arXiv subjects

Yiheng Feng

Publications and source records attributed to Yiheng Feng.

At least 19 recordsLinked to original sources

arXiv2026

RoboSense: Leveraging Robotaxi Fleets as Drive-by Sensors for Urban Traffic Monitoring

Urban traffic monitoring plays a critical role in safety analysis, congestion management, and incident response. The growing deployment of robotaxis creates a new opportunity for network-level traffic monitoring. Although robotaxis are primarily designed to serve passengers, they can also be leveraged as drive-by sensors to collect traffic data. Compared to conventional infrastructure sensors or probe vehicles, a fleet of robotaxis forms a cooperative perception environment, which can collectively gather spatially and temporally continuous traffic information. This paper proposes a novel dynamic robotaxi routing framework that explicitly incorporates traffic monitoring tasks as an objective. The framework introduces: (1) a cell-based network representation that aligns with sensing capabilities of robotaxis; (2) a cell-level monitoring metric to quantify spatiotemporal robotaxi coverage; and (3) a mixed-integer linear programming (MILP) formulation that jointly minimizes time-dependent travel time and maximizes traffic monitoring performance. A 5 by 5 urban grid network is built in SUMO to evaluate the framework under three robotaxi market penetration rates (2%, 5%, and 10%) with a range of objective weight combinations. Results show that incorporating spatiotemporal network coverage in the objective function can effectively improve the traffic monitoring performance. Interestingly, with appropriate weights between the two objectives, monitoring performance and robotaxi average speed can be improved simultaneously. This suggests better network monitoring leads to more accurate traffic state prediction and improved mobility. This win-win situation could incentivize robotaxi operators to contribute their vehicles as drive-by sensors for traffic monitoring.

cs.RO↗

arXiv2026

Drones as Annotators: Amodal 3D Auto-Labeling for Ground LiDAR with Aerial Priors

Scaling perception data in autonomous driving is hindered by manual 3D bounding box annotation, a costly and labor intensive process requiring substantial domain expertise. Existing auto-labeling methods reduce this burden, but most of them rely on onboard sensors, where a single ground-level viewpoint yields occluded and sparse observations and inaccurate object geometry. We introduce DAA (Drones as Annotators), a drone-assisted training-free framework for amodal 3D auto-labeling. DAA augments ground LiDAR with an aerial agent that provides less occluded vehicle detections with continuous tracks. Ground LiDAR, in turn, provides precise metric 3D geometry unavailable from aerial imagery alone. DAA exploits the two complementary yet heterogeneous modalities through a two-stage framework: (i) air-ground coordinate alignment unifies aerial detections and ground LiDAR scans into a shared map frame and bootstraps coarse 3D bounding boxes from the aligned aerial detections; (ii) EM-like amodal box refinement alternates between identifying the vehicle's foreground points and updating the coarse box from the identified foreground and aerial priors. We evaluate DAA on an air-ground cooperative perception dataset, where it consistently outperforms existing auto-labeling baselines. LiDAR detectors trained on DAA-generated labels remain competitive with those trained on manual annotations at moderate IoU thresholds. Evaluation against a reference vehicle with known poses and dimensions further confirms its accuracy. We also demonstrate that DAA transfers, without parameter retuning, from onboard to stationary roadside LiDAR and to multi-agent fused point clouds. Code and dataset will be released upon publication.

eess.IV↗

arXiv2026

Common-Center Geometry and Certified Radial Reconstruction for Energy-Form Full Conformal Regions

