Recent advances in Artificial Intelligence (AI) have enabled exciting applications, which are now playing important roles in everyday life ranging from language translation and image processing to recommender systems and autonomous driving. Most applications are based on Machine Learning (ML), which achieved great successes due to increasingly available computational resources and data. The current trend of AI offers numerous opportunities to contribute within areas of research, theory, technology, and application. In TRAIL, we investigate different directions of AI and ML to provide novel methods and insights to pave the way for future applications and technologies.
Structure
1. Overview
In TRAIL, we regard the term intelligence with respect to the behaviour of an entity. For simplification we assume an entity to be intelligent if it is able to learn from past experience, to think about future events or actions, and to act according to its knowledge, thoughts, and interaction with other entities. Our research in TRAIL focuses on these three main aspects:
Learn
Learning is the process of extracting knowledge from data which represents past experience. The knowledge can be used to identify salient patterns or structures in data or to make predictions. Machine Learning is currently the most active field in AI and has achieved tremendous progress in various domains over the last decade.
Publications
- Felip Guimerà Cuevas, Thomy Phan, Helmut Schmid, „Adaptive Bi-Nonlinear Neural Networks Based on Complex Numbers with Weights Constrained along the Unit Circle“, in PAKDD 2023, to appear.
- Robert Müller, Steffen Illium, Thomy Phan, Tom Haider, and Claudia Linnhoff-Popien, „Towards Anomaly Detection in Reinforcement Learning“, in AAMAS 2022 Blue Sky Ideas.
- Thomas Gabor, Steffen Illium, Maximilian Zorn, and Claudia Linnhoff-Popien, „Goals for Self-Replicating Neural Networks“, in ALIFE 2021.
- Robert Müller, Steffen Illium, and Claudia Linnhoff-Popien, „Deep Recurrent Interpolation Networks for Anomalous Sound Detection“, in IJCNN 2021, pp. 1-7.
- Steffen Illium, Robert Müller, Andreas Sedlmeier, and Claudia Linnhoff-Popien, „Surgical Mask Detection with Convolutional Neural Networks and Data Augmentations on Spectrograms“, in INTERSPEECH 2020, pp. 2052-2056
- Fabian Ritz, Felix Hohnstein, Robert Müller, Thomy Phan, Thomas Gabor, Claudia Linnhoff-Popien, and Carsten Hahn, „Towards Ecosystem Management from Greedy Reinforcement Learning in a Predator-Prey Setting“, in ALIFE 2020, pp. 518-525.
- Sebastian Feld, Andreas Sedlmeier, Markus Friedrich, Jan Franz, Lenz Belzner, „Bayesian Surprise in Indoor Environments“, in SIGSPATIAL 2019, pp. 129-138
- Daniel Elsner, Stefan Langer, Fabian Ritz, Robert Müller and Steffen Illium, „Deep Neural Baselines for Computational Paralinguistics“, in INTERSPEECH 2019, pp. 2388-2392
- Thomas Gabor, Steffen Illium, Andy Mattausch, Lenz Belzner, Claudia Linnhoff-Popien, „Self-Replication in Neural Networks“, in ALIFE 2019, pp. 424-431
- Thomas Gabor, Andreas Sedlmeier, Marie Kiermeier, Thomy Phan, Marcel Henrich, Monika Picklmair, Bernhard Kempter, Cornel Klein, Horst Sauer, Reiner Schmid, and Jan Wieghardt, „Scenario Co-Evolution for Reinforcement Learning on a GridWorld Smart Factory Domain“, in GECCO 2019, pp. 898-906
- Markus Friedrich, Pierre-Alain Fayolle, Thomas Gabor, Claudia Linnhoff-Popien, „Optimizing Evolutionary CSG Tree Extraction“. in GECCO 2019, pp. 1183-1191
- Sebastian Feld, Steffen Illium, Andreas Sedlmeier, Lenz Belzner, „Trajectory Annotation using Sequences of Spatial Perception“, in SIGSPATIAL 2018, pp. 329-338
Think
The goal of Thinking is to solve problems via explicit reasoning given a problem model, rules, or a simulator. Planning and Scheduling represent common classes of problem solvers and are often used for complex tasks like routing, task allocation, and decision making.
