arXiv subjects

Dengbo He

Publications and source records attributed to Dengbo He.

At least 19 recordsLinked to original sources

arXiv2026

SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use

Skills are becoming a reusable operational layer for LLM agents, encoding SOPs, domain rules, tool workflows, scripts, and validation routines. In realistic skill repositories, overlapping skills make reliable skill-use difficult. Final verifier success is too coarse for both evaluation and training, since an agent may pass through trial and error while selecting distractor skills, skipping required steps, composing workflows incorrectly or omitting final checks. We introduce SkillCoach, a self-evolving rubric framework for evaluating and enhancing agentic skill-use. SkillCoach derives skill-grounded process rubrics from real rollouts and evaluates trajectories along four dimensions: skill selection, skill following, skill composition, and skill-grounded reflection. It keeps the external verifier as a separate outcome signal, allowing process quality to be distinguished from accidental task success. The evolved rubrics further serve as process supervision for selecting high-quality training trajectories. Experiments show that evolved rubrics substantially improve evaluation quality, expose failures hidden by final accuracy, and provide stronger supervision signals than outcome-only filtering for enhancing agentic skill-use.

cs.AI↗

arXiv2026

MILD: Mediator Agent System with Bidirectional Perception and Multi-Layered Alignment for Human-Vehicle Collaboration

Prior studies report that partial driving automation can increase the cognitive demands on human drivers. This effect largely arises from human drivers' lack of transparent insight into the vehicle's intentions and decision logic, as well as from automated systems' limited awareness of the driver's dynamic state and preferences. This bidirectional misalignment undermines shared situational awareness and exacerbates coordination failures in human-vehicle interaction. To address these limitations, we argue for a paradigm shift that elevates the human role from passive supervisor to active manager. We introduce the Mediator-in-the-Loop-Driving (MILD) system, based on an agentic system architecture to facilitate synergistic human-vehicle collaboration. MILD integrates a perception agent for joint in-cabin and out-of-cabin understanding with a lightweight strategy agent that generates compliant and explainable action suggestions. To ensure these strategies are strictly aligned with safety regulations and human values, we develop Evidence- and Constraint-weighted Policy Optimization (ECPO). ECPO leverages automatic validators to steer the agent toward behaviors that are not only accurate but also structurally complete, substantiated by evidence, and free from constraint violations. Furthermore, a retrieval-augmented generation module dynamically incorporates constraints from traffic regulations, speed recommendations, and driver preferences into the decision loop. Field experiments across three open datasets demonstrate that MILD consistently outperforms baselines in both perception accuracy and strategy quality under auditable offline metrics, and yields higher human-rated policy adequacy, comfort, and explanation than baselines. This work offers a practical pathway for building auditable and aligned agents for human-vehicle collaborative driving.

cs.AI↗

arXiv2026

From Awareness to Intent: Mitigating Silent Driving System Failures through Prospective Situation Awareness Enhancing Interfaces

Silent automation failures, where a system fails to detect a hazard without warning, pose a critical safety challenge for partially automated vehicles. While research has mostly focused on takeover requests, how to support a driver in silent failure remains underexplored. We conducted a multi-modal driving simulator study with 48 participants to investigate how different Prospective Situation Awareness Enhancement (PSAE) interfaces, delivered via augmented reality head-up display, affect takeover performance. By integrating behavioral, subjective psychological, and physiological data, our analysis suggests that situational awareness (SA) serves as an important moderating factor through which PSAE interfaces improve takeover performance. Further, we found that providing perceptual cues was most effective in enhancing SA, while communicating system intent was superior for building trust. Finally, we identified a potential correlate of SA in the neuroactivity. Overall, this paper contributes to understanding how transparency-oriented interfaces may support drivers and provides design insights into HMI design for silent failures.