This note studies the geometry of full conformal prediction (FullCP) regions generated by an empirical energy-form pairwise score. Candidate-score convexity alone does not guarantee connected FullCP regions, even for empirical averages of losses convex in the candidate argument. For the energy-form score, each leave-one-out training comparison reduces exactly to a pairwise-dissimilarity sublevel condition. Under symmetry, a constant diagonal, a diagonal lower bound, and attainment of the associated Fr\'echet-type objective, all comparison regions share a minimizer; if they are convex, every nontrivial exact conformal region is star-shaped about that point. For power distances $\rho_\beta(x,y)=\|x-y\|^\beta$, this geometry holds for $\beta\ge1$, while the conventional energy score is strictly proper for $0<\beta<2$. For $d=1,\beta=1$, every nontrivial empirical-CRPS FullCP region is a nonempty closed interval (possibly $\mathbb R$ when $m=1$). For $1<\beta<2$ and $m\ge2$, explicit data-checkable derivative bounds give Lipschitz control of the radial exits and exact conformal radial function. Combined with directional root search and classical Lipschitz extensions, they yield certified inner and outer radial envelopes of width at most $\delta+2\widetilde Lh_{\mathcal U}$ and same-ray Hausdorff guarantees. An analytic two-dimensional example shows why preserving star-shaped but nonconvex geometry can matter. A staged two-dimensional study finds modest but systematic tightening of the generic certificate and frequent robust nonconvexity witnesses, with detected normalized radial departures typically small. The method is intended for low-dimensional multivariate outputs rather than high-dimensional scaling or runtime improvement.

stat.ML↗

arXiv2026

Transferable Reinforcement Learning via Probabilistic Latent Embeddings and Dynamic Policy Adaptation for Sim-to-Real Deployment

Due to limited resources and public safety concerns, deep reinforcement learning (RL) agents for many cyber-physical systems (e.g., autonomous vehicles) are first trained in simulators. However, when deployed in real world environments, they often suffer from performance degradation or safety violations because of the inevitable Sim2Real gap. Existing zero-shot approaches, such as robust safe RL and domain randomization, mitigate this issue but typically at the cost of degraded performance or residual safety risks when experiencing unmodeled system dynamics. To address these limitations, we propose a novel reinforcement learning framework that enables safe and efficient policy transfer via probabilistic latent embeddings and dynamic policy adaptation. We consider a family of Constrained Markov Decision Processes (CMDPs) under different environment contexts. By leveraging latent context variable in meta-RL, the proposed framework infers the latent representation of the environment from simulated experiences. Furthermore, it incorporates a distributional RL formulation, which allows risk levels of the deployed policy to be adjusted dynamically, based on the estimation accuracy of the latent context variable. This strategy promotes safety at the early deployment stage and improves efficiency through fast policy adaptation under the Sim2Real gap.

cs.LG↗

arXiv2026

Empowering Microscopic Traffic Simulators with Realistic Perception using Surrogate Sensor Models

Simulation is central to the evaluation of intelligent transportation system (ITS) applications. As ITS increasingly incorporates autonomous vehicle (AV) technologies as fleet vehicles and/or mobile sensors, accurate modeling of their perception capabilities becomes essential in high-fidelity simulations. While game-engine-based simulators reproduce realistic perception environments through 3D scene rendering and raw sensor data generation, they face scalability challenges in simulating traffic networks with a large number of AVs due to high computational cost. In contrast, microscopic traffic simulators (MTS) can scale efficiently but lack perception modeling capabilities. To bridge this gap, we propose MIDAR, a surrogate LiDAR detection model that mimics realistic LiDAR detections using only high-level features readily available from MTS. Specifically, MIDAR predicts true-positive and false-negative LiDAR detections based on the relative positions and dimensions of surrounding objects. To capture LiDAR visibility and occlusion effects, MIDAR introduces a ray-hit feature and a Refined Multi-hop Line-of-Sight (RM-LoS) graph processed by a geometry-aware Graph Transformer. MIDAR achieves an AUC of 0.94 in approximating LiDAR detection results using CARLA-generated point cloud data, and an AUC of 0.86 with real-world data from the nuScenes dataset. Two ITS applications, cooperative-perception-based adaptive signal control and vehicle trajectory reconstruction, are integrated with MIDAR to further validate its realism and necessity. Results show that MIDAR generates more realistic detection outputs as well as application-level performance metrics than simplified perception models while introducing minimal computational overhead, enabling seamless integration into large-scale, real-time traffic simulations. The code and data are publicly available at https://github.com/Purdue-CART-Lab/MIDAR.

cs.CV↗

arXiv2026

Found-RL: foundation model-enhanced reinforcement learning for autonomous driving