Publications
- Thomas Gabor, Thomy Phan, and Claudia Linnhoff-Popien, „Productive Fitness in Diversity-Aware Evolutionary Algorithms“, in NACO 2021
- Carsten Hahn, Sebastian Feld, and Hannes Schroter, „Predictive Collision Management for Time and Risk Dependent Path Planning“, in SIGSPATIAL 2020, pp. 405-408
- Thomy Phan, Thomas Gabor, Robert Müller, Christoph Roch, and Claudia Linnhoff-Popien, „Adaptive Thompson Sampling Stacks for Memory Bounded Open-Loop Planning“, in IJCAI 2019, pp. 5607-5613
- Thomas Gabor, Jan Peter, Thomy Phan, Christian Meyer, and Claudia Linnhoff-Popien, „Subgoal-Based Temporal Abstraction in Monte-Carlo Tree Search“, in IJCAI 2019, pp. 5562-5568
- Thomy Phan, Lenz Belzner, Marie Kiermeier, Markus Friedrich, Kyrill Schmid, and Claudia Linnhoff-Popien, „Memory Bounded Open-Loop Planning in Large POMDPs using Thompson Sampling“, in AAAI 2019, pp. 7941-7948
- Thomas Gabor, Lenz Belzner, and Claudia Linnhoff-Popien, „Inheritance-Based Diversity Measures for Explicit Convergence Control in Evolutionary Algorithms“, in GECCO 2018, pp. 841-848
Act
Acting of AI systems involves the process of making intelligent decisions based on knowledge learned from prior experience or explicit reasoning. Acting is also influenced by coexisting AI systems e.g., in a multi-agent system. Social interaction with humans is important to integrate AI into our everyday life.
Publications
- Thomy Phan, Fabian Ritz, Jonas Nüßlein, Michael Kölle, Lenz Belzner, and Claudia Linnhoff-Popien, „Attention-Based Recurrence for Multi-Agent Reinforcement Learning under State Uncertainty (Extended Abstract)“, in AAMAS 2023.
- Thomy Phan, Felix Sommer, Philipp Altmann, Fabian Ritz, Lenz Belzner, and Claudia Linnhoff-Popien, „Emergent Cooperation from Mutual Acknowledgment Exchange“, in AAMAS 2022.
- Thomy Phan, Fabian Ritz, Lenz Belzner, Philipp Altmann, Thomas Gabor, and Claudia Linnhoff-Popien, „VAST: Value Function Factorization with Variable Agent Sub-Teams“, in NeurIPS 2021.
- Kyrill Schmid, Robert Müller, Lenz Belzner, Johannes Tochtermann, and Claudia Linnhoff-Popien, „Stochastic Market Games“, in IJCAI 2021, pp. 384-390
- Fabian Ritz, Daniel Ratke, Thomy Phan, Lenz Belzner, and Claudia Linnhoff-Popien, „A Sustainable Ecosystem through Emergent Cooperation in Multi-Agent Reinforcement Learning“, in ALIFE 2021.
- Kyrill Schmid, Lenz Belzner, and Claudia Linnhoff-Popien, „Learning to Penalize Other Learning Agents“, in ALIFE 2021.
- Kyrill Schmid, Robert Mueller, Lenz Belzner, Johannes Tochtermann, and Claudia Linnhoff-Popien, „Distributed Emergent Agreements with Deep Reinforcement Learning“, in IJCNN 2021, pp. 1-8
- Thomy Phan, Lenz Belzner, Thomas Gabor, Andreas Sedlmeier, Fabian Ritz, and Claudia Linnhoff-Popien, „Resilient Multi-Agent Reinforcement Learning with Adversarial Value Decomposition“, in AAAI 2021, pp. 11308–11316
- Thomy Phan, Thomas Gabor, Andreas Sedlmeier, Fabian Ritz, Bernhard Kempter, Cornel Klein, Horst Sauer, Reiner Schmid, Jan Wieghardt, Marc Zeller, and Claudia Linnhoff-Popien, „Learning and Testing Resilience in Cooperative Multi-Agent Systems“, in AAMAS 2020, pp. 1055-1063
- Carsten Hahn, Fabian Ritz, Paula Wikidal, Thomy Phan, Thomas Gabor, Claudia Linnhoff-Popien, „Foraging Swarms using Multi-Agent Reinforcement Learning“, in ALIFE 2020, pp. 333–340.
