Institute for Cognitive Systems - TU München

Institute for Cognitive Systems - TU München The Institute for Cognitive Systems deals with the fundamental understanding and creation of cognitive systems. Impressum: http://www.ei.tum.de/ics

Happy Holidays from ICS 2025!
23/12/2025

Happy Holidays from ICS 2025!

ICS wishes happy holidays!

🌏🤖 Robotic Worlds 🤖🌏The Design Museum at the Pinakothek der Moderne is set to host the exhibition "Robotic Worlds" from ...
29/11/2025

🌏🤖 Robotic Worlds 🤖🌏

The Design Museum at the Pinakothek der Moderne is set to host the exhibition "Robotic Worlds" from 28 November 2025 to 28 November 2027. The TUM - Institute for Cognitive Systems team is pleased to have collaborated with Die Neue Sammlung - The Design Museum on this exhibit. 🙏

https://lnkd.in/dAVcsNSU

This exhibition will showcase a variety of robot designs from around the globe, featuring notable highlights such as:

- iCub humanoid robot from Istituto Italiano di Tecnologia
- HRP-2 humanoid robot from Kawada Technologies Inc/National Institute of Advanced Industrial Science and Technology (AIST)/CNRS
- Pepper robot from SoftBank Robotics Japan/Aldebaran Robotics/United Robotics Group
- UR-5 cobot from Universal Robots
- e-skin 500 from intouch-robotics GmbH
- and many more robots! 🤖 🤖 🤖

We look forward to sharing these innovative designs with the public.


Technische Universität München - TUM

04/08/2025

The next Doctoral Research Seminar, which will be next Monday August 4th, given by Prof. Hyon on "Study on torque-controlled hydraulic and pneumatic robots for field applications".

🗓️ Time: August 4th 10:30–11:30
📍 Place: Seminar Room 2026 (Karlstr. 45)
🧪 Title: Study on torque-controlled hydraulic and pneumatic robots for field applications

📄 This talk presents design and control of various hydraulic robotics developed in my lab for 15 years aiming at field applications. The robots include hydraulic manipulators, bipeds, quadrupeds, electro-pneumatic hybrid exoskeleton, and water-hydraulic manipulators, which are all equipped with joint torque servo to realize desired impedance with humans and surrounding environments. 🤖💡🌍

06/02/2025

The next Doctoral Research Seminar, which will be next Monday February 10th, given by Prof. Jana Diesner on "Using Natural Language Processing to Advance Social Science, Responsibly" 🤖.

February 10th 10:30-11:30

Seminar Room 2026 (Karlstr. 45)

Bringing together methods from natural language processing (NLP) and network analysis to consider the content and structure of information allows us to discover and re-evaluate theories and patterns of societal behavior. In this process, researchers must make a multitude of decisions that require expertise in managing data provenance, including data ethics and data preparation, and implementing research designs, including integrating LLMs into pipelines to downstream tasks. I present findings and lessons learned from using mixed methods approaches, including methods such as entity resolution, relation extraction, labeling entities with socio-demographic meta data, and using LLMs for these processes, to study how and why researchers collaborate and how people respond to crises. I discuss sources of biases and strategies for mitigating them.

09/01/2025

The next Doctoral Research Seminar, which will be next Monday January 13th, given by Arturo Desaix López Rojas on "Using Neural Networks to Solve Optimal Control Problems in Online Applications" 🤖.

January 13th 10:30-11:30
Seminar Room 2026 (Karlstr. 45)

Optimization has become increasingly popular in robotic systems over the last two decades, driven by advancements in computational capabilities, enabling the calculation of paths, gaits, and other parameters to achieve desired behaviors. A prominent example is Model Predictive Control (MPC), which determines the optimal combination of control inputs based on a predefined cost function. However, one major limitation of these methods is the significant computation time required to solve optimization problems, often exceeding the system's sample time. To address this challenge, this work explores the use of Neural Networks (NNs) with supervised learning to approximate solutions, replacing traditional numerical iterative solvers. Neural Networks offer faster and more consistent ex*****on times, making them well-suited for time-critical applications. Our contributions include a theoretical framework based on the Karush-Kuhn-Tucker (KKT) optimality conditions, providing sufficient criteria for the reliable replacement of iterative solvers with neural networks.
To demonstrate the practicality of this approach, we present a case study involving load transportation using a two-drone formation. In this example, both the control and inverse kinematics of the system are computed using the proposed neural network-based method. This work highlights the potential of leveraging neural networks to overcome the computational limitations of conventional optimization methods in online robotic applications. 🤖🧠

24/12/2024

Happy Holidays 🎉 The Chair for Cognitive Systems at the Technical University of Munich wishes everyone a happy, blessed, and joyful Christmas season, as well as a fantastic start to the New Year! 🎄✨

🎙️ Exciting News! 🚀Prof. Gordon Cheng  is featured in the latest podcast episode: "Speed, Teamwork, Persistence: Insight...
17/12/2024

🎙️ Exciting News! 🚀

Prof. Gordon Cheng is featured in the latest podcast episode: "Speed, Teamwork, Persistence: Insights into the Medical Technology Boom" on , hosted by Thomas Kink, EPO examiner.