Reinforcement Learning (RL) has emerged as a dominant paradigm for end-to-end autonomous driving (AD). However, RL suffers from sample inefficiency and a lack of semantic interpretability in complex scenarios. Foundation Models, particularly Vision-Language Models (VLMs), can mitigate this by offering rich, context-aware knowledge, yet their high inference latency hinders deployment in high-frequency RL training loops. To bridge this gap, we present Found-RL, a platform tailored to efficiently enhance RL for AD using foundation models. A core innovation is the asynchronous batch inference framework, which decouples heavy VLM reasoning from the simulation loop, effectively resolving latency bottlenecks to support real-time learning. We introduce diverse supervision mechanisms: Value-Margin Regularization (VMR) and Advantage-Weighted Action Guidance (AWAG) to effectively distill expert-like VLM action suggestions into the RL policy. Additionally, we adopt high-throughput CLIP for dense reward shaping. We address CLIP's dynamic blindness via Conditional Contrastive Action Alignment, which conditions prompts on discretized speed/command and yields a normalized, margin-based bonus from context-specific action-anchor scoring. Found-RL provides an end-to-end pipeline for fine-tuned VLM integration and shows that a lightweight RL model can achieve near-VLM performance compared with billion-parameter VLMs while sustaining real-time inference (approx. 500 FPS). Code, data, and models will be publicly available at https://github.com/ys-qu/found-rl.

cs.AI↗

arXiv2025

Vehicle-group-based Crash Risk Prediction and Interpretation on Highways

Previous studies in predicting crash risks primarily associated the number or likelihood of crashes on a road segment with traffic parameters or geometric characteristics, usually neglecting the impact of vehicles' continuous movement and interactions with nearby vehicles. Recent technology advances, such as Connected and Automated Vehicles (CAVs) and Unmanned Aerial Vehicles (UAVs) are able to collect high-resolution trajectory data, which enables trajectory-based risk analysis. This study investigates a new vehicle group (VG) based risk analysis method and explores risk evolution mechanisms considering VG features. An impact-based vehicle grouping method is proposed to cluster vehicles into VGs by evaluating their responses to the erratic behaviors of nearby vehicles. The risk of a VG is aggregated based on the risk between each vehicle pair in the VG, measured by inverse Time-to-Collision (iTTC). A Logistic Regression and a Graph Neural Network (GNN) are then employed to predict VG risks using aggregated and disaggregated VG information. Both methods achieve excellent performance with AUC values exceeding 0.93. For the GNN model, GNNExplainer with feature perturbation is applied to identify critical individual vehicle features and their directional impact on VG risks. Overall, this research contributes a new perspective for identifying, predicting, and interpreting traffic risks.

cs.LG↗

arXiv2025

Highly reliable, ultra-wideband, isolator-free quantum-dot mode-locked frequency combs for optical interconnects beyond 3.2Tb/s

Quantum dot mode-locked laser-based optical frequency combs are emerging as a critical solution for achieving low-cost, high-efficiency, and large-capacity optical interconnects. The practical implementation of wavelength division multiplexing interconnects necessitates a temperature-stable OFC source with a minimum 100 GHz channel spacing to enable high-bandwidth modulation while mitigating the complexity of optical filtering and detection. By leveraging the advanced co-doping technique and a colliding pulse mode-locking scheme, here, we report a compact, ultra-wideband, highly reliable, isolator-free 100 GHz-spacing InAs/GaAs QD OFC source operating up to a record temperature of 140 °C. The comb source delivers a record 3 dB optical bandwidth of 14.312 nm, containing flat-top comb lines, each supporting 128 Gb/s PAM-4 modulation, which results in a total throughput of 3.328 Tb/s with an extremely low power consumption of 0.394 pJ/bit at 25°C. Performance remains stable at 85 °C, with negligible degradation of device critical metrics. Remarkably, accelerated aging tests under harsh conditions (85 °C with 8x threshold current injection) revealed a mean time to failure of approximately 207 years. The QD OFC source demonstrated in this work, for the first time, establishes a concrete link between fundamental research on comb sources and their practical deployment in next-generation, high-density optical interconnect systems.

