arXiv subjects

Yiru Jiao

Publications and source records attributed to Yiru Jiao.

6 recordsLinked to original sources

arXiv2026

Arrive and Survive: Scaling Safe Goal-Conditioned Policy Learning from One-Bit Failure Signals

Contrastive reinforcement learning (CRL) scales effectively in goal-conditioned tasks by casting policy learning into a self-supervised contrastive objective. However, in a failure-terminated Markov decision process, established CRL considers pre-failure future goals only when constructing positive samples, without accounting for the probability mass removed by failure termination. Our theoretical analysis shows that this omission induces a systematic overestimation bias in goal-reaching values. Consequently, near-failure trajectories provide disproportionately strong supervision of success despite retaining little future occupancy. Unsafe actions can thereby be reinforced through catastrophic failure bootstrapping, leading to failed policy learning and unsustainable goal-reaching behaviours. To address this problem, we introduce two minimal yet strong corrections: mass-weighted InfoNCE corrects the overweighting of short surviving futures in critic learning, and a log-survival-mass score restores the missing survival mass in policy optimization. The resulting method, Safe Contrastive Reinforcement Learning (Safe-CRL), requires only the one-bit signal provided by failure termination to scale safe goal-conditioned policy learning. Across twelve failure-prone robot navigation and locomotion tasks, Safe-CRL consistently improves survival and substantially outperforms the Scaling-CRL baseline in goal-reaching performance. Additionally, deep Safe-CRL policies exhibit complex failure-avoidance behaviours. This study completes the CRL theory under failure termination and provides a scalable safe RL framework. The code is available via https://github.com/RomainLITUD/safe-crl.

cs.LG↗

arXiv2025

Learning collision risk proactively from naturalistic driving data at scale

Accurately and proactively alerting drivers or automated systems to emerging collisions is crucial for road safety, particularly in highly interactive and complex urban environments. Existing methods either require labour-intensive annotation of sparse risk, struggle to consider varying contextual factors, or are tailored to limited scenarios. Here we present the Generalised Surrogate Safety Measure (GSSM), a data-driven approach that learns collision risk from naturalistic driving without the need for crash or risk labels. Trained over multiple datasets and evaluated on 2,591 real-world crashes and near-crashes, a basic GSSM using only instantaneous motion kinematics achieves an area under the precision-recall curve of 0.9, and secures a median time advance of 2.6 seconds to prevent potential collisions. Incorporating additional interaction patterns and contextual factors provides further performance gains. Across interaction scenarios such as rear-end, merging, and turning, GSSM consistently outperforms existing baselines in accuracy and timeliness. These results establish GSSM as a scalable, context-aware, and generalisable foundation to identify risky interactions before they become unavoidable, supporting proactive safety in autonomous driving systems and traffic incident management. Code and experiment data are openly accessible at https://github.com/Yiru-Jiao/GSSM.

cs.RO↗

arXiv2025

Structure-preserving contrastive learning for spatial time series

The effectiveness of neural network models largely relies on learning meaningful latent patterns from data, where self-supervised learning of informative representations can enhance model performance and generalisability. However, self-supervised representation learning for spatially characterised time series, which are ubiquitous in transportation domain, poses unique challenges due to the necessity of maintaining fine-grained spatio-temporal similarities in the latent space. In this study, we introduce two structure-preserving regularisers for the contrastive learning of spatial time series: one regulariser preserves the topology of similarities between instances, and the other preserves the graph geometry of similarities across spatial and temporal dimensions. To balance the contrastive learning objective and the need for structure preservation, we propose a dynamic weighting mechanism that adaptively manages this trade-off and stabilises training. We validate the proposed method through extensive experiments, including multivariate time series classification to demonstrate its general applicability, as well as macroscopic and microscopic traffic prediction to highlight its particular usefulness in encoding traffic interactions. Across all tasks, our method preserves the similarity structures more effectively and improves state-of-the-art task performances. This method can be integrated with an arbitrary neural network model and is particularly beneficial for time series data with spatial or geographical features. Furthermore, our findings suggest that well-preserved similarity structures in the latent space indicate more informative and useful representations. This provides insights to design more effective neural networks for data-driven transportation research. Our code is made openly accessible with all resulting data at https://github.com/yiru-jiao/spclt

