A multimodal human-centered framework for assessing pedestrian well-being in the wild

Engineering notes

Key topics: autonomous driving, perception. See the paper for implementation details and experimental results.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。

Original abstract

Pedestrian well-being is a critical yet rarely measured component of sustainable urban mobility and livable city design. Existing approaches to evaluating pedestrian environments often rely on static, infrastructure-based indices or retrospective surveys, which may overlook the dynamic, subjective, and psychophysiological dimensions of everyday walking experience. This paper introduces a multimodal, human-centered framework for assessing pedestrian well-being in the wild by integrating three complementary data streams: continuous physiological sensing, geospatial tracking, and momentary and short-term self-reports collected using the experience sampling method. The framework conceptualizes pedestrian experience as a triangulation across environmental context, objective physiological response, and subjective perception, supporting a more holistic and situated understanding of how urban environments influence well-being. The utility of our framework is then demonstrated through a naturalistic case study conducted in the Greater Philadelphia region, in which participants wore research-grade wearable sensors and carried GPS-enabled smartphones during their regular daily activities. Physiological indicators of autonomic nervous system activity, including heart rate variability and electrodermal activity, were synchronized with spatial trajectories and in-situ self-reports of stress, affect, and perceived infrastructure conditions. Results illustrate substantial inter and intraindividual variability within the study sample in both subjective experience and physiological response, as well as context-dependent patterns that may be associated with traffic exposure, pedestrian infrastructure quality, and environmental enclosure. The findings also suggest that commonly used walkability indices may not fully capture some experiential dimensions of pedestrian well-being within the contexts examined in this study. The proposed framework provides an initial methodological foundation for multimodal assessment of pedestrian experience that can be further evaluated across larger, more diverse populations and urban contexts.

Links and sources

• PDF from original source

Comments