cond-mat.mes-hall↗

arXiv2025

Impact Analysis of Inference Time Attack of Perception Sensors on Autonomous Vehicles

As a safety-critical cyber-physical system, cybersecurity and related safety issues for Autonomous Vehicles (AVs) have been important research topics for a while. Among all the modules on AVs, perception is one of the most accessible attack surfaces, as drivers and AVs have no control over the outside environment. Most current work targeting perception security for AVs focuses on perception correctness. In this work, we propose an impact analysis based on inference time attacks for autonomous vehicles. We demonstrate in a simulation system that such inference time attacks can also threaten the safety of both the ego vehicle and other traffic participants.

cs.CR↗

arXiv2025

A Dynamic Unmanned Aerial Vehicle Routing Framework for Urban Traffic Monitoring

Unmanned Aerial Vehicles (UAVs) have great potential in urban traffic monitoring due to their rapid speed, cost-effectiveness, and extensive field-of-view, while being unconstrained by traffic congestion. However, their limited flight duration presents critical challenges in sustainable recharging strategies and efficient route planning in long-term monitoring tasks. Additionally, existing approaches for long-term monitoring often neglect the evolving nature of urban traffic networks. In this study, we introduce a novel dynamic UAV routing framework for long-term, network-wide urban traffic monitoring, leveraging existing ground vehicles as mobile charging stations without disrupting their operations. To address the complexity of long-term monitoring scenarios involving multiple flights, we decompose the problem into manageable single-flight tasks, in which each flight is modeled as a Team Arc Orienteering Problem with Decreasing Profits with the objective to collectively maximize the spatiotemporal network coverage. Between flights, we adaptively update the edge weights to incorporate real-time traffic changes and revisit intervals. We validate our framework through extensive microscopic simulations in a modified Sioux Falls network under various scenarios. Comparative results demonstrate that our model outperforms three baseline approaches, especially when historical information is incomplete or absent. Moreover, we show that our monitoring framework can capture network-wide traffic trends and construct accurate Macroscopic Fundamental Diagrams (MFDs). These findings demonstrate the effectiveness of the proposed dynamic UAV routing framework, underscoring its suitability for efficient and reliable long-term traffic monitoring. Our approach's adaptability and high accuracy in capturing the MFD highlight its potential in network-wide traffic control and management applications.

math.OC↗

arXiv2024

On-Board Vision-Language Models for Personalized Autonomous Vehicle Motion Control: System Design and Real-World Validation

Personalized driving refers to an autonomous vehicle's ability to adapt its driving behavior or control strategies to match individual users' preferences and driving styles while maintaining safety and comfort standards. However, existing works either fail to capture every individual preference precisely or become computationally inefficient as the user base expands. Vision-Language Models (VLMs) offer promising solutions to this front through their natural language understanding and scene reasoning capabilities. In this work, we propose a lightweight yet effective on-board VLM framework that provides low-latency personalized driving performance while maintaining strong reasoning capabilities. Our solution incorporates a Retrieval-Augmented Generation (RAG)-based memory module that enables continuous learning of individual driving preferences through human feedback. Through comprehensive real-world vehicle deployment and experiments, our system has demonstrated the ability to provide safe, comfortable, and personalized driving experiences across various scenarios and significantly reduce takeover rates by up to 76.9%. To the best of our knowledge, this work represents the first end-to-end VLM-based motion control system in real-world autonomous vehicles.

cs.AI↗

arXiv2023

Evaluation of Infrastructure-based Warning System on Driving Behaviors-A Roundabout Study