cs.HC↗

arXiv2025

PAVE: An End-to-End Dataset for Production Autonomous Vehicle Evaluation

Most existing autonomous-driving datasets (e.g., KITTI, nuScenes, and the Waymo Perception Dataset), collected by human-driving mode or unidentified driving mode, can only serve as early training for the perception and prediction of autonomous vehicles (AVs). To evaluate the real behavioral safety of AVs controlled in the black box, we present the first end-to-end benchmark dataset collected entirely by autonomous-driving mode in the real world. This dataset contains over 100 hours of naturalistic data from multiple production autonomous-driving vehicle models in the market. We segment the original data into 32,727 key frames, each consisting of four synchronized camera images and high-precision GNSS/IMU data (0.8 cm localization accuracy). For each key frame, 20 Hz vehicle trajectories spanning the past 6 s and future 5 s are provided, along with detailed 2D annotations of surrounding vehicles, pedestrians, traffic lights, and traffic signs. These key frames have rich scenario-level attributes, including driver intent, area type (covering highways, urban roads, and residential areas), lighting (day, night, or dusk), weather (clear or rain), road surface (paved or unpaved), traffic and vulnerable road users (VRU) density, traffic lights, and traffic signs (warning, prohibition, and indication). To evaluate the safety of AVs, we employ an end-to-end motion planning model that predicts vehicle trajectories with an Average Displacement Error (ADE) of 1.4 m on autonomous-driving frames. The dataset continues to expand by over 10 hours of new data weekly, thereby providing a sustainable foundation for research on AV driving behavior analysis and safety evaluation. The PAVE dataset is publicly available at https://hkustgz-my.sharepoint.com/:f:/g/personal/kema_hkust-gz_edu_cn/IgDXyoHKfdGnSZ3JbbidjduMAXxs-Z3NXzm005A_Ix9tr0Q?e=9HReCu.

cs.CV↗

arXiv2025

FedHUG: Federated Heterogeneous Unsupervised Generalization for Remote Physiological Measurements

Remote physiological measurement gained wide attention, while it requires collecting users' privacy-sensitive information, and existing contactless measurements still rely on labeled client data. This presents challenges when we want to further update real-world deployed models with numerous user data lacking labels. To resolve these challenges, we instantiate a new protocol called Federated Unsupervised Domain Generalization (FUDG) in this work. Subsequently, the \textbf{Fed}erated \textbf{H}eterogeneous \textbf{U}nsupervised \textbf{G}eneralization (\textbf{FedHUG}) framework is proposed and consists of: (1) Minimal Bias Aggregation module dynamically adjusts aggregation weights based on prior-driven bias evaluation to cope with heterogeneous non-IID features from multiple domains. (2) The Global Distribution-aware Learning Controller parameterizes the label distribution and dynamically manipulates client-specific training strategies, thereby mitigating the server-client label distribution skew and long-tail issue. The proposal shows superior performance across state-of-the-art techniques in estimation with either RGB video or mmWave radar. The code will be released.

cs.CV↗

arXiv2025

The Formation of Trust in Autonomous Vehicles after Interacting with Robotaxis on Public Roads

This study investigates how pedestrian trust, receptivity, and behavior evolve during interactions with Level-4 autonomous vehicles (AVs) at uncontrolled urban intersections in a naturalistic setting. While public acceptance is critical for AV adoption, most prior studies relied on simplified simulations or field tests. We conducted a real-world experiment in a commercial Robotaxi operation zone, where 33 participants repeatedly crossed an uncontrolled intersection with frequent Level-4 Robotaxi traffic. Participants completed the Pedestrian Behavior Questionnaire (PBQ), Pedestrian Receptivity Questionnaire for Fully AVs (PRQF), pre- and post-experiment Trust in AVs Scale, and Personal Innovativeness Scale (PIS). Results showed that trust in AVs significantly increased post-experiment, with the increase positively associated with the Interaction component of PRQF. Additionally, both the Positive and Error subscales of the PBQ significantly influenced trust change. This study reveals how trust forms in real-world pedestrian-AV encounters, offering insights beyond lab-based research by accounting for population heterogeneity.

