arXiv subjects

Haojie Zhu

Publications and source records attributed to Haojie Zhu.

10 recordsLinked to original sources

arXiv2026

Programmable and scalable on-chip WDM processing platform enabled by cascaded FSR-free resonators

Wavelength-division multiplexing (WDM) is pivotal for expanding the capacity and functionality of photonic systems, from communications to computing. However, on-chip implementation for broadband operation is fundamentally limited by the narrow free spectral range (FSR) and inefficient drop transmission of conventional optical microcavities. Here, we transcend this limit with a scalable integrated WDM processing platform based on cascaded dual-sided coupled Fabry-Pérot add-drop resonators. This unit achieves a record-large FSR-free bandwidth (> 300 nm) and low insertion loss (< 0.5 dB), while enabling independent manipulation of monochromatic light in both the wavelength and intensity domains. Leveraging these performances, we architect programmable cores with up to 20 channels in a single bus waveguide to demonstrate application versatility by configuring as: a high-capacity on-chip WDM communication fabric (2.4-Tbps single-link WDM transmission and O-to-C-band multi-subband (de)triplexing), a reconfigurable optical processor (broadband and hitless wavelength-selective switching), and a parallel computing accelerator (theoretically capable of 1.28-TOPS convolution operations, 16-channel modulation). This work establishes a unified and versatile WDM processing platform that bridges high-speed optical communication with in-line computing, charting a scalable and backward-compatible path toward petabit-per-second-class links and hundreds of TOPS of on-chip computation, resolving a critical bottleneck for next-generation photonic systems.

physics.optics↗

arXiv2026

DECODE: Domain-aware Continual Domain Expansion for Motion Prediction

Motion prediction is critical for autonomous vehicles to effectively navigate complex environments and accurately anticipate the behaviors of other traffic participants. As autonomous driving continues to evolve, the need to assimilate new and varied driving scenarios necessitates frequent model updates through retraining. To address these demands, we introduce DECODE, a novel continual learning framework that begins with a pre-trained generalized model and incrementally develops specialized models for distinct domains. Unlike existing continual learning approaches that attempt to develop a unified model capable of generalizing across diverse scenarios, DECODE uniquely balances specialization with generalization, dynamically adjusting to real-time demands. The proposed framework leverages a hypernetwork to generate model parameters, significantly reducing storage requirements, and incorporates a normalizing flow mechanism for real-time model selection based on likelihood estimation. Furthermore, DECODE merges outputs from the most relevant specialized and generalized models using deep Bayesian uncertainty estimation techniques. This integration ensures optimal performance in familiar conditions while maintaining robustness in unfamiliar scenarios. Extensive evaluations confirm the effectiveness of the framework, achieving a notably low forgetting rate of 0.044 and an average minADE of 0.584 m, significantly surpassing traditional learning strategies and demonstrating adaptability across a wide range of driving conditions.

cs.CV↗

arXiv2026

Detecting low left ventricular ejection fraction from ECG using an interpretable and scalable predictor-driven framework

Low left ventricular ejection fraction (LEF) frequently remains undetected until progression to symptomatic heart failure, underscoring the need for scalable screening strategies. Although artificial intelligence-enabled electrocardiography (AI-ECG) has shown promise, existing approaches rely solely on end-to-end black-box models with limited interpretability or on tabular systems dependent on commercial ECG measurement algorithms with suboptimal performance. We introduced ECG-based Predictor-Driven LEF (ECGPD-LEF), a structured framework that integrates foundation model-derived diagnostic probabilities with interpretable modeling for detecting LEF from ECG. Trained on the benchmark EchoNext dataset comprising 72,475 ECG-echocardiogram pairs and evaluated in predefined independent internal (n=5,442) and external (n=16,017) cohorts, our framework achieved robust discrimination for moderate LEF (internal AUROC 88.4%, F1 64.5%; external AUROC 86.8%, F1 53.6%), consistently outperforming the official end-to-end baseline provided with the benchmark across demographic and clinical subgroups. Interpretability analyses identified high-impact predictors, including normal ECG, incomplete left bundle branch block, and subendocardial injury in anterolateral leads, driving LEF risk estimation. Notably, these predictors independently enabled zero-shot-like inference without task-specific retraining (internal AUROC 75.3-81.0%; external AUROC 71.6-78.6%), indicating that ventricular dysfunction is intrinsically encoded within structured diagnostic probability representations. This framework reconciles predictive performance with mechanistic transparency, supporting scalable enhancement through additional predictors and seamless integration with existing AI-ECG systems.

