direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Wissenschaftlicher Mitarbeiter und Doktorand

Lupe

I finished my Master's degree in Electrical Engineering, specializing in Robotics and Telecommunication, at the Technical University of Berlin in Germany in 2018 and started the same year at the Chair Industry Grade Networks and Clouds, TU Berlin as a research scientist and PhD student. My research focuses on applications of Reinforcement Learning and Computer Vision for autonomous navigation.

For students, I offer the supervision of bachelor/master theses on interesting topics about robotics, computer vision, and AI. Topics are related to computer vision and autonomous navigation and include, for instance, deep learning for object recognition, localization, sensor fusion, reinforcement learning for navigation, industrial process automation and optimization. Please pay attention to open topics on page "Abschlussarbeiten" in "Studium und Lehre" Section. For any questions or if you are interested, please get in contact with me via linhdoan(at)win.tu-berlin.de or .

 

Please visit my personal website linhdoan.io for more information about my projects.

 

Publications (Selection)

2022

Arena-Bench: A Benchmarking Suite for Obstacle Avoidance Approaches in Highly Dynamic Environments
Accepted for IEEE Robotics and Automation Letters, 2022
Authors: Linh Kästner, Teham Bhuiyan, Tuan Anh Le, Elias Treis, Johannes Cox, Boris Meinardus, Jacek Kmiecik, Reyk Carstens, Duc Pichel, Bassel Fatloun, Niloufar Khorsandi, Jens Lambrecht


All-in-One: A DRL-based Control Switch Combining State-of-the-art Navigation Planners
Proceedings of the 2021 IEEE International Conference on Robotics and Automation ICRA22, Philadelphia, USA
Authors:
Linh Kästner, Johannes Cox, Teham Buiyan, Jens Lambrecht

 

Enhancing Navigational Safety in Crowded Environments using Semantic-Deep-Reinforcement-Learning-based Navigation
Proceedings of the 2021 IEEE International Conference on Robotics and Automation ICRA22, Philadelphia, USA
Authors:
Linh Kästner, Bassel Fatloun, Daniel Gawrisch, Jens Lambrecht

 

https://arxiv.org/search/cs?searchtype=author&query=K%C3%A4stner%2C+L

2021

Arena-Rosnav: Towards Deployment of Deep-Reinforcement-Learning-Based Obstacle Avoidance into Conventional Autonomous Navigation Systems
Proceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems IROS21, Praque, Czech Republik
Authors:
Linh Kästner, Teham Buiyan, Xinlin Zhao, Lei Jiao, Tuan Anh Le, Zhengcheng Shen, Jens Lambrecht

 

Connecting Deep-Reinforcement-Learning-based Obstacle Avoidance with Conventional Global Planners using Waypoint Generators
Proceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems IROS21, Praque, Czech Republik
Authors:
Linh Kästner, Teham Buiyan, Xinlin Zhao, Zhengcheng Shen, Cornelius Marx, Jens Lambrecht

 

Spatial Imagination With Semantic Cognition for Mobile Robots
Proceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems IROS21, Praque, Czech Republik
Authors:
Zhengcheng Shen, Linh Kästner, Jens Lambrecht

 

2020

A 3D-Deep-Learning-based Augmented Reality Calibration Method for Robotic Environments using Depth Sensor Data
Proceedings of the IEEE/RSJ International Conference on Robotics and Automation (ICRA), Paris
Authors: Linh Kästner, Vlad Catalin Frasineanu, Jens Lambrecht

 

Memory-Aided Deep-Reinforcement-Learning-based Navigation in Complex Environments
Proceedings of the IEEE/RSJ International Symposium on System Integration (SII), Fukushima
Authors: Linh Kästner, Cornelius Marx, Jens Lambrecht

 

Deep Reinforcement Learning Semantic Navigation in Highly Dynamic Environments
Proceedings of the IEEE/RSJ International Conference on Automation Science and Engineering (CASE), Hong Kong
Authors: Linh Kästner, Cornelius Marx, Jens Lambrecht

 

A Markerless Deep Learning-based 6 Degrees of Freedom PoseEstimation for with Mobile Robots using RGB Data
Proceedings of the 6th IEEE International Conference on Control, Automation and Robotics (ICCAR 2020), Singapore
Authors: Linh Kästner, Daniel Dimitrov, Jens Lambrecht

 

2019

Augmented-Reality-Based Visualization of Navigation Data of Mobile Robots on the Microsoft Hololens -- Possibilities and Limitations
Proceedings of the 9th IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and the 9th IEEE International Conference on Robotics, Automation and Mechatronics (RAM), Bangkok
Authors: Linh Kästner, Jens Lambrecht

 

 

For a full list of publications, please visit my Website, Google Scholar or Researchgate profile.

 

Curriculum Vitae

2018 -
TU Berlin Fachgebiet Industry Grade Networks and Clouds, PhD Student & Research Asisstant

03.2018 - 10.2018
Fraunhofer Research Institute Fokus/HHI, Student Researcher

05.2017 - 03.2018
Corning Incorporated, Student Researcher

10.2014 - 10.2018
B.Sc. and MSc. Electrical Engineering at TU Berlin, Grade 1.3 (Excellent, GPA: 3.7/4)

 

 

Zusatzinformationen / Extras

Direktzugang

Schnellnavigation zur Seite über Nummerneingabe

Contact

M.Sc. Linh Kästner
Doktorand
Fakultät 4
Sekr. TEL 18-1
Raum Flores (17.Stock)
Ernst-Reuter-Platz 7
10587 Berlin
+49 30 835358412
linhdoan.io

Webseite