Open Student Thesis Offers
When writing your thesis at TUM I6, please follow our thesis guidelines. A guide to writing good thesis can be found here. A collection of useful material for research can be found here.
Autonomous Vehicles
The Cyber Physical Systems group is pursuing a wide range of research directions related to safe decision making, motion planning and control for autonomous vehicles, involving both formal methods, sampling- and optimization-based methods as well as learning-based methods.
Currently, the following thesis proposals are open:
- [MA] Encoding the Future: Deep Representations for Traffic using Graph Neural Networks
- [MA] Deep Generative Models for Road Network Synthesis
- [BA/MA] Learning Isometric Embeddings of Road Networks using Multidimensional Scaling
- [MA] Efficient Trajectory Repairing for Autonomous Vehicles Regarding Traffic Rule Violations
Spiking Neural Networks - Next Generation AI for Autonomous Driving
At the KI-ASIC project we are researching about the application of bio-inspired neural networks to real-world applications.
If you are interested in learning about neuroscience and how neuromorphic engineering is trying to narrow the gap between biology an technology, do not hesitate to contact us.
You can take a look to our currently open thesis proposals:
- Study and implementation of time-based spiking neuron models
- Implementation of a real-time SNN in Intel’s Loihi
- Design of an electronic circuit for converting sensor data into spikes
Autonomous Path Planning in Robotics
Currently open positions:
Additionally, we will have open topics in safe reinforcement learning for manipulators and mobile platforms in the future.
If you are interested in these topics, you can contact: jakob (dot) thumm (at) tum.de
Modular Robotics
For interest in a BA/MA thesis in machine learning for modular robotics, please contact Jonathan Kuelz.
We also offer industrial thesis with the startup RobCo. For the current thesis offered with RobCo please have a look at their website. For general interest in a Bachelors or Masters Thesis with RobCo, please follow this link.
Formal Methods and Reachability Analysis
Real-time Operating Systems
Neurorobotics in the Human Brain Project
- Spiking Neural Networks with Random Backpropagation
- Hierarchical Robot Motion Control with Spiking Neural Networks
- Classical Conditioning with a simulated Robot and Spiking Neural Networks
- Robot Control with Embodied Learning Rules in Spiking Neural Networks
- [Forschungspraktikum] Human Walking Analysis and Animation in Simulation
- [Forschungspraktikum] Robot Control with Cognitive Architecture ACT-R
- Developmental Body Modeling in Soft Robotics
- Cloud-Based Robotics for Machine Learning
- Virtual Neurorobotics with Intel Loihi
- Spiking Compliant Robot Control with Intel Loihi
- Integration of the Neural Simulator NEST into the Neurorobotics Platform
- Hierarchical Temporal Memory (HTM) with Spiking Neural Networks
- Deep Spiking Q-Networks
- Autonomous Locomotion Control for Snake Robot Based on Bio inspired Vision Sensor and Spiking Neural Network
- Advanced Autonomous Driving Control Based on Bio inspired Vision Sensor and Spiking Neural Network
- Spiking Neural Network for Autonomous Navigation based on LiDAR Sensor
- Deep Spiking Reinforcement Learning
- Learning adaptive target reaching with Recurrent Neural Networks
Providentia++ - A Testbed for Autonomous Driving
- Real-Time and Robust 3D Object Detection on the Autonomous Driving Test Stretch Using LiDAR Point Cloud Data
- Real-Time and Multi-Modal 3D Object Detection on the Autonomous Driving Test Stretch Using Camera and LiDAR Sensors
- Deep Traffic Scenario Mining, Detection, Classification and Generation on the Autonomous Driving Test Stretch using the CARLA Simulator
- Real-Time Camera-Only 3D Object Detection for Autonomous Driving
- Sensor Fusion and Vehicle Tracking for Intelligent Transportation Systems
- Adaptive Data Distribution Services, V2X Communication Protocols, Channel Quality Prediction and Optimal Resource Allocation
- Highly Scalable Software Architecture for Intelligent Transportation Systems
- Automated Camera Stabilization and Calibration for Intelligent Transportation Systems
Reinforcement Learning, Representation Learning, Meta-RL and Robotics
Three of our DEMOs can be found at https://sites.google.com/view/kuka-environment/ , https://sites.google.com/view/cemrl, and https://videoviewsite.wixsite.com/rlsnake.
- [BA/MA] Meta Reinforcement Learning in Dynamic Environment
- [BA/MA] Complex Robotic Manipulation via Actionable Representation Learning Guided Exploration
- [BA/MA] Reinforcement Learning via Hindsight Experience Replay (HER)
- [BA/MA] Reinforcement Learning for Adaptive Locomotion of Snake-like Robot
- [BA/MA] Energy-Efficient Gait Exploration for Snake-like Robots Based on Adversarial Reinforcement Learning
- [MA/GR] Vision-Based Continual Reinforcement Learning for Robotic Manipulation Tasks
- [BA/MA] Imitation Learning via Demonstration
We have seveal other open topics in the domain of reinforcement learning in robotics and we also accept open proposals or ideas with yourselves. For more information, please contact Zhenshan Bing.
Neural SLAM and Biomimetic Rodent Robot
- [MA/BA] Design and Control of a Rat Robot with Actuated Spine and Ribs
- [MA/BA] Biologically Plausible Spatial Navigation (NeuralSLAM)
- [MA/BA] Brain-inspired Localization and Mapping based on LiDAR Sensor
For more information about this topic, please contact Zhenshan Bing and Florian Walter.
Machine Learning Algorithms for Hybrid Vehicle Data
Please see this page for the available topics about 3D Object Detection and Tracking.
Project SunRISE: Anomaly Detection in Time-Sensitive Networks
Autonomous Robot & Visual Servo & Deep Learning & Robot Design & Medical Robotics
For more information, please visit my homepage Mingchuan Zhou or contact me via email (zhoum@in.tum.de).
Data Analysis and Deep Learning in Robot-Based Additive Manufacturing
BA / IDP / MA - partly in cooperation with Siemens AG
For more information, please visit my homepage Raven Reisch or contact me via email (raven.reisch@tum.de).
OSBORNE (Future Automotive E/E Architectures for Autonomous Cars)
We have a set of open topics in the domain of affective computing and multimodal emotion recognition, within the context of OSBORNE project, for more information please contact Sina.
HORSE / REMODEL
We have several open topics related to computer vision in the HORSE and REMODEL projects. Please contact Arne for more details.
Machine Learning, Robustness and Safety
TBD, please contact Thomas Brunner.
Collaboration with Chair for Product Development and Lightweight Design
External thesis proposals
- Masterthesis – Grey-Box Modellierung und Validierung des Motoraufheizverhaltens auf dem Rollenprüfstand und im Fahrzeug mittels Machine Learning
- [MA] Behavior Planning for Autonomous Driving by Combining Neural Networks and Tree Search (ZF Friedrichshafen AG)
- [MA] Hybrid Parallel Online POMDP Decision Making for Lane Changes in Urban Areas (ZF Friedrichshafen AG)