cs.HC↗

arXiv2025

PhysDrive: A Multimodal Remote Physiological Measurement Dataset for In-vehicle Driver Monitoring

Robust and unobtrusive in-vehicle physiological monitoring is crucial for ensuring driving safety and user experience. While remote physiological measurement (RPM) offers a promising non-invasive solution, its translation to real-world driving scenarios is critically constrained by the scarcity of comprehensive datasets. Existing resources are often limited in scale, modality diversity, the breadth of biometric annotations, and the range of captured conditions, thereby omitting inherent real-world challenges in driving. Here, we present PhysDrive, the first large-scale multimodal dataset for contactless in-vehicle physiological sensing with dedicated consideration on various modality settings and driving factors. PhysDrive collects data from 48 drivers, including synchronized RGB, near-infrared camera, and raw mmWave radar data, accompanied with six synchronized ground truths (ECG, BVP, Respiration, HR, RR, and SpO2). It covers a wide spectrum of naturalistic driving conditions, including driver motions, dynamic natural light, vehicle types, and road conditions. We extensively evaluate both signal-processing and deep-learning methods on PhysDrive, establishing a comprehensive benchmark across all modalities, and release full open-source code with compatibility for mainstream public toolboxes. We envision PhysDrive will serve as a foundational resource and accelerate research on multimodal driver monitoring and smart-cockpit systems.

cs.AI↗

arXiv2025

Not Only Consistency: Enhance Test-Time Adaptation with Spatio-temporal Inconsistency for Remote Physiological Measurement

Remote physiological measurement (RPM) has emerged as a promising non-invasive method for monitoring physiological signals using the non-contact device. Although various domain adaptation and generalization methods were proposed to promote the adaptability of deep-based RPM models in unseen deployment environments, considerations in aspects such as privacy concerns and real-time adaptation restrict their application in real-world deployment. Thus, we aim to propose a novel fully Test-Time Adaptation (TTA) strategy tailored for RPM tasks in this work. Specifically, based on prior knowledge in physiology and our observations, we noticed not only there is spatio-temporal consistency in the frequency domain of BVP signals, but also that inconsistency in the time domain was significant. Given this, by leveraging both consistency and inconsistency priors, we introduce an innovative expert knowledge-based self-supervised \textbf{C}onsistency-\textbf{i}n\textbf{C}onsistency-\textbf{i}ntegration (\textbf{CiCi}) framework to enhances model adaptation during inference. Besides, our approach further incorporates a gradient dynamic control mechanism to mitigate potential conflicts between priors, ensuring stable adaptation across instances. Through extensive experiments on five diverse datasets under the TTA protocol, our method consistently outperforms existing techniques, presenting state-of-the-art performance in real-time self-supervised adaptation without accessing source data. The code will be released later.

cs.CV↗

arXiv2025

The impact of the following vehicles behaviors on the car following behaviors of the ego-vehicle

Among all types of crashes, rear-end crashes dominate, which are closely related to the car-following (CF) behaviors. Traditional CF behavior models focused on the influence of the vehicle in front, but usually ignored the peer pressure from the surrounding road users, including the following vehicle (FV). Based on an open dataset, the highD dataset, we investigated whether the FV's states can affect the CF behavior of the ego-vehicle in CF events. Two types of CF events were extracted from highD database, including the tailgated events, where the time headway between the FV and the ego-vehicle (i.e., time gap) was smaller than 1 second, and the gapped events, where the time gap was larger than 3 seconds. The dynamic time warping was used to extract CF pairs with similar speed profiles of the leading vehicle (LV). Statistical analyses were conducted to compare the CF-performance metrics in tailgated and gapped events. Then, the inverse reinforcement learning was used to recover the reward function of the ego-vehicle drivers in different CF events. The results showed that the ego-driver would adjust their CF behavior in response to the pressure from a tailgating FV, by maintaining a closer distance to the LV, but at the same time, driving more cautiously. Further, drivers were still able to adjust their CF strategies based on the speed of traffic flow and the distance to the LV, even when being tailgated. These findings provide insights regarding more accurate modelling of traffic flow by considering the peer pressure from surrounding road users.

