User Group: Investor

  • Cyber Valley Research Fund advances robotic perception techniques

    Cyber Valley Research Fund advances robotic perception techniques

    Current autonomous systems still lack the capabilities of humans in scene perception and object manipulation tasks. Jörg Stückler and his team developed a method that combines differentiable physics and deep learning to estimate an object’s position, orientation, and velocity, while also simultaneously determining the friction between an object and its surface. The team also explored how understanding an object’s dynamics could improve control strategies, such as predicting how a robot’s actions will impact the object and guiding it to a desired location.  

    Their findings inspire new methods and approaches that adapt robotics object manipulation skills to the physical properties of objects. Although the research is still in its scientific development stage, it has the potential to revolutionize applications by enabling robots to manipulate objects more flexibly and adaptively.  

    This project yielded the following publications: 


    1. Kandukuri, R. K., Strecke, M., Stueckler, J. Physics-Based Rigid Body Object Tracking and Friction Filtering From RGB-D Videos. Accepted for International Conference on 3D Vision (3DV), 2024. Preprint arXiv:2309.15703. 

    2. EV-SynPhys and EV-RealPhys datasets accompanying at https://keeper.mpdl.mpg.de/d/5ec213b655b44e40a382/ 

    3. The 3DV 2024 paper was presented as poster presentation at the International Conference on 3D Vision 2024. Parts of the results reported in the paper have been also presented in a keynote given at the IEEE International Conference on Multi-Sensor Fusion and Integration / Symposium on Sensor and Data Fusion (MFI/SDF) in Bonn in November 2023. Parts of the project results have been presented at the Cyber Valley Research Fund symposium in November 2023. 

    This research project started in June 2020 and concluded in December 2023. Dr. Jörg Stückler is now a Professor of Computer Science at the University of Augsburg. 

  • Cyber Valley Research Fund drives research excellence

    Cyber Valley Research Fund drives research excellence

    One notable project supported by the Research Fund was Caterina De Bacco’s project “Relaxing Restrictive Independence Assumptions in Networks”. The project aimed to improve our understanding of fundamental patterns in networks through advanced probabilistic generative models. It began in April 2020 and concluded in December 2023.

    By leveraging the growing availability of rich datasets, De Bacco’s project developed advanced network models to capture complex interactions within various domains. The project team created a model that combines node information with network structure to analyze multilayer networks. By developing analytical approximations, the project addressed the complexity of real-world interactions, incorporating features like reciprocity and multiplexity.
     
    Extending beyond the concept of conditional independence, the research team developed two new methods for modeling connections between nodes. One uses Poisson distributions and relies on pseudo-likelihood approximations, while the other utilizes Bivariate-Bernoulli distributions. Both methods provide a better understanding of network interactions.
     
    Additionally, the project delved into how the developed ideas and methods could be applied to generalized data sets, specifically hypergraphs, where the interactions involve groups of nodes, and further developed their generative models. These models present several advantages for hypergraph analysis and can effectively identify communities and predict missing connections.
     
    These new models represent a major advancement in network analysis, offering reliable and scalable solutions for understanding complex interactions. The project has set the stage for future research and two more models are currently in development, focusing on multilayer networks with additional information and hierarchical structures. 
     
     
    This project yielded the following publications:

    1. M. Contisciani, E. A. Power, and C. De Bacco. “Community detection with node attributes in multilayer networks”. Scientific Reports 10.1 (2020), page 15736.

    2. K.Higham, M. Contisciani, and C. De Bacco. “Multilayer patent citation networks: A comprehensive analytical framework for studying explicit technological relationships”. Technological Forecasting and Social Change 179 (2022), page 121628.

    3. H. Safdari, M. Contisciani,and C. De Bacco. “Generative model for reciprocity and community detection in networks”. Physical Review Research 2 (2021).

    4. M. Contisciani, H. Safdari, and C. De Bacco. “Community detection and reciprocity in networks by jointly modelling pairs of edges”. Journal of Complex Networks 10.4 (2022).

