Inverse augmentation: Transposing real people into pedestrian models. (March 2023)

• Record Type: Journal Article
• Authors: Torrens, Paul M.; Gu, Simin
• Is Part Of: Computers, environment and urban systems. Volume 100(2023)
• Publication Date: 2023-03
• Subjects: Virtual geographic environment -- Virtual reality -- Geosimulation -- Geographic automata system -- Pedestrians -- Behavioral geography; City planning -- Data processing -- Periodicals; Regional planning -- Data processing -- Periodicals; 303.4834
• DOI: 10.1016/j.compenvurbsys.2022.101923
• Languages: English
• ISSNs: 0198-9715

Abstract

Abstract: We introduce a scheme for immersing real human users in urban simulations, and for enabling them to transpose their embodied behavior into models. We achieve this by inverse augmentation, flipping traditional philosophies of augmented reality. Rather than beginning with real-world scenes and embellishing them with graphics, we proceed from a base of synthetic, modeled, streetscapes filled with agent characters, which we augment with real human users. Participants are then allowed to use their natural abilities to explore the simulation scenarios. We achieve this by employing mobile virtual reality to allow users to build dynamic presence in a fused geosimulation and virtual geographic environment that they can physically view and walk around in. Our central argument is that inversion of this kind allows for the detail and nuances of human behavior to be brought directly into simulation, where they would traditionally be difficult to capture and represent. We show that close matches between real physical activity on the ground and actions in the model world can be achieved, as measured by spatial analysis and encephalography of user brain activity. We demonstrate the usefulness of the approach with an application to studying pedestrian road-crossing behavior. Graphical abstract: Unlabelled Image Highlights: We introduce an inverse augmentation scheme for mapping real human physical behavior to a simulation comprising a coupled Virtual Geographic Environment with realistic behavior-driven agent models for vehicles and pedestrians. Agents are designed with very high-fidelity detail and implemented as geographic automata for efficient functioning within VGE systems. All agent characters in the model react naturally to human participants as they would in the real world, including gaze and interest, velocity-based steering, avoiding collisions, and engaging in conversation. We performed experiments to monitor the brain activity of users while engaged in the experiments using sensor-assisted electroencephalography. While preliminary, this work suggests that users' neurological appreciation for the simulation has bearing on (and perhaps linkage to) their real-world brain activity of perception, action, and cognition. We demonstrate that the system (including the agent models) can be transferred from VR to augmented reality (AR), opening the possibility that new methods of Augmented Geographic Environments (AGEs) may be developed.