planning and control for underwater intervention drones (part of SEAVENTION project).
- Vilde Gjærum 2019-22: Explainable AI methods for cyber-physical systems (part of the EXAIGON project)
- Sindre B. Remman 2020-24: Explainable AI methods for cyberphysical systems (part of the EXAIGON project)
Co-supervisor
- Glenn Ivar Bitar (2017-20) - Energy-optimal and autonomous control for car ferries (Main supervisor: Morten Breivik)
- Emil Hjelseth Thyri (2019-22): Automation and autonomy for all-electric autonomous passenger ferries (part of the project NTNU Autoferry. (Main supervisor: Morten Breivik))
MSc Students
- 2020-21 Supervision of 5 students (AI and control, Explainable AI, autonomous ships)
- 2019-20 Supervision of 11 MSc students within AI and control
-
2018-19: I supervise 8 MSc students who work on AI methods for autonomous ships, ROVS, robotic manipulators, and self-driving cars.
-
2017-18 Supervision of 5 MSc students (AI planning, deep learning, reinforcement learning)
Projects
2020-2024 EXAIGON (Project manager, WP leader)
2018-2021: SEAVENTION (WP participant and PhD student main supervisor)
2018-2021: NTNU Autoferry (WP participant and PhD student co-supervisor)
2013-2017: NextGenIMR (Postdoctoral researcher)
Courses
- TK8109 - Advanced Guidance, Navigation and Control
- TTK4192 - Mission Planning for Autonomous Systems
Scientific, academic and artistic work
Displaying a selection of activities. See all publications in the database
2020
- (2020) Hybrid Collision Avoidance for ASVs Compliant with COLREGs Rules 8 and 13-17. Frontiers in Robotics and AI. vol. 7 (11).
- (2020) Dynamic Wireless Charging of Autonomous Vehicles: Small-scale demonstration of inductive power transfer as an enabling technology for self-sufficient energy supply. IEEE Electrification Magazine. vol. 8 (1).
2019
- (2019) Energy-Optimized Hybrid Collision Avoidance for ASVs. 2019 18th European Control Conference (ECC).
- (2019) Warm-started optimized trajectory planning for ASVs. IFAC-PapersOnLine. vol. 52 (21).
- (2019) Autonomous docking using direct optimal control. IFAC-PapersOnLine. vol. 52 (21).
2018
- (2018) Energy-Optimized Path Planning for Autonomous Ferries. 11th IFAC Conference on Control Applications in Marine Systems, Robotics, and Vehicles CAMS 2018 Opatija, Croatia, 10–12 September 2018.
- (2018) Curved path following with deep reinforcement learning: Results from three vessel models. OCEANS 2018 MTS/IEEE Charleston.
- (2018) Straight-Path Following for Underactuated Marine Vessels using Deep Reinforcement Learning. 11th IFAC Conference on Control Applications in Marine Systems, Robotics, and Vehicles CAMS 2018 Opatija, Croatia, 10–12 September 2018.
2017
- (2017) 3D Path Following and Tracking for an Inspection Class ROV. Conference on Ocean & Arctic Engineering 2017 . The American Society of Mechanical Engineers; Trondheim. 2017-06-25 - 2017-06-30.
- (2017) A Voronoi-diagram-based dynamic path-planning system for underactuated marine vessels. Control Engineering Practice. vol. 61.
- (2017) Direct and Indirect Adaptive Integral Line-of-Sight Path-Following Controllers for Marine Craft Exposed to Ocean Currents. International Journal of Adaptive Control and Signal Processing. vol. 31 (4).
2016
- (2016) A 3D Dynamic Voronoi Diagram-Based Path-Planning System for UUVs. OCEANS 2016 MTS/IEEE Monterey.
- (2016) Online Path Planning for Surface Vehicles Exposed to Unknown Ocean Currents Using Pseudospectral Optimal Control. IFAC-PapersOnLine. vol. 49 (23).
2015
- (2015) Outlier Rejection in Underwater Acoustic Position Measurements Based on Prediction Errors. 4th edition of IFAC workshop on navigation, guidance and control of underwater vehicles, . IFAC; Girona. 2015-04-28 - 2015-04-30.
2014
- (2014) Guidance and Path-Planning Systems for Autonomous Vehicles. Norges teknisk-naturvitenskapelige universitet. 2014. ISBN 978-82-326-0176-9. Doktoravhandlinger ved NTNU (126).
- (2014) Integral LOS Path Following for Curved Paths Based on a Monotone Cubic Hermite Spline Parametrization. IEEE Transactions on Control Systems Technology. vol. 22 (6).
- (2014) Minimization of Cross-track and Along-track Errors for Path Tracking of Marine Underactuated Vehicles. European Control Conference (ECC'14) ; Strasbourg. 2014-07-24 - 2014-07-27.
- (2014) Trajectory tracking and ocean current estimation for marine underactuated vehicles. Proceedings of the IEEE Conference on Control Applications.
2013
- (2013) A Quaternion-Based LOS Guidance Scheme for Path Following of AUVs. Elsevier IFAC Publications / IFAC Proceedings series.
- (2013) Continuous Curvature Path Planning using Voronoi diagrams and Fermat's spirals. Elsevier IFAC Publications / IFAC Proceedings series.
- (2013) Continuous-Curvature Path Generation using Fermat's Spiral. Modeling, Identification and Control. vol. 34 (4).
- (2013) Line-of-Sight Guidance for Path Following of Marine Vehicles. Advanced in Marine Robotics.
2012
- (2012) A Time-Varying Lookahead Distance Guidance Law for Path Following. 9th IFAC Conference on Maneouvring and Control of Marine Craft ; Arenzano. 2012-09-19 - 2012-09-21.