- Christoph Roch, Thomy Phan, Sebastian Feld, Robert Müller, Thomas Gabor, Carsten Hahn, and Claudia Linnhoff-Popien, „A Quantum Annealing Algorithm for Finding Pure Nash Equilibria in Graphical Games“, in ICCS 2020.
- Carsten Hahn, Thomy Phan, Thomas Gabor, Lenz Belzner, and Claudia Linnhoff-Popien, „Emergent Escape-based Flocking Behavior using Multi-Agent Reinforcement Learning“, in ALIFE 2019, pp. 598–605
- Thomy Phan, Kyrill Schmid, Lenz Belzner, Thomas Gabor, Sebastian Feld, and Claudia Linnhoff-Popien, „Distributed Policy Iteration for Scalable Approximation of Cooperative Multi-Agent Policies (Extended Abstract)“, in AAMAS 2019, pp. 2162-2164
- Kyrill Schmid, Lenz Belzner, Thomas Gabor, and Thomy Phan, „Action Markets in Deep Multi-Agent Reinforcement Learning“, in ICANN 2018, pp. 240-249
- Thomy Phan, Lenz Belzner, Thomas Gabor, and Kyrill Schmid, „Leveraging Statistical Multi-Agent Online Planning with Emergent Value Function Approximation“, in AAMAS 2018, pp. 730-738
2. Projects and Activities
Projects
Current Projects
- AI-Fusion (Fraunhofer IKS)
- Modular Machine Learning (Siemens)
Past Projects
- Federated Decentralized Learning 2 (Siemens)
- Federated Decentralized Learning 1 (Siemens)
- Constrained Graphs For Optimal Flow (Telekom)
- Dependability of Machine Learning in Industrial Environments 2 (Siemens)
- Dependability of Machine Learning in Industrial Environments 1 (Siemens)
- ErLoWa: Recognition and Localization of of Leaks in Water Networks (SWM)
- Engineering of Decentralized Systems (Siemens)
3. Teaching
We offer a diverse set of lectures and practical courses with each covering different areas of AI.
- Intelligent Systems (Lecture): SS 2019, SS 2020, WS 2022/23
- Natural Computing (Lecture): SS 2022
- Computational Intelligence (Lecture): WS 2022/23
- Autonomous Systems (Practical Course): SS 2019, WS 2019/20, SS 2020, WS 2020/21, SS 2021, WS 2021/22, SS 2022, WS 2022/23
- Affective Computing (Practical Course): SS 2017, WS 2017/18, SS 2018, WS 2018/19, SS 2019, WS 2019/20, SS 2020, WS 2020/21, SS 2021, WS 2021/22, SS 2022, WS 2022/23
- Innovative Mobile Applications (Practical Course): WS 2015/16, SS 2016, WS 2016/17, SS 2017, WS 2017/18, SS 2018, SS 2019
- Artificial Intelligence (Seminar): SS 2017
- Artificial Intelligence (Working Group): SS 2019, WS 2019/20, SS 2020, WS 2020/21, SS 2021, WS 2021/22, SS 2022, WS 2022/23
Students eligible to attend these courses have the opportunity to learn about the theoretic aspects of AI and to practice their skills by implementing and evaluating algorithms. Courses are occasionally held in cooperation with industrial partners to enable our students to gain further experience. Especially skilled students are offered to actively participate in TRAIL by carrying out individual research projects or writing their theses about exciting topics in the field of AI.
4. The TRAIL Team of Experts

Thomy Phan
(Head)