News
ZITI’s Prof. Dr. Dr. Lorenzo Masia was invited as a speaker on the development of soft wearable exosuits to the 2024 Nature Conference on Transformative Technologies on Neuroengineering in Shenzhen, China (April 10-12, 2024).
Soft wearable robotics, or exosuits have been introduced in the last decade as possible candidates to overcome the limitations from devices using rigid structures, the exoskeletons.
Despite the exosuits initially promised tangible improvements, yet their soft wearable architecture presents multiple challenges in controlling such technology symbiotically with the human wearer. Prof. Masia introduces advanced control strategies in soft wearable robotics to restore motor function in patients affected by various neurological diseases, like stroke, multiple sclerosis and spinal cord injuries. He illustrates how such technology, due to its high ergonomics and portability, has been progressively used in the wide context of supporting aging as well as for augmentation of human performance in wellness and to improve safety in working environments. Furthermore, the use of the latest algorithm employing machine learning can provide wearable robotics with an additional boost, relying on artificial vision and machine learning to exploit situational awareness and adapting its robotic assistance in a symbiotic way.
Prof. Lorenzo Masia has been working at the Institute of Computer Engineering (ZITI) since 2019, leading the ARIES Lab (Assistive Robotics and Interactive ExoSuits). His academic career includes positions at the Massachusetts Institute of Technology (MIT), the Italian Institute of Technology (IIT), Nanyang Technological University (NTU) of Singapore, and the University of Twente (The Netherlands). He is an associate editor for Wearable Technologies (Cambridge Press), IEEE RAL Robotics and Automation Letters, IEEE Transaction on Neural Systems and Rehabilitation Engineering and the Journal of NeuroEngineering and Rehabilitation.
He has been appointed as Program Chair for the IEEE International Conference in Rehabilitation Robotics (ICORR) 2015, IEEE International Conference on Biomedical Robotics and Biomechatronics (BIOROB) 2016 and International Conference on Neurorehabilitation (ICNR 2018). Prof. Masia served as Chairman for Workshop/Tutorial for the IEEE International Conference on Robotics and Automation (IEEE ICRA 2017), and was the Co-Program Chair of IEEE ICORR 2017 (London, UK), and Co-Program Chair, Editor in Chief and Editor of Publication for IEEE BIOROB 2018. IN 2024, he will be General Chair for IEEE BIOROB 2024 the leading conference in Biomedical Robotics and Biomechatronics hosted in Heidelberg.
- Details
ZITI is very happy to welcome Dr.-Ing. Arya Mazaheri for a visit on April 29 2024.
Dr. Mazaheri will give a public talk at 4 pm in the ZITI lecture room (INF 350, room U014).
Title: Full-stack AI: Towards efficient AI for next-level autonomous systems
Abstract: AI-based applications are revolutionizing the way we approach prediction tasks by leveraging deep neural networks, including recently emerged Transformers and large language models. However, the challenge of efficiently training and deploying these complex models—especially on smaller edge devices with limited processing power—remains significant. Addressing this, various methods have been developed to improve different aspects of model design and deployment, including accuracy, speed, energy efficiency, cost, and adaptable performance. On the other hand, full-stack AI takes a holistic approach, optimizing the entire AI development cycle to balance all these design concerns effectively. In my talk, I will demystify the layers of full-stack AI development and discuss each component in detail. I'll also share the results of my research, showcasing the practical improvements we can achieve in AI application performance.
Speaker: Dr. Arya Mazaheri is a senior researcher at TU Darmstadt and co-founder of the spin-off PanocularAI, working on the computer systems side of AI. He received his Ph.D. in Computer Science from TU Darmstadt in 2021 on the topic of performance engineering of data-intensive applications. His research expertise covers HPC performance engineering and deep learning, with a special focus on developing multitask models that automatically achieve high task accuracy, low computational cost/energy, and strong robustness. He has published more than 12 research papers in prestigious HPC and AI/ML conferences. Since 2022, he is actively transferring his research results on accelerated AI into a spin-off, which has been awarded several times by hessian.AI and Germany Trade and Invest.
- Details
ZITI is very happy to welcome Prof. Jan Stallkamp for a visit on January 29 2024.
Prof. Stallkamp will give a public talk at 4 pm in the ZITI lecture room (INF 350, room U014). The talk will be in german.