cs.LG↗

arXiv2024

A Unified Probabilistic Approach to Traffic Conflict Detection

Traffic conflict detection is essential for proactive road safety by identifying potential collisions before they occur. Existing methods rely on surrogate safety measures tailored to specific interactions (e.g., car-following, side-swiping, or path-crossing) and require varying thresholds in different traffic conditions. This variation leads to inconsistencies and limited adaptability of conflict detection in evolving traffic environments. Consequently, a need persists for consistent detection of traffic conflicts across interaction contexts. To address this need, this study proposes a unified probabilistic approach. The proposed approach establishes a unified framework of traffic conflict detection, where traffic conflicts are formulated as context-dependent extreme events of road user interactions. The detection of conflicts is then decomposed into a series of statistical learning tasks: representing interaction contexts, inferring proximity distributions, and assessing extreme collision risk. The unified formulation accommodates diverse hypotheses of traffic conflicts and the learning tasks enable data-driven analysis of factors such as motion states of road users, environment conditions, and participant characteristics. Jointly, this approach supports consistent and comprehensive evaluation of the collision risk emerging in road user interactions. Our experiments using real-world trajectory data show that the approach provides effective collision warnings, generalises across distinct datasets and traffic environments, covers a broad range of conflict types, and captures a long-tailed distribution of conflict intensity. The findings highlight its potential to enhance the safety assessment of traffic infrastructures and policies, improve collision warning systems for autonomous driving, and deepen the understanding of road user behaviour in safety-critical interactions.

cs.RO↗

arXiv2023

A Conflict Resolution Dataset Derived from Argoverse-2: Analysis of the Safety and Efficiency Impacts of Autonomous Vehicles at Intersections

As the deployment of autonomous vehicles (AVs) in mixed traffic flow becomes increasingly prevalent, ensuring safe and smooth interactions between AVs and human agents is of critical importance. How road users resolve conflicts at intersections has significant impacts on driving safety and traffic efficiency. These impacts depend on both the behaviours of AVs and humans' reactions to the presence of AVs. Therefore, using real-world data to assess and compare the safety and efficiency measures of AV-involved and AV-free scenarios is crucial. To this end, this paper presents a high-quality conflict resolution dataset derived from the open Argoverse-2 motion forecasting data to analyse the safety and efficiency impacts of AVs. The contribution is twofold: First, we propose and apply a specific data processing pipeline to select scenarios of interest, rectify data errors, and enhance the raw data in Argoverse-2. As a result, 5000+ cases where an AV resolves conflict with a human road user and 16000+ conflict resolution cases without AVs are obtained. Motion data is smooth and consistent in these cases. This open dataset comprises diverse and balanced conflict resolution regimes. Second, this paper employs surrogate safety measures and a novel efficiency measure to assess the impact of AVs at intersections. The results suggest that human drivers exhibit similar safety and efficiency performances when interacting with AVs and with other human drivers. In contrast, pedestrians demonstrate more diverse reactions. Furthermore, due to the safety-prior strategy of AVs, the average efficiency of AV-involved conflict resolution decreases by 8.6% compared to AV-free cases. This informative dataset provides a valuable resource for researchers and the findings give insights into the possible impacts of AVs. The dataset is openly available via https://github.com/RomainLITUD/conflict_resolution_dataset.

cs.RO↗

arXiv2023

Large Car-following Data Based on Lyft level-5 Open Dataset: Following Autonomous Vehicles vs. Human-driven Vehicles

Car-Following (CF), as a fundamental driving behaviour, has significant influences on the safety and efficiency of traffic flow. Investigating how human drivers react differently when following autonomous vs. human-driven vehicles (HV) is thus critical for mixed traffic flow. Research in this field can be expedited with trajectory datasets collected by Autonomous Vehicles (AVs). However, trajectories collected by AVs are noisy and not readily applicable for studying CF behaviour. This paper extracts and enhances two categories of CF data, HV-following-AV (H-A) and HV-following-HV (H-H), from the open Lyft level-5 dataset. First, CF pairs are selected based on specific rules. Next, the quality of raw data is assessed by anomaly analysis. Then, the raw CF data is corrected and enhanced via motion planning, Kalman filtering, and wavelet denoising. As a result, 29k+ H-A and 42k+ H-H car-following segments are obtained, with a total driving distance of 150k+ km. A diversity assessment shows that the processed data cover complete CF regimes for calibrating CF models. This open and ready-to-use dataset provides the opportunity to investigate the CF behaviours of following AVs vs. HVs from real-world data. It can further facilitate studies on exploring the impact of AVs on mixed urban traffic.

eess.SY↗