eess.SY↗

arXiv2025

Do Electric Vehicles Induce More Motion Sickness Than Fuel Vehicles? A Survey Study in China

Electric vehicles (EVs) are a promising alternative to fuel vehicles (FVs), given some unique characteristics of EVs, for example, the low air pollution and maintenance cost. However, the increasing prevalence of EVs is accompanied by widespread complaints regarding the high likelihood of motion sickness (MS) induction, especially when compared to FVs, which has become one of the major obstacles to the acceptance and popularity of EVs. Despite the prevalence of such complaints online and among EV users, the association between vehicle type (i.e., EV versus FV) and MS prevalence and severity has not been quantified. Thus, this study aims to investigate the existence of EV-induced MS and explore the potential factors leading to it. A survey study was conducted to collect passengers' MS experience in EVs and FVs in the past one year. In total, 639 valid responses were collected from mainland China. The results show that FVs were associated with a higher frequency of MS, while EVs were found to induce more severe MS symptoms. Further, we found that passengers' MS severity was associated with individual differences (i.e., age, gender, sleep habits, susceptibility to motion-induced MS), in-vehicle activities (i.e., chatting with others and watching in-vehicle displays), and road conditions (i.e., congestion and slope), while the MS frequency was associated with the vehicle ownership and riding frequency. The results from this study can guide the directions of future empirical studies that aim to quantify the inducers of MS in EVs and FVs, as well as the optimization of EVs to reduce MS.

cs.HC↗

arXiv2025

Supporting Car-Following Behavior through V2V-Based Beyond-Visual-Range Information Display

Rear-end collisions constituted a large portion of crashes on the road, despite efforts to mitigate rear-end collisions, such as forward collision warnings. The chance of rear-end collisions is closely related to drivers' car-following (CF) behaviors in the traffic flow. Given that drivers may rely on more than the information of the direct lead vehicle (DLV) when making CF decisions, expanding drivers' perceptual range by providing beyond-visual-range (BVR) information based on vehicle-to-vehicle (V2V) communication may enhance CF safety. Thus, four different human-machine interfaces (HMIs) providing various types of BVR information in CF events were designed, including Brake-HMI showing only brake action of indirect lead vehicles (ILV), Dis-HMI and THW-HMI showing the relative distance and time headway between the ILV and DLV, respectively, and Video-HMI showing the live-stream video of ILV from the perspective of DLV. A driving simulator experiment with 40 participants was conducted to evaluate the impact of BVR-based HMI on driving safety in CF events. We found that, in general, BVR information could improve CF safety without overloading drivers and compromising their visual attention allocation strategies, particularly among novice drivers, by enabling quicker brake responses and increasing time headway and time-to-collision in brake events. The Brake-HMI yielded the safest performance in chain brake events, whereas Video-HMI increased attentional demands without observable benefits. This research provides insights into enabling drivers' BVR perception based on V2V communication to enhance driving safety in CF scenarios.

cs.HC↗

arXiv2025

Align the GAP: Prior-based Unified Multi-Task Remote Physiological Measurement Framework For Domain Generalization and Personalization

