Hi there!
I am Firas.
On this page you will find some information about me. In case you are interested in a more detailed CV, click on the button below (updated on 12.11.2024).
Quick
Links
If you want to checkout my latest projects, publications, videos or simply want to contact me, checkout the links on the right.
Latest Tweets
Publications
My
Education
Ph.D. Student at the Intelligent Autonomous Systems Group
TU Darmstadt, Germany
Robot Learning
Master of Science
TU Braunschweig, Germany
Electronic Systems
Master of Science
TU Braunschweig, Germany
Mechanical Engineering Field Automotive Engieering
Bachelor of Science
TU Braunschweig, Germany
Industrial Engineering Field Mechanical Engineering
My
Experience
and Process Control
(2. Master Thesis)
Comparison of reinforcement learning algorithms and evolution strategies for joint-space robotic manipulation. Training a pose estimator for real-world objects based on simulated data only. Introducing redundancy resolution to policy search to yield saver and more natural-looking policies. Evaluation on a simulated and real Franka Emika Panda robot arm.
(1. Master Thesis)
Development of a tactical maneuver planner for automated urban driving using deep reinforcement learning and tree search algorithms. Combining deep reinforcement learning and dynamic programming to speed-up training and enhance the overall performance.
Development of a modular simulation environment for tactical maneuver planning in urban scenarios.
(i.e, Bachelor Thesis)
Development of a plug-in hybrid fuel cell drive train model for tank-to-wheel energy comparisons to other conventional, hybrid and battery-electric drivetrains.
Technical
Skills
Robot Learning Workshop
I am excited to announce that I will be co-organizing the Next-Gen Robot Learning Symposium at the Technical University of Darmstadt on 4th November 2024!
Paper accepted at HUMANOIDs!
Our paper, Exciting Action: Investigating Efficient Exploration for Learning Musculoskeletal Humanoid Locomotion, was accepted at the International Conference on Humanoid Robots. In this work, we
Paper accepted at ICLR!
Our Paper, Time-Efficient Reinforcement Learning with Stochastic Stateful Policies, was accepted at the International Conference on Learning Representations (ICLR) 2024! We introduce a novel training