Human-AI-Things Interaction and AI-Augmented & Collaborative Design
This platform studies and prototypes interactions between people and intelligent physical systems, including robots and drones. Those using the platform can design, build, and test interaction concepts such as voice, gesture, and shared-autonomy control, and examine how trust, safety, and transparency shape the way people work alongside autonomous machines. The platform supports sustainability applications such as drone-based environmental monitoring, robot-assisted waste sorting, and smart-environment sensing. All of these are developed around human needs rather than technology alone.
Generative Design Systems: Investigation of AI-powered concept generation, design space exploration, and automated synthesis while maintaining human agency and creative control.
Human-AI Co-Creation: Empirical study of optimal collaboration patterns, communication interfaces, and control allocation in creative partnerships between humans and AI systems.
Rapid Prototyping Methodologies: Development and evaluation of AI-enhanced approaches for accelerating the ideation-to-prototype cycle while ensuring human values alignment.
Responsible AI Design: Participatory methods for embedding ethical considerations, fairness constraints, and sustainability criteria into early-stage design processes.
AI-Enabled Research and AI Tools in Research
This platform equips users to apply AI across the entire research cycle, from literature review and data collection to analysis, modeling, and reporting. It provides access to machine learning, large language models, and automated analytics, along with guidance on responsible, reproducible, and ethical use. Speeding up routine tasks and revealing patterns in complex data lets teams focus on interpretation and innovation. It is especially useful for sustainability problems such as climate modeling, resource optimization, and food security, where evidence is abundant and varied.
Large Board XR for Visual Mining and Large Datasets Visualization
This platform uses a large-format display and extended reality (XR) technologies to enable teams to explore massive, multidimensional datasets visually and collaboratively. Users can walk through data, compare scenarios side by side, and discover hidden relationships through visual mining, rather than reading tables or small screens. The shared immersive space helps platform users, industry partners, and decision-makers quickly reach a common understanding. Typical uses include climate trends, recycling flows, supply chains, and food-security indicators.
Immersive Analytics: Investigation of how spatial computing, large displays, and embodied interaction enhance data comprehension and pattern discovery (Chandler et al., 2015).
Collaborative Sensemaking: Study of how teams coordinate attention, negotiate interpretations, and construct shared understanding when exploring complex datasets (Convertino et al., 2011).
Visual Data Mining: Development of visualization-based approaches for exploratory data analysis, hypothesis generation, and insight extraction from large, multidimensional datasets.
Sustainability Visualization: Specialized investigation of how to represent environmental data, system dynamics, and impact projections in ways accessible to diverse stakeholders.
Explainable AI: Critical brainstorming to make the reasoning of AI systems and their complex data patterns interpretable to human decision-makers.
From complex datasets to shared understanding.
Large-format and XR exploration supports visual comparison, collaborative interpretation, and evidence-informed decision-making across research and industry teams.
Usability and UX Testing of Tangible, Haptics, and Immersive Intelligent User Interfaces
This platform provides a controlled setting to evaluate how real users experience tangible applications, haptic feedback devices, and other X/R immersive interfaces. Studies can combine task-based testing, observation, questionnaires, and behavioral measures to assess usability, comfort, presence, accessibility, and cognitive load. The findings feed back into design, so that prototypes are refined before wider deployment. The platform helps ensure that new human-centric technologies are effective, inclusive, and enjoyable to use, including those built to support sustainable behaviors and training.
Usability Testing: Systematic evaluation of AI system learnability, efficiency, memorability, error rates, and user satisfaction (Nielsen, 1994).
Cognitive Task Analysis: Investigation of mental models, decision-making processes, and cognitive load in human-AI collaboration (Endsley, 2017).
Participatory Design: Co-creation approaches that position end-users as active research partners rather than passive subjects (Schuler & Namioka, 1993).
Longitudinal Studies: Extended-duration evaluation of AI system adoption, adaptation, and impact on work practices and behavior patterns.
Agentic AI Programming, Simulation, and Performance Testbench
This platform is a development and evaluation environment for AI agents that can plan, reason, use tools, and act with a degree of autonomy. Those using it can program multi-agent systems, run them in simulated environments, and benchmark their reliability, efficiency, safety, and decision quality under repeatable conditions. Simulation lowers the cost and risk of experimenting before systems meet the real world. The testbench therefore supports proof-of-concept solutions that can be rigorously tested for sustainability challenges such as energy management, waste logistics, and climate response.
Autonomous Vehicle Systems: Investigation of perception, planning, and control for self-driving vehicles with emphasis on human-AI shared control, explanatory interfaces, and safety-critical decision-making.
Intelligent Robotics: Development of robots capable of complex manipulation, human-robot collaboration, and operation in unstructured environments for applications including precision agriculture and environmental monitoring.
Unmanned Aerial Systems: Research in drone autonomy, swarm coordination, and applications for sustainability, including wildlife monitoring, precision agriculture, and disaster response.
Human-AI Teaming: Fundamental investigation of trust calibration, workload allocation, communication protocols, and shared mental models in human-AI partnerships (O'Neill et al., 2020) and their application to programming and design.
