Alex Mitrevski

PhD Student, Research Associate b-it and MigrAVE, Team Leader b-it-bots@Home

Field of research

Robot fault diagnosis and fault tolerance with a focus on learning-based methods

PhD topic: Skill Generalisation and Experience Acquisition for Predicting and Avoiding Execution Failures supervised by Prof. Dr. Gerhard Lakemeyer and Prof. Dr. Paul G. Plöger

Contact

Porträt Aleksandar Mitrevski, wissenschaftlicher Mitarbeiter Informatik
Email: 
aleksandar.mitrevski [at] h-brs.de

Sankt Augustin

Grantham-Allee 20
53757
Sankt Augustin
Room: 
C201

Profile

Research interests

  • Knowledge representation and reasoning (knowledge retrieval, forgetting mechanisms, template- and case-based reasoning)
  • Lifelong robot learning
  • Simulation-based robot learning and reasoning
  • Robot fault detection and diagnosis
  • Cognitive robotics

Teaching

  • SS 2021
    • TA Mathematics for Robotics and Control
    • Project coach Software Development Project
  • WS 2020
    • TA Mathematics for Robotics and Control
    • Project coach Software Development Project
  • SS 2020
    • TA Mathematics for Robotics and Control
    • Project coach Software Development Project
  • WS 2019
    • Lecturer Research and Development Colloquium
    • TA Mathematics for Robotics and Control
  • SS 2019
    • Lecturer Fault Detection and Diagnosis
  • WS 2018
    • TA Mathematics for Robotics and Control
    • TA Scientific Experimentation and Evaluation
  • SS 2018
    • Lecturer Research and Development Colloquium (together with Argentina Ortega)
    • TA Mathematics for Robotics and Control
    • TA Scientific Experimentation and Evaluation
  • WS 2017/18
    • TA Mathematics for Robotics and Control
    • TA Scientific Experimentation and Evaluation
  • SS 2017
    • TA Probabilistic Methods for Robotics
    • TA Mathematics for Robotics and Control (together with Santosh Thoduka)
    • TA Scientific Experimentation and Evaluation (together with Santosh Thoduka)

Co-supervised master's theses

  • Visuomotor policy learning for predictive manipulation
  • Robust environment sound classification and anomaly detection using deep learning
  • owards improvements on RoboCup@Home robots architecture, capabilities and development process

Co-supervised R&D projects

  • Incorporating contextual knowledge into human-robot collaborative task execution
  • Learning corrective models for multistep actions by analysing videos
  • Registering and visualizing point cloud data with existing 3D CityGML Models
  • A comparative analysis of fault detection approaches in mobile robots
  • Tell your robot what to do: Evaluation of natural language models for robot command processing
  • Manipulating Handles in Domestic Environments
  • Learning grasp evaluation models using synthetic 3D object-grasp representations
  • Dynamic motion primitives
  • Ontology-Based Robot Fault Diagnosis
  • Automated Test Generation for Robot Self-Examination
  • Semantic information by acoustic clues: A modern approach to anomaly detection for robotics

Publications