    5. H. Safdari, M. Contisciani, and C. De Bacco. “Reciprocity, community detection, and link prediction in dynamic networks”. Journal of Physics: Complexity 3.1 (2022).

    6. C. De Bacco, M. Contisciani, J. Cardoso-Silva, H. Safdari, G. Lima Borges, D. Baptista, T. Sweet, J.-G. Young, J. Koster, C. T. Ross, R. McElreath, D. Redhead, and E. A. Power. “Latent network models to account for noisy, multiply reported social network data”. Journal of the Royal Statistical Society Series A: Statistics in Society 183 (2023).

    7. H. Safdari, M. Contisciani, and C. De Bacco. “Anomaly, reciprocity, and community detection in networks”. Physical Review Research 5.3 (2023).

    8. M. Contisciani, F. Battiston, and C. De Bacco. “Inference of hyperedges and overlapping communities in hypergraphs”. Nature Communications 13.1 (2022).

    9. N. Ruggeri, M. Contisciani, F. Battiston, and C. De Bacco. “Community detection in large hypergraphs”. Science Advances 28 (2023).

    10. Q. F. Lotito, M. Contisciani, C. De Bacco, L. Di Gaetano, L. Gallo, A. Montresor, F. Musciotto, N. Ruggeri, and F. Battiston. “Hypergraphx: a library for higher-order network analysis”. Journal of Complex Networks 11.3 (2023).

  • The Cyber Valley Start-up Network welcomes four new members

    The Cyber Valley Start-up Network welcomes four new members

    Beyondbots

    BeyondBots provides intelligent business automation solutions to streamline workflows and enhance operational efficiency. The company is an Intelligent Automation Provider, dedicated to scaling process automation using No Code / Low Code and AI-based technology. As a specialized solution partner, Beyondbots supports companies through every phase of their automation journey. This includes taking the initial first steps, developing an effective blueprint, and scaling existing initiatives in experienced organizations. Their holistic perspective on automation provides a unique advantage, combining expertise in change management, business processes, and technology.

    Casculate

    Casculate provides AI-based software solutions for the manufacturing industry. The company develops custom apps to streamline commercial processes from cost calculation to production planning. Integration with ERP systems ensures continuous monitoring throughout the entire product lifecycle. The design and development process is tailored to individual needs. It begins with domain experts visiting facilities to understand unique challenges. Subsequent steps involve collaborative design sessions with specialists to align visions with the development team. Development proceeds iteratively, with frequent feedback.

    NextStepHR

    NextStepHR specializes in employer branding and social media recruiting campaigns for small- and medium-sized businesses. The company is developing an artificial intelligence system that gathers data from job listings and filled positions across online portals. This AI system autonomously places job ads for companies on multiple platforms based on their location. It analyzes job postings and user activity on different channels, correlating this information to identify the best platforms for ad placement. The goal is to post job ads on platforms with a high concentration of qualified candidates and low competition. Additionally, the AI system can create social media ads if it detects promising opportunities to attract potential employees. All these processes are analyzed and evaluated automatically.

    Ventecon Technologies

    Ventecon Technologies is transforming the world of product management with AI. Product managers, the backbone of any company, juggle market demands, resource constraints, and fierce competition. To support them, Ventecon Technologies provides AI Co-Workers that streamline their work, making it easier to innovate and succeed. By enhancing product management with AI, the company solves internal challenges. Their AI Co-Workers boost efficiency, drive innovation, and ultimately improve the well-being of communities everywhere.

    In joining the Cyber Valley Start-up Network, these four start-ups enhance the diversity and collaborative culture of the Cyber Valley Community. We are pleased to have them on board.

  • Cyber-physical twins of human organs

    Cyber-physical twins of human organs

    Dr. Tian Qiu led the project in collaboration with three medical departments at the University Hospitals in Tübingen and Freiburg. The project team successfully created and studied six highly realistic organ models, including the kidney, bladder, prostate, liver, vagina, and brain. These models combine the advantages of physical and cyber models to improve the collection of hard-to-get biomedical data under realistic conditions for analysis and modeling.

