Ariel Noyman

Ariel Noyman, Kai Hu, Kent Larson

Understanding human behavior in built environments is critical for designing functional, user centered urban spaces. Traditional approaches, such as manual observations, surveys, and simplified simulations, often fail to capture the complexity and dynamics of real world behavior. To address these limitations, we introduce TravelAgent, a novel simulation platform that models pedestrian navigation and activity patterns across diverse indoor and outdoor environments under varying contextual and environmental conditions. TravelAgent leverages generative agents integrated into 3D virtual environments, enabling agents to process multimodal sensory inputs and exhibit human-like decision-making, behavior, and adaptation. Through experiments, including navigation, wayfinding, and free exploration, we analyze data from 100 simulations comprising 1898 agent steps across diverse spatial layouts and agent archetypes, achieving an overall task completion rate of 76%. Using spatial, linguistic, and sentiment analyses, we show how agents perceive, adapt to, or struggle with their surroundings and assigned tasks. Our findings highlight the potential of TravelAgent as a tool for urban design, spatial cognition research, and agent-based modeling. We discuss key challenges and opportunities in deploying generative agents for the evaluation and refinement of spatial designs, proposing TravelAgent as a new paradigm for simulating and understanding human experiences in built environments.

Kai Hu, Parfait Atchade-Adelomou, Carlo Adornetto et al.

Understanding human behavior in urban environments is a crucial field within city sciences. However, collecting accurate behavioral data, particularly in newly developed areas, poses significant challenges. Recent advances in generative agents, powered by Large Language Models (LLMs), have shown promise in simulating human behaviors without relying on extensive datasets. Nevertheless, these methods often struggle with generating consistent, context-sensitive, and realistic behavioral outputs. To address these limitations, this paper introduces the Preference Chain, a novel method that integrates Graph Retrieval-Augmented Generation (RAG) with LLMs to enhance context-aware simulation of human behavior in transportation systems. Experiments conducted on the Replica dataset demonstrate that the Preference Chain outperforms standard LLM in aligning with real-world transportation mode choices. The development of the Mobility Agent highlights potential applications of proposed method in urban mobility modeling for emerging cities, personalized travel behavior analysis, and dynamic traffic forecasting. Despite limitations such as slow inference and the risk of hallucination, the method offers a promising framework for simulating complex human behavior in data-scarce environments, where traditional data-driven models struggle due to limited data availability.

Ariel Noyman, Yasushi Sakai, Kent Larson

Processes of urban planning, urban design and architecture are inherently tangible, iterative and collaborative. Nevertheless, the majority of tools in these fields offer virtual environments and single user experience. This paper presents CityScopeAR: a computational-tangible mixed-reality platform designed for collaborative urban design processes. It portrays the evolution of the tool and presents an overview of the history and limitations of notable CAD and TUI platforms. As well, it depicts the development of a distributed networking system between TUIs and CityScopeAR, as a key in design collaboration. It shares the potential advantage of broad and decentralized community-engagement process using such tools. Finally, this paper demonstrates several real-world tests and deployments of CityScopeAR and proposes a path to future integration of AR/MR devices in urban design and public participation.

Ariel Noyman, Tobias Holtz, Johannes Kroger et al.

This paper describes the conception, development and deployment of a novel HCI system for public participation and decision making. This system was applied for the process of allocating refugee accommodation in the City of Hamburg within the FindingPlaces project in 2016. The CityScope a rapid prototyping platform for urban planning and decision making offered a technical solution which was complemented by a workshop process to facilitate effective interaction of multiple participants and stakeholder groups. This paper presents the origins of CS and the evolution of the tangible user interface approach to urban planning and public participation. It further outlines technical features of the system, including custom hardware and software in use, utilization in real time as well as technical constraints and limitations. Special focus is on the adaptation of the CS technology to the specific demands of Hamburg FP project, whose procedures, processes, and results are reflected. The final section analyzes success factors as well as shortcomings of the approach, and indicates further R&D as well as application scenarios for the CS.