cs.LG↗

arXiv2025

Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving

Autonomous driving heavily relies on accurate and robust spatial perception. Many failures arise from inaccuracies and instability, especially in long-tail scenarios and complex interactions. However, current vision-language models are weak at spatial grounding and understanding, and VLA systems built on them therefore show limited perception and localization ability. To address these challenges, we introduce Percept-WAM, a perception-enhanced World-Awareness-Action Model that is the first to implicitly integrate 2D/3D scene understanding abilities within a single vision-language model (VLM). Instead of relying on QA-style spatial reasoning, Percept-WAM unifies 2D/3D perception tasks into World-PV and World-BEV tokens, which encode both spatial coordinates and confidence. We propose a grid-conditioned prediction mechanism for dense object perception, incorporating IoU-aware scoring and parallel autoregressive decoding, improving stability in long-tail, far-range, and small-object scenarios. Additionally, Percept-WAM leverages pretrained VLM parameters to retain general intelligence (e.g., logical reasoning) and can output perception results and trajectory control outputs directly. Experiments show that Percept-WAM matches or surpasses classical detectors and segmenters on downstream perception benchmarks, achieving 51.7/58.9 mAP on COCO 2D detection and nuScenes BEV 3D detection. When integrated with trajectory decoders, it further improves planning performance on nuScenes and NAVSIM, e.g., surpassing DiffusionDrive by 2.1 in PMDS on NAVSIM. Qualitative results further highlight its strong open-vocabulary and long-tail generalization.

cs.CV↗

arXiv2025

Improving Traffic Signal Data Quality for the Waymo Open Motion Dataset

Datasets pertaining to autonomous vehicles (AVs) hold significant promise for a range of research fields, including artificial intelligence (AI), autonomous driving, and transportation engineering. Nonetheless, these datasets often encounter challenges related to the states of traffic signals, such as missing or inaccurate data. Such issues can compromise the reliability of the datasets and adversely affect the performance of models developed using them. This research introduces a fully automated approach designed to tackle these issues by utilizing available vehicle trajectory data alongside knowledge from the transportation domain to effectively impute and rectify traffic signal information within the Waymo Open Motion Dataset (WOMD). The proposed method is robust and flexible, capable of handling diverse intersection geometries and traffic signal configurations in real-world scenarios. Comprehensive validations have been conducted on the entire WOMD, focusing on over 360,000 relevant scenarios involving traffic signals, out of a total of 530,000 real-world driving scenarios. In the original dataset, 71.7% of traffic signal states are either missing or unknown, all of which were successfully imputed by our proposed method. Furthermore, in the absence of ground-truth signal states, the accuracy of our approach is evaluated based on the rate of red-light violations among vehicle trajectories. Results show that our method reduces the estimated red-light running rate from 15.7% in the original data to 2.9%, thereby demonstrating its efficacy in rectifying data inaccuracies. This paper significantly enhances the quality of AV datasets, contributing to the wider AI and AV research communities and benefiting various downstream applications. The code and improved traffic signal data are open-sourced at https://github.com/michigan-traffic-lab/WOMD-Traffic-Signal-Data-Improvement

cs.RO↗

arXiv2025

Behavioral Safety Assessment towards Large-scale Deployment of Autonomous Vehicles

Autonomous vehicles (AVs) have significantly advanced in real-world deployment in recent years, yet safety continues to be a critical barrier to widespread adoption. Traditional functional safety approaches, which primarily verify the reliability, robustness, and adequacy of AV hardware and software systems from a vehicle-centric perspective, do not sufficiently address the AV's broader interactions and behavioral impact on the surrounding traffic environment. To overcome this limitation, we propose a paradigm shift toward behavioral safety, a comprehensive approach focused on evaluating AV responses and interactions within traffic environment. To systematically assess behavioral safety, we introduce a third-party AV safety assessment framework comprising two complementary evaluation components: Driver Licensing Test and Driving Intelligence Test. The Driver Licensing Test evaluates AV's reactive behaviors under controlled scenarios, ensuring basic behavioral competency. In contrast, the Driving Intelligence Test assesses AV's interactive behaviors within naturalistic traffic conditions, quantifying the frequency of safety-critical events to deliver statistically meaningful safety metrics before large-scale deployment. We validated our proposed framework using \texttt{Autoware.Universe}, an open-source Level 4 AV, tested both in simulated environments and on the physical test track at the University of Michigan's Mcity Testing Facility. The results indicate that \texttt{Autoware.Universe} passed 6 out of 14 scenarios and exhibited a crash rate of 3.01e-3 crashes per mile, approximately 1,000 times higher than average human driver crash rate. During the tests, we also uncovered several unknown unsafe scenarios for \texttt{Autoware.Universe}. These findings underscore the necessity of behavioral safety evaluations for improving AV safety performance prior to widespread public deployment.

