arXiv subjects

Zishuo Zhu

Publications and source records attributed to Zishuo Zhu.

4 recordsLinked to original sources

arXiv2026

NARRATE: A Multimodal Real-World Australian Driving Dataset for Human-Centred Explanations in Automated Driving

Automated vehicles must explain their decisions in ways that passengers can understand, monitor, and trust. Existing language-annotated driving datasets are mostly observer-written, post-hoc, simulation-based, or generated from sensor inputs, rather than elicited from the driver performing the action. We introduce NARRATE, a multimodal real-world Australian driving dataset comprising 2,050 annotated events from 35 experienced drivers and driving instructors on public roads. Each event is grounded in synchronised visual, localisation, motion, and LiDAR streams and paired with in-vehicle and/or post-drive free-text explanations. NARRATE provides action labels, scenario-context labels spanning six high-level and 32 fine-grained categories, and span-level Situational Awareness (SA) annotations over driver explanations for Perception, Comprehension and Projection. Four benchmark tasks (SA, scenario-context, driver-action classification, and explanation generation) show that this structure is learnable from driver language, while fine-grained context recognition and explanation generation remain challenging. NARRATE paves a path towards more human-centred and domain-aware explanation models for automated driving.

cs.CV↗

arXiv2026

X-Blocks: Linguistic Building Blocks of Natural Language Explanations for Automated Vehicles

Natural language explanations play a critical role in establishing trust and acceptance of automated vehicles (AVs), yet existing approaches lack systematic frameworks for analysing how humans linguistically construct driving rationales across diverse scenarios. This paper introduces X-Blocks (eXplanation Blocks), a hierarchical analytical framework that identifies the linguistic building blocks of natural language explanations for AVs at three levels: context, syntax, and lexicon. At the context level, we propose RACE (Reasoning-Aligned Classification of Explanations), a multi-LLM ensemble framework that combines Chain-of-Thought reasoning with self-consistency mechanisms to robustly classify explanations into 32 scenario-aware categories. Applied to human-authored explanations from the Berkeley DeepDrive-X dataset, RACE achieves 91.45 percent accuracy and a Cohens kappa of 0.91 against cases with human annotator agreement, indicating near-human reliability for context classification. At the lexical level, log-odds analysis with informative Dirichlet priors reveals context-specific vocabulary patterns that distinguish driving scenarios. At the syntactic level, dependency parsing and template extraction show that explanations draw from a limited repertoire of reusable grammar families, with systematic variation in predicate types and causal constructions across contexts. The X-Blocks framework is dataset-agnostic and task-independent, offering broad applicability to other automated driving datasets and safety-critical domains. Overall, our findings provide evidence-based linguistic design principles for generating scenario-aware explanations that support transparency, user trust, and cognitive accessibility in automated driving systems.

cs.AI↗

arXiv2025

Designing for Dignity while Driving: Interaction Needs of Blind and Low-Vision Passengers in Fully Automated Vehicles

Fully automated vehicles (FAVs) hold promise for enhancing the mobility of blind and low-vision (BLV) individuals. To understand the situated interaction needs of BLV passengers, we conducted six on-road, and in-lab focus groups with 16 participants, immersing them in real-world driving conditions. Our thematic analysis reveals that BLV participants express a high initial 'faith' in FAVs, but require layered, value-sensitive information during the ride to cultivate trust. The participants' modality preference for voice suggests re-evaluating the role of haptics for BLV users in FAVs. Our findings show the importance of a respectful interaction design in FAVs that both address BLV users' mobility challenges and uphold their dignity. While others have advocated for a dignity lens, our contribution lies in grounding this framework in empirical findings and unpacking what it means to design for dignity in the context of FAVs.

cs.HC↗

arXiv2024

A Random Forest-based Prediction Model for Turning Points in Antagonistic Event-Group Competitions

At present, most of the prediction studies related to antagonistic event-group competitions focus on the prediction of competition results, and less on the prediction of the competition process, which can not provide real-time feedback of the athletes' state information in the actual competition, and thus can not analyze the changes of the competition situation. In order to solve this problem, this paper proposes a prediction model based on Random Forest for the turning point of the antagonistic event-group. Firstly, the quantitative equation of competitive potential energy is proposed; Secondly, the quantitative value of competitive potential energy is obtained by using the dynamic combination of weights method, and the turning point of the competition situation of the antagonistic event-group is marked according to the quantitative time series graph; Finally, the random forest prediction model based on the optimisation of the KM-SMOTE algorithm and the grid search method is established. The experimental analysis shows that: The quantitative equation of competitive potential energy can effectively reflect the dynamic situation of the competition; The model can effectively predict the turning point of the competition situation of the antagonistic event-group, and the recall rate of the model in the test set is 86.13%; The model has certain significance for the future study of the competition situation of the antagonistic event-group.

cs.LG↗