Multi-source synsemantic domain generalization (MSSDG) for multi-task remote physiological measurement seeks to enhance the generalizability of these metrics and attracts increasing attention. However, challenges like partial labeling and environmental noise may disrupt task-specific accuracy. Meanwhile, given that real-time adaptation is necessary for personalized products, the test-time personalized adaptation (TTPA) after MSSDG is also worth exploring, while the gap between previous generalization and personalization methods is significant and hard to fuse. Thus, we proposed a unified framework for MSSD\textbf{G} and TTP\textbf{A} employing \textbf{P}riors (\textbf{GAP}) in biometrics and remote photoplethysmography (rPPG). We first disentangled information from face videos into invariant semantics, individual bias, and noise. Then, multiple modules incorporating priors and our observations were applied in different stages and for different facial information. Then, based on the different principles of achieving generalization and personalization, our framework could simultaneously address MSSDG and TTPA under multi-task remote physiological estimation with minimal adjustments. We expanded the MSSDG benchmark to the TTPA protocol on six publicly available datasets and introduced a new real-world driving dataset with complete labeling. Extensive experiments that validated our approach, and the codes along with the new dataset will be released.

cs.CV↗

arXiv2025

Towards Generalizable Drowsiness Monitoring with Physiological Sensors: A Preliminary Study

Accurately detecting drowsiness is vital to driving safety. Among all measures, physiological-signal-based drowsiness monitoring can be more privacy-preserving than a camera-based approach. However, conflicts exist regarding how physiological metrics are associated with different drowsiness labels across datasets. Thus, we analyzed key features from electrocardiograms (ECG), electrodermal activity (EDA), and respiratory (RESP) signals across four datasets, where different drowsiness inducers (such as fatigue and low arousal) and assessment methods (subjective vs. objective) were used. Binary logistic regression models were built to identify the physiological metrics that are associated with drowsiness. Findings indicate that distinct different drowsiness inducers can lead to different physiological responses, and objective assessments were more sensitive than subjective ones in detecting drowsiness. Further, the increased heart rate stability, reduced respiratory amplitude, and decreased tonic EDA are robustly associated with increased drowsiness. The results enhance understanding of drowsiness detection and can inform future generalizable monitoring designs.

eess.SP↗

arXiv2025

Sage Deer: A Super-Aligned Driving Generalist Is Your Copilot

The intelligent driving cockpit, an important part of intelligent driving, needs to match different users' comfort, interaction, and safety needs. This paper aims to build a Super-Aligned and GEneralist DRiving agent, SAGE DeeR. Sage Deer achieves three highlights: (1) Super alignment: It achieves different reactions according to different people's preferences and biases. (2) Generalist: It can understand the multi-view and multi-mode inputs to reason the user's physiological indicators, facial emotions, hand movements, body movements, driving scenarios, and behavioral decisions. (3) Self-Eliciting: It can elicit implicit thought chains in the language space to further increase generalist and super-aligned abilities. Besides, we collected multiple data sets and built a large-scale benchmark. This benchmark measures the deer's perceptual decision-making ability and the super alignment's accuracy.

cs.CV↗

arXiv2025

When and How to Integrate Multimodal Large Language Models in College Psychotherapy: Perspectives from Multi-stakeholders

As mental health issues rise among college students, there is an increasing interest and demand in leveraging Multimodal Language Models (MLLM) to enhance mental support services, yet integrating them into psychotherapy remains theoretical or non-user-centered. This study investigated the opportunities and challenges of using MLLMs within the campus psychotherapy alliance in China. Through three studies involving both therapists and student clients, we argue that the ideal role for MLLMs at this stage is as an auxiliary tool to human therapists. Users widely expect features such as triage matching and real-time emotion recognition. At the same time, for independent therapy by MLLM, concerns about capabilities and privacy ethics remain prominent, despite high demands for personalized avatars and non-verbal communication. Our findings further indicate that users' sense of social identity and perceived relative status of MLLMs significantly influence their acceptance. This study provides insights for future intelligent campus mental healthcare.

cs.HC↗

arXiv2024

STAHGNet: Modeling Hybrid-grained Heterogenous Dependency Efficiently for Traffic Prediction

