CAI Projects

AVATAR lets visitors control a humanoid robot in VR, seeing through its eyes and manipulating objects via intuitive, body-based teleoperation.

Talking Bots: Interactive voice interface for humanoid robots in networking events with context-aware conversational capabilities.

Humanoid Robot Assistant with Physical Agetic AI: Towards general robotics for mobile manipulation with adaptability across tasks and environments.

The goal of the project is to strengthen surveillance of antimicrobial resistance in animals and food products, with a focus on international travelers. The project will explore (and quantify the uncertainty of) using AI-based text and image mining techniques to extract data on the prevalence of…

The ARMADA doctoral network aims at training 15 versatile and interconnected Early-Stage Researchers (ESRs) to specialise in the overarching area of Conversational Artificial Intelligence (Conversational AI).

Background: Injuries in the age group of children and adolescents are a major public health concern and cause individual suffering and costs for the healthcare system and society. Evidence-based, targeted and effective injury prevention must be based on reliable data. Currently, this is not…

The goal of the LINA consortium is to create a basis for the largest European (real and virtual) infrastructure for research, development and safe testing of autonomous systems / UAS (Unmanned Aircraft System) for commercial products in the canton of Zurich.

This research project is focused on development of an artificial intelligence-based method for optimizing the control functionality of Belimo's HVAC field devices in order to significantly reduce the energy consumption in buildings.

This Bridge Discovery project will establish innovative technology for polymer 3D printing extrusion head, including software for process optimization, trajectory optimization, and closed loop control.

In these two collaborative projects funded by NCCR Automation, we aim to develop methods for advancing manufacturing systems' productivity, resilience, and efficiency within the framework of Industry 4.0 by focusing on two topics: 1. Control and Task Planning for Advanced Manufacturing: This…

Digital Manufacturing as a Service Technology (DMaaST) is designed to improve the manufacturing ecosystem's resilience and adaptive capacity to external events through a Smart Manufacturing Platform structured into four layers: The data layer establishes a foundation for interoperable data exchange…

The proposed research seeks to merge data-driven methods, symbolic knowledge, and domain expertise to enhance the planning, optimization, and control of industrial robots and processes in robot-based manufacturing. By incorporating sensor data, we can leverage additional information to monitor and…

A structured inventory of potential use cases is developed for onboard satellite AI compute, organised across application domains and AI capability types, with key system assumptions and qualitative assessments of feasibility, novelty, and impact. Selected use cases are then refined into detailed,…

OrthoSense by Leg&airy revolutionizes ankle-foot orthotics by turning subjective brace fitting into data-driven care. Embedded sensors capture pressure data, enabling AI driven biomechanical algorithms to tailor each brace’s shape and fit to the individual patient while enabling patients tracking.

For the further development of an intraoral scanner (IOS), various AI stereo matching algorithms are being examined for their suitability for use in the product. The aim is to identify a suitable model for training and implementation, to convert it to TensorRT and to optimize the real-time…

The goal of the project is to strengthen surveillance of antimicrobial resistance in animals and food products, with a focus on international travelers. The project will explore (and quantify the uncertainty of) using AI-based text and image mining techniques to extract data on the prevalence of…

SCRAI brings responsible AI to the ground by bridging the gap between societal values and development of AI technology and solutions. The SCRAI Think-and-Do Tank will help organizations to exploit the potential of AI while complying with legal requirements and being compatible with societal…

ZHAW is offering, in partnership with IEEE SA, the IEEE CertifAIEd (TM) Authorized Assessor Training. IEEE CertifAIEd is a certification program for assessing ethics of Autonomous Intelligent Systems (AIS) to help protect, differentiate, and grow product adoption. The resulting certificate and mark…

Certification of AI Systems by an accredited body increases trust, accelerates adoption and enables their use for safety-critical applications. We develop a Certification Scheme comprising specific requirements, criteria, measures, and technical methods for assessing Machine Learning enabled…

Development of a Proof of Concept for visual Open Set Recognition (OSR) algorithms applied to a Hematology task, the classification of white blood cells.

The project enables a novel, combined, adaptive cancer therapy combining tumor treating field and radiation therapy due to significantly improved static (3D) and time-resolved (4D) low dose Cone Beam Computer Tomography images based on artificial intelligence image reconstruction algorithms.

In this project we use generative deep learning methods (GANs and VAEs) to produce realistic astronomical mock-observations of numerically simulated astrophysical objects, as they will be obseved by the Square Kilometre Array Telescope (SKA). This project contributes to the Swiss-wide activities for…

Understanding effective and ethical ways of using vast amounts of data is a significant challenge to science and society as a whole. Data Science encompasses such activities and is therefore inherently interdisciplinary and applied. ZHAW is an early mover in the field of Data Science. Since 2013…

Project DIR3CT aims at improving the image quality of CBCT images by deep learning (DL) the 3D reconstruction from X-ray images end-to-end. This enables a novel CBCT product to be used during radiation therapy and will allow the use of these images for adaptive treatment.

