TUC
Conference2026Accepted
Beyond Either-Or Reasoning: Transduction and Induction as Cooperative Problem-Solving Paradigms
Zenkner, Janis, Sesterhenn, Tobias, Bartelt, Christian
ECML PKDD 2026Paper
CORE Labs
Labs for Cognitive
Robotics in Europe
Shared research infrastructure, joint projects, and a cross-national team advancing cognitive autonomous systems.
Explore the labsThe Initiative
One lab across three cities
CORE Labs runs shared laboratories in Goslar, Cluj-Napoca, and Rostock as a single facility. A joint compute cluster, common datasets, and a co-supervised student project programme let teams collaborate across borders.
This shared infrastructure turns three institutions into one coherent scientific platform for cognitive systems research.
Participating Institutions
Our labs operate as a unified distributed entity, sharing resources, data, and expertise to accelerate discovery.
Prof. Dr. Christian Bartelt
Principal Investigator
TU Clausthal
Dr. Christian Sacarea
Principal Investigator
Babeș-Bolyai University
Prof. Dr. Stefan Lüdtke
Principal Investigator
University of Rostock
Scientific Coordination
Lab leads
Our lab leads coordinate research and operational activities across our distributed locations.
David Szilagyi
TUC & UBB Operations
TU Clausthal / Babeș-Bolyai University
Leading operations fostering collaboration on autonomous systems and embodied robotics.
Physical AIEmbodied AILocomanipulationImitation Learning
Ashwin Nedungadi
Rostock Operations
University of Rostock
Leading robotics research at Rostock focusing on multi-modal egocentric perception, spatial reasoning, and robot learning.
Multi-Modal PerceptionSpatial ReasoningRobot Learning
Patrick Knab
Multimodal Methods Lead
TU Clausthal
Developing multimodal methods that fuse visual and language information to improve model robustness, generalization, and reasoning across diverse real-world tasks.
Multimodal LearningVision-Language ModelsCross-Modal Reasoning
Tim Grams
Policy Learning Lead
TU Clausthal
Researching Reinforcement Learning, Large Language Models, and Self-play algorithms for autonomous decision-making.
Reinforcement LearningImitation LearningLLMsSelf-play
Cognitive Robotics
Cognitive roboticsDynamic manipulationOperational intelligence
DyNAMO
Our research advances Cognitive Robotics by bridging perception, reasoning, and action. At the core is Dynamo, a comprehensive framework for dynamic manipulation and operational intelligence.
Dynamo is a cognitive robotic system built to adapt to unstructured environments and learn through interaction. By integrating foundation models with rigorous control theory, it achieves versatile, robust behavior in real-world settings.
VLA policyLeRobotJetson inference
Vial Sort
Language-conditioned vial sorting on a Waveshare SO-101 arm using a pi0 vision-language-action model fine-tuned with LoRA. Two experiments compare static versus domain-randomized training data.
A VLA-based pick-and-place pipeline built with LeRobot: the robot receives a natural language instruction, observes the workspace from three RGB camera views, and executes the requested vial arrangement on Jetson inference. The project studies whether randomized training data improves transfer when lighting, rack placement, and vial colors change.
RidgebackPerson trackingSensor fusion3D perception
Leader Following
Leader following on a Ridgeback mobile base: camera-based detection singles out a chosen person by appearance, while fused point-cloud perception tracks the leader and visualizes the intended follow path in RViz.
The Ridgeback picks one designated person out of a multi-person scene, then fuses camera detection with point-cloud perception to follow them through clutter. Two iterations compare 2D and full 3D sensing for environment understanding.
Coming Soon
Project Unknown
A new initiative building upon Video Joint Embedding Predictive Architectures.
Autonomous Driving
Our autonomous driving research combines cutting-edge algorithms with practical implementation, resulting in robust solutions for real-world scenarios.
Simulation
Traffic Network Builder
Interactive tools for constructing and simulating complex traffic networks to rigorously test autonomous systems.
Evaluation
Benchmarking Framework
A comprehensive benchmarking suite for evaluating autonomous driving algorithms across various metrics and scenarios.
Motion Planning
Real-Time Corridor Planning
Advanced corridor planning using cubic spirals for smooth, kinematically feasible trajectory generation in real-time.
Field Test
Real-World 1:10 Scale Autonomous Driving
Testing real-world 1:10 scale autonomous driving capabilities, showcasing reliable navigation and control.
CORE Labs
Research publications
A rotating preview of recent publications connected to CORE Labs. Open the archive for the full publication list across the CORE Network.
View all publications