Traffic flow prediction plays a critical role in the intelligent transportation system, and it is also a challenging task because of the underlying complex Spatio-temporal patterns and heterogeneities evolving across time. However, most present works mostly concentrate on solely capturing Spatial-temporal dependency or extracting implicit similarity graphs, but the hybrid-granularity evolution is ignored in their modeling process. In this paper, we proposed a novel data-driven end-to-end framework, named Spatio-Temporal Aware Hybrid Graph Network (STAHGNet), to couple the hybrid-grained heterogeneous correlations in series simultaneously through an elaborately Hybrid Graph Attention Module (HGAT) and Coarse-granularity Temporal Graph (CTG) generator. Furthermore, an automotive feature engineering with domain knowledge and a random neighbor sampling strategy is utilized to improve efficiency and reduce computational complexity. The MAE, RMSE, and MAPE are used for evaluation metrics. Tested on four real-life datasets, our proposal outperforms eight classical baselines and four state-of-the-art (SOTA) methods (e.g., MAE 14.82 on PeMSD3; MAE 18.92 on PeMSD4). Besides, extensive experiments and visualizations verify the effectiveness of each component in STAHGNet. In terms of computational cost, STAHGNet saves at least four times the space compared to the previous SOTA models. The proposed model will be beneficial for more efficient TFP as well as intelligent transport system construction.

cs.AI↗

arXiv2024

Modeling Battery Electric Vehicle Users' Charging Decisions in Scenarios with Both Time-Related and Distance-Related Anxiety

As one of the most promising alternatives to internal combustion engine vehicles, battery electric vehicles (BEVs) have become increasingly prevalent in recent years. However, range anxiety is still a major concern among BEV users or potential users in recent years. The social-psychological factors were found to be associated with range anxiety, but how the charging decisions are affected by range anxiety is still unclear. Thus, in our study, through an online questionnaire issued in mainland China, we collected 230 participants' charging decisions in 60 range-anxiety-inducing scenarios in which both distance-related, and time-related anxiety co-existed. Then, an interpretable machine learning (ML) approach with the Shapley Additive Explanations method was used to model BEV users' charging decisions in these scenarios. To further explore users' decision-making mechanisms, a Bayesian-Network-regression mixed approach was used to model the inner topological structure among the factors influencing users' decisions. We find that both time-related and distance-related factors can affect users' charging decisions, but the influence of waiting time is softer compared to the BEV range. Users' charging decisions can also be moderated by users' psychological states (i.e., range anxiety level and trust in range estimation system), individual differences (i.e., age and personality), and BEV using experience (i.e., driving mileage, display mileage and range estimation cycle of range estimation system), of which, the range anxiety level is more directly related with users' charging decisions. Findings from this study can provide insights into the optimization of charge station distribution and customization of the charging recommendation system.

cs.HC↗

arXiv2024

Revisiting Interactions of Multiple Driver States in Heterogenous Population and Cognitive Tasks

In real-world driving scenarios, multiple states occur simultaneously due to individual differences and environmental factors, complicating the analysis and estimation of driver states. Previous studies, limited by experimental design and analytical methods, may not be able to disentangle the relationships among multiple driver states and environmental factors. This paper introduces the Double Machine Learning (DML) analysis method to the field of driver state analysis to tackle this challenge. To train and test the DML model, a driving simulator experiment with 42 participants was conducted. All participants drove SAE level-3 vehicles and conducted three types of cognitive tasks in a 3-hour driving experiment. Drivers' subjective cognitive load and drowsiness levels were collected throughout the experiment. Then, we isolated individual and environmental factors affecting driver state variations and the factors affecting drivers' physiological and eye-tracking metrics when they are under specific states. The results show that our approach successfully decoupled and inferred the complex causal relationships between multiple types of drowsiness and cognitive load. Additionally, we identified key physiological and eye-tracking indicators in the presence of multiple driver states and under the influence of a single state, excluding the influence of other driver states, environmental factors, and individual characteristics. Our causal inference analytical framework can offer new insights for subsequent analysis of drivers' states. Further, the updated causal relation graph based on the DML analysis can provide theoretical bases for driver state monitoring based on physiological and eye-tracking measures.

cs.HC↗