We are developing an end-to-end system for the automatic detection, segmentation, and identification of music in full-length movies. Audio is analyzed in one-second windows using pretrained models, merged into candidate tracks, reviewed, and submitted to external APIs; identification accuracy is…

SCRAI brings responsible AI to the ground by bridging the gap between societal values and development of AI technology and solutions. The SCRAI Think-and-Do Tank will help organizations to exploit the potential of AI while complying with legal requirements and being compatible with societal…

The dAIrector automates multi-cam live productions of concerts, theatre, comedy, musicals through creative AI direction following the dramaturgy on stage. It provides small stages, events, festivals, and artists access to a worldwide audience via YourStage.live.

Numerous new posters and bills arrive daily at the Swiss National Library to be added to its catalogue. How can the process of poster cataloguing be enhanced by current AI systems?

The goal of this pilot study is to research requirements needed to develop a computational model that simulates the fluidic and electro-biochemical dynamics in the power-to-liquid process in order to optimise the performance, efficiency and longevity of enzymes.

The scope of AI4REALNET covers the perspective of AI-based solutions addressing critical systems (electricity, railway, and air traffic management) modelled by networks that can be simulated, and are traditionally operated by humans, and where AI systems complement and augment human abilities. It…

We recently released "A Theory of Natural Intelligence", proposing a possible key to the emergence of intelligence in biological learners. Goal of this fellowship is to develop a technical implementation of the concept of self-organizing netfragments within contemporary deep artificial neural nets.

The Centre for Artificial Intelligence (CAI) of the ZHAW, together with the Cantonal Hospital Aarau, has laid the foundations for machine learning-supported body composition analysis on image files of the KSA within the framework of preliminary studies and has achieved promising results. The aim of…

Certification of AI Systems by an accredited body increases trust, accelerates adoption and enables their use for safety-critical applications. We develop a Certification Scheme comprising specific requirements, criteria, measures, and technical methods for assessing Machine Learning enabled…

We develop a distributed machine learning system to sort out defect plastic parts during production. Main challenge is the transferability of learnt process know-how from case to case; the solution builds on domain adaptation, continual data-centric deep learning and federated edge computing.

The project enables a novel, combined, adaptive cancer therapy combining tumor treating field and radiation therapy due to significantly improved static (3D) and time-resolved (4D) low dose Cone Beam Computer Tomography images based on artificial intelligence image reconstruction algorithms.

Monitoring diverse sensor signals of patients in intensive care can be key to detect potentially fatal emergencies. But in order to perform the monitoring automatically, the monitoring system has to know what is currently happening to the patient: if the patient is for example currently being moved…

This project will identify proven methods, practices and standards that support responsible research and development of AI systems for health. They will be tested in use cases from medical imaging and neurotechnology, publicly released and published as a guideline of recommended best practices.

PDF is the most popular document format to provide and distribute information on the internet. It was developed by Adobe 1996 but has been an open format since 2008. It was estimated in 2015 that more than 2.5 trillion PDF documents exist on the internet, covering all aspects of life and research,…

The automatic analysis of X-ray/CT images through artificial intelligence models can be useful to automate the clinical scanning procedure. Nonetheless, the limited access to real COVID patient data leads to the need of synthesizing image samples. The goal of this project is to use existing CT/X-ray…

Hospitals and research institutes are highly investigating applications of AI in medical imaging. However, developed models and datasets are barely mergeable, and the research results are not reproducible on different datasets due to different CT scanners used. Radiologists told us that “unifying…

Project DIR3CT aims at improving the image quality of CBCT images by deep learning (DL) the 3D reconstruction from X-ray images end-to-end. This enables a novel CBCT product to be used during radiation therapy and will allow the use of these images for adaptive treatment.

The main ambition of TAILOR is to build the capacity of providing the scientific foundations for Trustworthy AI in Europe by developing a network of research excellence centers with a technical focus on combining research excellence in the areas of learning, optimisation and reasoning . The current…

We will develop language technologies for imperfect Swiss German speech. These technologies are crucial to build AI applications for persons with speech disorders, e.g chatbots for children in speech therapy or diagnosis tools for patients with Parkinson’s Disease.

The project investigates the feasibility of AI-supported conversation simulations in XR for professional communication training. The innovative focus is on capturing and evaluating para- and nonverbal communication signals.

Jill & Jules are a two relatable AI characters who motivate young Swiss voters. By presenting referendums through interactive, informal conversations in Swiss German, Jill & Jules make complex or seemingly mundane topics accessible and engaging.

SwissNLP would like to take concerted action to better network Swiss players from industry, science and administration in the field of Natural Language Processing (NLP). For this reason various activities are to be carried out until the end of 2025 such as expert group meetings, applied conferences,…

We take first steps towards developing ChaLL, a voice-based chatbot that provides language learners with opportunities to practice speaking in both focused and unfocused task-based conversations and receive feedback, free from the time constraints and pressures of the traditional classroom setting.