🎧 Listen here: https://creators.spotify.com/pod/show/european-patent-office/episodes/Speed--teamwork--persistence-insights-into-the-medical-technology-boom-e2s9dvs/a-abm9srh

Gain valuable insights into the rapid growth of

Leading Tech Voices: health & well-being EPO examiner Tom Kink leads a conversation with eminent inventors and scholars in the area of medical technologies, professors Gordon Chang and Chris Hancock. The talk highlights the significant increase in patent applications in medical technologies over the...

Our "artificial robotic skin" work will be featured on 3sat TV in the documentary "Fantastic Sense of Movement". 🤖 Thank...
12/10/2024

Our "artificial robotic skin" work will be featured on 3sat TV in the documentary "Fantastic Sense of Movement". 🤖

Thanks to the team Bilderfest for putting this together. 🙏



Wenlan Shen Armleder Julio Rogelio Guadarrama Olvera Gordon Cheng

Die Tiefensensibilität unseres Körpers ist eine Superkraft, ohne die wir im Alltag nicht funktionieren würden. Deshalb müssen wir diesen "sechsten Sinn" ein Leben lang trainieren.

20/09/2024

We are happy to welcome Prof. Daniel J. Preston from Rice University at TUM - Institute for Cognitive Systems on 27 September.
Prof. Preston will offer us an exciting guest talk.

Title: Material-Enabled Technologies for Soft and Fluidic Robots.

Abstract: The emerging field of soft robotics, which incorporates unconventional or compliant materials in autonomous systems, has simultaneously reshaped traditional robotics applications and introduced new use cases for robots. However, many useful classes of materials remain relatively unexplored, and furthermore, the vast majority of soft robotics research has targeted actuation and sensing, with power and control schemes still relying on bulky, rigid electronic components. My research program addresses open questions in these domains by applying our expertise in energy, fluids, and materials. For instance, biotic materials—non-living materials derived from living organisms—have remained underutilized in robotics, despite having played a role in human development since the times our early ancestors wore animal hides as clothing and used bones for tools. In the first part of my talk, I describe how we repurposed an inanimate spider as a ready-to-use actuator requiring only a single fabrication step, initiating the area of “necrobotics” in which biotic materials are used as robotic components. The second part of my talk focuses on assistive wearable robots, which currently rely on bulky and hard control systems and power supplies, or alternatively require cumbersome tethers to external infrastructure. To address this limitation, my group has developed completely soft fluidic digital logic components fabricated entirely from textiles. Our fluidic logic platform enables integrated memory, decision making, and the ability to interact with and adapt to stimuli and the environment, all without the use of rigid valves or electronics. Meanwhile, we address limitations in power delivery by developing “self-powered” textile-based wearable robots that harvest energy from the motion of the human body. The integration of fluidic logic and energy harvesting in textile architectures represents an important step toward fully soft, self-sufficient wearable robots that are as comfortable, resilient, and practical as everyday clothing.

Location: 2026, Karlstraße-Seminarraum (2906.02.026)
Time: 10:00 a.m.
Address: Karlstr. 45(2906)/II, 80333 München

Highlights from publications:
Embedded Fluidic Sensing and Control with Soft Open-Cell Foams
https://onlinelibrary.wiley.com/doi/abs/10.1002/adfm.202403379
Fluidically programmed wearable haptic textiles
https://www.cell.com/device/fulltext/S2666-9986(23)00083-2
Logic-enabled textiles
https://www.pnas.org/doi/abs/10.1073/pnas.2202118119
A wearable textile-based pneumatic energy harvesting system for assistive robotics
https://www.science.org/doi/10.1126/sciadv.abo2418





02/05/2024

🎉 Congratulations to our colleagues Fengyi Wang, Xiangyu Fu, prof. Nitish Thakor and prof. Gordon Cheng. Their paper "Object Classification Utilizing Neuromorphic Proprioceptive Signals in Active Exploration: Validated on a Soft Anthropomorphic Hand” has been accepted for publication for IEEE RAS EMBS 10th International Conference on Biomedical Robotics and Biomechatronics (BioRob 2024) taking place in Heidelberg (Germany) from 1-4 September 2024. 📅

Adresse

KarlStr. 45
Munich
80333

Benachrichtigungen

Lassen Sie sich von uns eine E-Mail senden und seien Sie der erste der Neuigkeiten und Aktionen von Institute for Cognitive Systems - TU München erfährt. Ihre E-Mail-Adresse wird nicht für andere Zwecke verwendet und Sie können sich jederzeit abmelden.

Teilen