Title: Automatisierung in der Medizin: Leicht gesagt, schwer getan
Abstract: Moderne diagnostischen und therapeutische Verfahren erfordern die Beherrschung zunehmend komplexer Prozesse, deren Ausführung aufgrund der wachsenden Ressourcenknappheit im Gesundheitswesen die Kliniken vor immer größere Herausforderungen stellt. Die Unterstützung der Prozessabläufe durch Automatisierungslösungen liegt daher für viele klinische Bereiche nahe. Effiziente Lösungen sind jedoch speziell in der Diagnostik und Therapie selten anzutreffen, da sie um ein Vielfaches aufwändiger sind als beispielsweise in der Produktion. Die hohe Komplexität und Dynamik des menschlichen Organismus, eine scheinbar unendliche Variabilität der schweren Erkrankungen und nicht zuletzt das typische „Menscheln“ in jedem medizinischen Betrieb haben neben organisatorischen Einflüssen einen umfassenden Einsatz der Automatisierung für diagnostische und therapeutische Anwendungen verhindert. Der Seminarbeitrag stellt die Aufgaben und der Anforderungen der Automatisierung in einer modernen Klinik vor. Es zeigt die technologischen Grenzen ebenso wie neue Forschungsansätze bei der Realisierung von Closed-Loop-Systemen in der Medizin auf und stellt dabei ganz nebenbei die Arbeitsschwerpunkte des Mannheimer Institut für Intelligente Systeme in der Medizin MIISM vor.
Speaker: Prof. Dr. Ing. Jan Stallkamp studierte Maschinenbau an der Rheinisch-Westfälischen-Technischen-Hochschule (RWTH) Aachen mit dem Schwerpunkt Luft- und Raumfahrttechnik. Nach dem Studium arbeitete er als wissenschaftlicher Mitarbeiter im Bereich der Medizintechnik am Fraunhofer-Institut für Produktionstechnik und Automatisierung (IPA) in Stuttgart. Im Jahr 2005 promovierte er an der Universität Stuttgart und wurde Abteilungsleiter am IPA. Ab 2011 baute er die Fraunhofer-Projektgruppe für Automatisierung in der Medizin und Biotechnologie (PAMB) auf dem Campus des Universitätsklinikums in Mannheim auf und übernahm deren Leitung. 2014 folgte er dem Ruf auf die Professur für Automatisierung in der Medizin und Biotechnologie an der Medizinischen Fakultät Mannheim der Universität Heidelberg (MedMa). 2019 wechselte er vollständig an die MedMa. Aktuell ist er geschäftsführender Direktor des Mannheimer Instituts für Intelligente Systeme in der Medizin MIiSM an der Medizinischen Fakultät Mannheim und leitet die Abteilung Automatisierung in der Medizin und Biotechnologie. Sein Forschungsschwerpunkt ist die Automatisierung von diagnostischen und therapeutischen Prozessen mit dem Fokus auf der Entwicklung von Closed-Loop-Systemen für den Interventionsraum.
- Details
Prof. Cacucciolo will give a public talk at 4 pm in the conference room of Mathematikon (INF 250, 5th floor)
Title: Solid-State Soft Pumps for Electrically driven Artificial Muscles, Soft Robots, and Active Textiles
Abstract: Electro-active robotic materials produce force/motion/temperature change in response to an electrical stimulus (example artificial muscles) and generate electrical signals in response to physical stimuli (soft sensors). Fluid pressure and fluid circulation are essential tools to build such devices. Fluids are ubiquitously used in engineering to cool-down or heat-up machines, create motion, lift weights. Fluid-driven active wearables can be used for muscular support, haptic feedback, thermal management. My work has focused on technologies to miniaturize fluidics to use it in autonomous and wearables robots. Our solid-state pumps solve the challenge of integrating fluid circulation in soft robots and wearables, replacing noisy and bulk pumps and compressors with stretchable or fiber-shaped pumps. I will present our work on understanding ElectroHydroDynamics pumping and selecting materials and geometries to build pumps that are silent, compact (1 g weight) and all made of soft materials. I will then discuss how these pumps can be connected with soft actuators and used to power untethered robotic systems. Similar to circulation systems in humans and animals, these solid-state pumps bring the wide capabilities of fluids to the next generation of intelligent robots and wearables.