The PRISM project focuses on detecting radicalization events in Social Media networks. Overall, we are interested in unveiling the mechanics that lead to the event of extremist ideology being transferred and incorporated into a social media user’s world view. Specifically, the proposed project aims…

The DOSSMA project will investigate suspicious and malicious behaviour on social media platforms. In a first phase, we will compile an extensive survey report on the areas that are currently being researched, including the respective state-of-the-art, existing solutions and initiatives. This report…

If children are questioned in preliminary proceedings about their own experiences or observations relevant to criminal law, it depends decisively on the quality of the questioning whether their statements can be used in criminal proceedings or whether decisions can be made on this basis and…

The project implements an online service for companies to monitor suppliers for violations ofenvironmental, social, or governance norms. To do so, a vast variety of sources, such as news outlets, is monitored using machine learning and natural language processing with near human-level accuracy.

Tamedia would like to develop a software system that automatically generates news articles from hockey game data.ZHAW will explore the different state-of-the-art technologies to evaluate the feasibility of developing a natural language system that generates rich contextual ice hockey game report…

This research project will investigate how a communication strategy for the marketing and communication of the diverse cultural activities and sites in the Lake Constance region could be shaped.For a sustainable strategy development the digitization of the communication, by which also the cultural…

The industrial project partner offers online brokering of loans, mortgages and insurances. The brokering process involves several phone calls of a call agent with a potential client. This is time-consuming and highly repetitive. For this reason, we want to develop a dialogue system which can take…

Entry, discharge, radiology and pathology reports and other clinical documents are a valuable resource to be harvested for precision medicine. They are typically stored in a free text format, only little structure is imposed and terminology is heterogeneous. We will apply natural language…

In the SCAI project, ZHAW and legartis investigate how content of contracts can automatically be evaluated legally by applying methods from the areas of Natural Language Processing and Deep Learning.

The LIHLITH project is a fundamental pilot research project which introduces a new lifelong learning framework for the interaction of humans and machines on specific domains. A Lifelong Learning system learns different tasks sequentially, over time, getting better at solving future related tasks…

Compared with earlier regulations, the 4th European Money Laundering Directive (MLD4) imposes rigorously increased requirements. It compels obliged entities to conduct in depth screenings of customers and their associations. The Libra Project aims at providing a one tool solution for meeting MLD4…

DeepText develops a software framework to automatically analyse texts in order to extract important information. The framework comprises modern algorithms from the field of machine learning (deep learning) that are better at analyzing texts than traditional approaches. They can for example be used…

AI video interviews (AVI) can mistake circumstance — language, disability, neurodivergence or technical setup — for low competence, resulting in unfair outcomes. This project will identify factors and strategies that enable fairer AI-based competence assessment.

In a time when artificial intelligence is rapidly moving from experimentation into everyday practice, the gap between high-level principles and real-world implementation is becoming increasingly visible. While frameworks for trustworthy AI are evolving, their translation into concrete decisions,…

OrthoSense by Leg&airy revolutionizes ankle-foot orthotics by turning subjective brace fitting into data-driven care. Embedded sensors capture pressure data, enabling AI driven biomechanical algorithms to tailor each brace’s shape and fit to the individual patient while enabling patients tracking.

SCRAI brings responsible AI to the ground by bridging the gap between societal values and development of AI technology and solutions. The SCRAI Think-and-Do Tank will help organizations to exploit the potential of AI while complying with legal requirements and being compatible with societal…

ZHAW is offering, in partnership with IEEE SA, the IEEE CertifAIEd (TM) Authorized Assessor Training. IEEE CertifAIEd is a certification program for assessing ethics of Autonomous Intelligent Systems (AIS) to help protect, differentiate, and grow product adoption. The resulting certificate and mark…

The goal of this project is to develop an International Data Governance Framework (IDGF) that can advance responsible international brain research and innovation. This will start with the identification of the technical, legal, ethical and organizational challenges to IDGF and the development of…

In the midst of societal digital transformation, post-pandemic economic recovery, and geopolitical tensions around the globe, the need for a carefully curated space for deliberation and networking presents unprecedented urgency. Against this backdrop, we propose the creation of an intellectually…

The goal of this project is to develop an International Data Governance Framework (IDGF) that can advance responsible international brain research and innovation. This will start with the identification of the technical, legal, ethical and organizational challenges to IDGF and the development of…

The scope of AI4REALNET covers the perspective of AI-based solutions addressing critical systems (electricity, railway, and air traffic management) modelled by networks that can be simulated, and are traditionally operated by humans, and where AI systems complement and augment human abilities. It…

Certification of AI Systems by an accredited body increases trust, accelerates adoption and enables their use for safety-critical applications. We develop a Certification Scheme comprising specific requirements, criteria, measures, and technical methods for assessing Machine Learning enabled…