    For the physical models, the project team optimized 3D printing and soft material molding techniques to replicate the anatomy and texture of human organs. Additionally, they engineered new hydrogel materials that behave like real soft tissue in surgical procedures. The team also created a brain model comprising composite hydrogel that exhibits life-like mechanical properties and high optical transparency, enabling high-resolution imaging. 

    The project’s cyber models incorporated sensing technologies such as optical imaging, ultrasound imaging, and electrical sensing. These integrated systems can generate large amounts of data, making possible real-time feedback and quantitative evaluation of surgical outcomes. The project also leveraged Augmented Reality (AR) to enhance medical training. Medics participated in initial trials by applying the new cyber-physical organ models to optimize surgical instruments and digital surgical training.  

    The Cyber Valley Research Fund has allocated five million euros to promote innovation and scientific excellence. Research groups were encouraged to submit project proposals that were evaluated according to ethical and societal considerations.  
     

    This project yielded the following peer-reviewed publications:

    1. Choi et al. (2021): Soft urinary bladder phantom for endoscopic training, Ann. Biomed. Eng., 49, 2412-2420, DOI: 10.1007/s10439-021-02793-0 

    2. Hackner et al. (2021): Panoramic imaging assessment of different bladder phantoms – an evaluation study, Urology, 156, e103-e110, DOI: 10.1016/j.urology.2021.05.036

    3. Kim et al. (2022): A high-fidelity artificial urological system for the quantitative assessment of endoscopic skills, J. Funct. Biomater., 13(4)301, DOI: 10.3390/jfb13040301 

    4. Tan et al. (2021): Soft liver phantom with a hollow biliary system, Ann. Biomed. Eng., 49, 2139-2149, DOI: 10.1007/s10439-021-02726-x 

    5. Tonyali S., Mueller A.-S. et al. (2024): Automated and quantitative surgical technique evaluation for TURP. In preparation

    6. Mueller A.-S., et al. (2024): Surgical training of bladder tumor resection on hydrogel models with quantitative assessment based on 3D ultrasound scanning. In preparation

    7. Li et al. (2020): Realistic full urinary tract phantom for endoscopic training, The European Association of Endoscopic Surgery (EAES), Poster 

    8. Kim et al. (2021): Organ Phantom for the Assessment of Robotic Surgeries, Hamlyn Symposium on Medical Robotics (HSMR), Poster 

    9. Kim et al. (2021): Computer-assisted quantitative assessment of endo. skills based on a urological phantom, 55th DGBMT Ann. Conf. on Biomed. Eng., Talk, 66, S212-217, Link to abstract

    10. Kim et al. (2022): A hybrid surgical simulator for interactive endoscopic training, IEEE Inter. Conf. of the Engineering in Medicine and Biology Society (EMBC), Poster, DOI: 10.1109/EMBC48229.2022.9871697 

    11. Tan et al. (2021): A realistic liver phantom for the training and quantitative evaluation of endoscopic skills, 17th World Congress of Endo. Surgery (WCES), Poster, 344272, P201 

    12. Mueller A.-S., et al. (2023): Surgical training of tumor resection on hydrogel models with quantitative assessment based on 3D ultrasound scanning. DKFK German Cancer Research Congress (GCRC). Poster 

    13. Fischer, F.; et al. (2023): Wireless force sensing of a micro-robot penetrating a viscoelastic solid, International Nonlinear Dynamics Conference (NODYCON), Talk 

    14. Fischer, F. et al. (2022): 3D fabrication of microvascular networks on artificial organ models for endoscopic surgical simulation. Poster. Future 3D Additive Manufacturing – The 3DMM2O Conference

    Public events and public media reports: 

    1. Presentation of German Chancellor Dr. Merkel during virtual visit of Cyber Valley, 2020; Link to article

    2. University of Stuttgart representing at Hannover Messe 2023; Link to article

    3. Stuttgarter Zeitung; Link to article

    4. Spotify, Cyber Valley Podcast, AI in Medicine; Link to spotify episode