cs.RO↗

arXiv2025

TeraSim: Uncovering Unknown Unsafe Events for Autonomous Vehicles through Generative Simulation

Traffic simulation is essential for autonomous vehicle (AV) development, enabling comprehensive safety evaluation across diverse driving conditions. However, traditional rule-based simulators struggle to capture complex human interactions, while data-driven approaches often fail to maintain long-term behavioral realism or generate diverse safety-critical events. To address these challenges, we propose TeraSim, an open-source, high-fidelity traffic simulation platform designed to uncover unknown unsafe events and efficiently estimate AV statistical performance metrics, such as crash rates. TeraSim is designed for seamless integration with third-party physics simulators and standalone AV stacks, to construct a complete AV simulation system. Experimental results demonstrate its effectiveness in generating diverse safety-critical events involving both static and dynamic agents, identifying hidden deficiencies in AV systems, and enabling statistical performance evaluation. These findings highlight TeraSim's potential as a practical tool for AV safety assessment, benefiting researchers, developers, and policymakers. The code is available at https://github.com/mcity/TeraSim.

cs.RO↗

arXiv2022

Electron transfer under the Floquet modulation in donor-bridge-acceptor systems

Electron transfer (ET) processes are of broad interest in modern chemistry. With the advancements of experimental techniques, one may modulate the ET via such as the light-matter interactions. In this work, we study the ET under a Floquet modulation occurring in the donor-bridge-acceptor systems, with the rate kernels projected out from the exact disspaton equation of motion formalism. This together with the Floquet theorem enables us to investigate the interplay between the intrinsic non-Markovianity and the driving periodicity. The observed rate kernel exhibits a Herzberg-Teller-like mechanism induced by the bridge fluctuation subject to effective modulation.

physics.chem-ph↗

arXiv2020

A Spatio-Temporal Kernel Density Estimation Framework for Predictive Crime Hotspot Mapping and Evaluation

Predictive hotspot mapping plays a critical role in hotspot policing. Existing methods such as the popular kernel density estimation (KDE) do not consider the temporal dimension of crime. Building upon recent works in related fields, this article proposes a spatio-temporal framework for predictive hotspot mapping and evaluation. Comparing to existing work in this scope, the proposed framework has four major features: (1) a spatio-temporal kernel density estimation (STKDE) method is applied to include the temporal component in predictive hotspot mapping, (2) a data-driven optimization technique, the likelihood cross-validation, is used to select the most appropriate bandwidths, (3) a statistical significance test is designed to filter out false positives in the density estimates, and (4) a new metric, the predictive accuracy index (PAI) curve, is proposed to evaluate predictive hotspots at multiple areal scales. The framework is illustrated in a case study of residential burglaries in Baton Rouge, Louisiana in 2011, and the results validate its utility.

stat.AP↗

arXiv2019

Simultaneous Identification and Control Using Active Signal Injection for Series Hybrid Electric Vehicles based on Dynamic Programming

Hybrid electric vehicles (HEVs) have an over-actuated system by including two power sources, a battery pack and an internal combustion engine. This feature of HEV is exploited in this paper to simultaneously achieve accurate identification of battery parameters/states. By actively injecting current signals, state of charge, state of health, and other battery parameters can be estimated in a specific sequence to improve the identification performance when compared to the case where all parameters and states are estimated concurrently using the baseline current signals. A dynamic programming strategy is developed to provide the benchmark results about how to balance the conflicting objectives corresponding to identification and system efficiency. The tradeoff between different objectives is presented to optimize the current profile so that the richness of signal can be ensured and the fuel economy can be optimized. In addition, simulation results show that the Root-Mean-Square error of the estimation can be decreased by up to 100% at a cost of less than 2% increase in fuel consumption. With the proposed simultaneous identification and control algorithm, the parameters/states of the battery can be monitored to ensure safe and efficient application of the battery for HEVs.

eess.SY↗