Speaker: Vito is an Associate Professor at Politecnico di Bari (Italy) and a researcher at MIT (US), as well as the CEO of the spin-off Omnigrasp Srl. Vito’s work focuses on advancing soft-matter machines and robotic materials for human-centric robotics. Vito obtained his Ph.D. in 2017 from Scuola Superiore Sant’Anna Pisa (Italy) working on bio-inspired soft robotics. From 017 to 2021, he worked as a scientist at EPFL in Switzerland, developing miniaturized artificial muscles. Vito's research on solid-state soft pumps, published on Nature in 2019 and on Science in 2023, advances the integration of fluidics into robots and wearables by replacing bulky pumps with silent, polymer-based ones. This research sets the base for the project ROBOFLUID, which has been awarded the ERC Starting grant by the European Research Council in 2023. Vito published 19 journal articles and 14 articles in conference proceedings, has an h-index of 17 and over 3300 citations.
- Details
Dr. Hager will give a public talk at 4 pm in the ZITI lecture room (INF 350, room U014)
Title: Performance Engineering with Resource-Based Metrics
Abstract: High Performance Computing is all about resources and how to use them efficiently. This is not just executive-level chatter but can be leveraged in practice and lead to surprisingly actionable conclusions. In this talk, I will show how resource-based thinking in HPC helps to focus on promising opportunities for optimization from the single core to the supercomputer level. A centerpiece of this line of thinking is resource-based performance modeling, which describes the interaction of hardware and Software in simple mathematical terms based on first principles. Beyond performance modeling and optimization, resource metrics can also be employed in cluster job monitoring to support the identification of "bad" jobs, for which I will give examples from daily operations at Erlangen National High Performance Computing Center (NHR@FAU).
Speaker: Georg Hager holds a PhD and a Habilitation degree in Computational Physics from the University of Greifswald. He leads the Training & Support Division at Erlangen National High Performance Computing Center (NHR@FAU) and is an associate lecturer at the Institute of Physics at the University of Greifswald. Recent research includes architecture-specific optimization strategies for current microprocessors, performance engineering of scientific codes on chip and system levels, and the analytic modeling of structure formation in large-scale parallel codes. Georg Hager has authored and co-authored more than 100 peer-reviewed publications and was instrumental in developing and refining the Execution-Cache-Memory (ECM) performance model and energy consumption models for multicore processors. In 2018, he won the “ISC Gauss Award” (together with Johannes Hofmann and Dietmar Fey) for a paper on accurate performance and power modeling. He received the “2011 Informatics Europe Curriculum Best Practices Award” (together with Jan Treibig and Gerhard Wellein) for outstanding contributions to teaching in computer science. His textbook “Introduction to High Performance Computing for Scientists and Engineers” is recommended or required reading in many HPC-related lectures and courses worldwide. Together with colleagues from FAU, HLRS Stuttgart, and TU Wien he develops and conducts successful international tutorials on node-level performance engineering and hybrid programming.
- Details
ZITI is very happy to welcome Dr. Patrick van der Smagt for a visit on November 23.
Dr. van der Smagt will give a public talk at 2.30pm at Mathematikon (INF 205) in Room 5/104.
Abstract:
Mutual predictability is the key to interaction. Or in simpler terms: "experience makes teamwork". Of course, prediction isn't all that simple. We'll look at "generative AI", but without the hype, and see how we use that to learn the dynamics of complex stochastic systems, use that to predict -- and control. And give some examples, in robotics and beyond, of where this can be used.
About the speaker:
Patrick van der Smagt is director of AI research at Volkswagen Group, and leads its Machine Learning Research Lab in Munich (https://argmax.ai), which focuses on fundamental research on machine learning for time series modelling and optimal control. He is faculty member of the LMU Graduate School of Systemic Neurosciences and research professor at Eötvös Loránd University Budapest, and previously professor at TUM. He is the founding head of a European industry initiative on trust in AI (https://etami.org) and member of the AI Council of the State of Bavaria. Besides publishing some CC papers on machine learning, robotics, and motor control, he has won a number of awards, including the 2013 Helmholtz-Association Erwin Schrödinger Award for his work on controlling robots by tetraplegic patients with permanent brain implants, the 2014 King-Sun Fu Memorial Award, the 2013 Harvard Medical School/MGH Martin Research Prize, and best-paper awards at machine learning and robotics conferences and journals. Patrick is or was area chair for the large ML conferences and reviews for funding agencies around the globe.
- Details
