Research Associate in "Perception, decision making and control of autonomous systems in robotics" (m/w/d)
Contributed by: Naim Bajcinca, mec-apps@mv.uni-kl.de
Research Framework
Research on autonomous systems in robotics combines traditional and modern control techniques with artificial intelligence (AI) by considering a holistic system characterised by sensor-based perception, AI-driven decision making, followed be the actuator-based physical interaction with the environment. This multifaceted research opportunity involves conducting in-depth investigations, designing experiments, and developing algorithms to improve the capabilities of autonomous systems. The tasks encompass challenges in different domains, such as environment perception, scene understanding, sensor fusion, modeling, data analysis and simulation. Researchers in perception and decision-making for autonomous systems play a critical role in developing safe and efficient algorithms, tighty coupled with control algorithms to finally ensure safe and accurate task and action execution.
Task Description
Research activities in this field involve a combination of theoretical work, software and hardware development, algorithm implementation, testing, and evaluation.
- Review the literature in the field of perception, scene understanding and decision making for autonomous systems,
- Literature review in the related fields followed by trainining and evaluation of deep/machine learning models like semantic scene segmentation and object detection
- Develop and implement deep/machine learning models for scene understanding, object detection, tracking
- Model the detected static and dynamic objects in an interactive graph and build graph neural networks for scene understanding
- Representing the interactive graph as a spatial-temporal graph of the environment that can be used for a safe path planning and decision-making
- Working with different sensors like LiDAR, cameras, and radar.
- Explore and experiment with mRulti-task learning techniques to simultaneously handle various tasks, such as lane detection, object recognition, and traffic sign identification
- Integrate and test the developed algorithms in real time on test vehicle
Qualification
- Above average university degree in computer engineering, computer science, or mathematics
- Advanced computer vision skills
- Practical experience with convolutional neural networks, graph neural networks and deep learning libraries e.g. Pytorch, Tensorflow
- Excellent programming skills in Python or C++
- Proven research experience in the field of computer vision
- Organizational and cooperation skills with scientific as well as industrial partners of different disciplines
- Proficiency in English or / and German is essential
Application procedure and deadline:
Applications must include the following elements (as a single PDF file):
- Cover letter with a brief description of why you want to pursue research studies, about what your academic interests are, and how they relate to your previous studies and future goals
- CV including your relevant professional experience and knowledge
- Copies of diplomas and grades from previous university studies
- Two references
- List of publications
Send an email with the required documents to the address: @mec-apps@mv.uni-kl.de. We will process your application as soon as received. The application deadline is 12:00AM CEST 30. June 2024.
For more information, visit our webpage: https://mv.rptu.de/fgs/mec/research
