Text to Blind Motion

TL;DR

This paper introduces BlindWays, a novel multimodal benchmark dataset capturing 3D motion and textual descriptions of blind pedestrians in urban environments, highlighting the limitations of current models in understanding diverse human movement behaviors.

Contribution

The work presents the first dataset of 3D motion and textual descriptions for blind pedestrians, and evaluates existing models, revealing their poor performance on this new, diverse data.

Findings

State-of-the-art models perform poorly on blind pedestrian data.

Blind pedestrians exhibit distinct movement patterns not captured by current models.

The dataset enables future research on diverse human motion understanding.

Abstract

People who are blind perceive the world differently than those who are sighted, which can result in distinct motion characteristics. For instance, when crossing at an intersection, blind individuals may have different patterns of movement, such as veering more from a straight path or using touch-based exploration around curbs and obstacles. These behaviors may appear less predictable to motion models embedded in technologies such as autonomous vehicles. Yet, the ability of 3D motion models to capture such behavior has not been previously studied, as existing datasets for 3D human motion currently lack diversity and are biased toward people who are sighted. In this work, we introduce BlindWays, the first multimodal motion benchmark for pedestrians who are blind. We collect 3D motion data using wearable sensors with 11 blind participants navigating eight different routes in a real-world urban setting. Additionally, we provide rich textual descriptions that capture the distinctive movement characteristics of blind pedestrians and their interactions with both the navigation aid (e.g., a white cane or a guide dog) and the environment. We benchmark state-of-the-art 3D human prediction models, finding poor performance with off-the-shelf and pre-training-based methods for our novel task. To contribute toward safer and more reliable systems that can seamlessly reason over diverse human movements in their environments, our text-and-motion benchmark is available at https://blindways.github.io.