Searcharxiv⌕ Search

arXiv subjects

Megan Applegate-Kenton

Publications and source records attributed to Megan Applegate-Kenton.

3 recordsLinked to original sources

Multimodal Masked Diffusion Autoencoder for Modeling Impaired Driving

Human cognitive state (e.g., distraction, stress), gaze, and behavior interact with the driving environment in subtle ways that AI could use to assist drivers, but ground-truth labels for human cognitive state levels are costly to obtain at scale. We propose a multimodal masked-diffusion autoencoder, ID-MAE, that adds a self-supervised objective to impairment prediction: alongside predicting the impairment label as a masked token, it reconstructs masked gaze and trajectory. To probe the effects of different modalities and types of impairments on model inference, we introduce DIVERT, a driving-simulator dataset containing 103 hours of driving data (n = 109) with ten impairment inductions spanning cognitive, visual, and emotional states, recorded with gaze, vehicle state, and scene video. We demonstrate how ID-MAE affords significant improvements in impairment inference results on both the DIVERT dataset and existing datasets, and enables strong results in additional tasks, such as trajectory and gaze prediction. For location-matched pairs, our model achieves a paired AUC of 0.706 for impairment detection on DIVERT, compared to 0.590 without reconstruction loss, improving over existing baselines. We probe the design space in terms of input modalities, masking scheme, positional encoding, attention mechanism, and decoding. We also investigate the interaction between various impairments in training and inference, demonstrating that visually demanding distractions are separable from cognitive distractions. Code and data will be available upon acceptance.

cs.CV↗

Dream to Assist: Intent-Conditioned World Models for Shared Vehicle Control

Assistive agents in shared-control settings face a dual challenge: acting proactively to align with the human's intentions while remaining legible enough for the human to comprehend and fluently respond in real time. We present Dream2Assist, a model-based reinforcement learning framework for tightly-coupled shared decision making that addresses both sides of this challenge. Our approach extends a recurrent state-space world model with intent inference, enabling an assistive policy trained via fictitious co-play to anticipate and support discrete human objectives without overriding human agency. Beyond the computational framework, we describe the full deployment pipeline needed to translate a world-model-based policy into a safe, human-centered system in a resource-efficient way. Crucially, we address the sim-to-real-human gap via policy down-selection and reward restructuring within an iterative human-machine interface design. We validate the framework through three human-subjects studies and a preliminary on-vehicle deployment spanning two qualitatively distinct domains: high-speed racing (N=30) and urban driving with richer intent structure (N=10). Our results demonstrate that intent conditioning yields measurable improvements in torque alignment and collision rate. We surface key design insights and practices for deploying learning-based assistive agents in safety-critical, real-time human-robot teaming.

cs.RO↗

Inconsistent by Design: A Systematic Review of Experimental Design Practices Across Impaired Driving Domains

Impaired driving, including distraction, fatigue, and intoxication, leads to thousands of fatalities annually. Impairment detection and related assistive technologies are rapidly advancing, but their full potential remains unrealized. The inconsistent maturity of impairment research and anomalies within individual domains are key barriers, including variations in taxonomic characterization, experimental data-collection methodologies, and treatment of impairments across studies. We present a unified review of impairment studies, covering 91 studies across nine impairment domains coded on three dimensions: impairment induction methods, scenario hazards, and observable phenomena and metrics. Our key findings include: (1) a proposed performance-degradation vs. event-response paradigm for existing impairment domains, (2) a maturity framework along the three dimensions, and (3) an analysis of impairment research methodologies, revealing anomalies and gaps in the treatment of scenarios and metrics. We further propose recommendations for standardizing methodologies to support future cross-domain research and development of holistic detection and assistive systems.

cs.HC↗