Smart intersections have the potential to improve road safety with sensing, communication, and edge computing technologies. Perception sensors installed at a smart intersection can monitor the traffic environment in real time and send infrastructure-based warnings to nearby travelers through V2X communication. This paper investigated how infrastructure-based warnings can influence driving behaviors and improve roundabout safety through a driving-simulator study - a challenging driving scenario for human drivers. A co-simulation platform integrating Simulation of Urban Mobility (SUMO) and Webots was developed to serve as the driving simulator. A real-world roundabout in Ann Arbor, Michigan was built in the co-simulation platform as the study area, and the merging scenarios were investigated. 36 participants were recruited and asked to navigate the roundabout under three danger levels (e.g., low, medium, high) and three collision warning designs (e.g., no warning, warning issued 1 second in advance, warning issued 2 seconds in advance). Results indicated that advanced warnings can significantly enhance safety by minimizing potential risks compared to scenarios without warnings. Earlier warnings enabled smoother driver responses and reduced abrupt decelerations. In addition, a personalized intention prediction model was developed to predict drivers' stop-or-go decisions when the warning is displayed. Among all tested machine learning models, the XGBoost model achieved the highest prediction accuracy with a precision rate of 95.56% and a recall rate of 97.73%.

cs.HC↗

arXiv2023

An enhanced motion planning approach by integrating driving heterogeneity and long-term trajectory prediction for automated driving systems

Navigating automated driving systems (ADSs) through complex driving environments is difficult. Predicting the driving behavior of surrounding human-driven vehicles (HDVs) is a critical component of an ADS. This paper proposes an enhanced motion-planning approach for an ADS in a highway-merging scenario. The proposed enhanced approach utilizes the results of two aspects: the driving behavior and long-term trajectory of surrounding HDVs, which are coupled using a hierarchical model that is used for the motion planning of an ADS to improve driving safety.

cs.RO↗

arXiv2023

Improving Autonomous Vehicle Mapping and Navigation in Work Zones Using Crowdsourcing Vehicle Trajectories

Prevalent solutions for Connected and Autonomous vehicle (CAV) mapping include high definition map (HD map) or real-time Simultaneous Localization and Mapping (SLAM). Both methods only rely on vehicle itself (onboard sensors or embedded maps) and can not adapt well to temporarily changed drivable areas such as work zones. Navigating CAVs in such areas heavily relies on how the vehicle defines drivable areas based on perception information. Difficulties in improving perception accuracy and ensuring the correct interpretation of perception results are challenging to the vehicle in these situations. This paper presents a prototype that introduces crowdsourcing trajectories information into the mapping process to enhance CAV's understanding on the drivable area and traffic rules. A Gaussian Mixture Model (GMM) is applied to construct the temporarily changed drivable area and occupancy grid map (OGM) based on crowdsourcing trajectories. The proposed method is compared with SLAM without any human driving information. Our method has adapted well with the downstream path planning and vehicle control module, and the CAV did not violate driving rule, which a pure SLAM method did not achieve.

cs.RO↗

arXiv2022

IDM-Follower: A Model-Informed Deep Learning Method for Long-Sequence Car-Following Trajectory Prediction

Model-based and learning-based methods are two major types of methodologies to model car following behaviors. Model-based methods describe the car-following behaviors with explicit mathematical equations, while learning-based methods focus on getting a mapping between inputs and outputs. Both types of methods have advantages and weaknesses. Meanwhile, most car-following models are generative and only consider the inputs of the speed, position, and acceleration of the last time step. To address these issues, this study proposes a novel framework called IDM-Follower that can generate a sequence of following vehicle trajectory by a recurrent autoencoder informed by a physical car-following model, the Intelligent Driving Model (IDM).We implement a novel structure with two independent encoders and a self-attention decoder that could sequentially predict the following trajectories. A loss function considering the discrepancies between predictions and labeled data integrated with discrepancies from model-based predictions is implemented to update the neural network parameters. Numerical experiments with multiple settings on simulation and NGSIM datasets show that the IDM-Follower can improve the prediction performance compared to the model-based or learning-based methods alone. Analysis on different noise levels also shows good robustness of the model.

eess.SY↗

arXiv2022

A Cooperative Perception Environment for Traffic Operations and Control

Existing data collection methods for traffic operations and control usually rely on infrastructure-based loop detectors or probe vehicle trajectories. Connected and automated vehicles (CAVs) not only can report data about themselves but also can provide the status of all detected surrounding vehicles. Integration of perception data from multiple CAVs as well as infrastructure sensors (e.g., LiDAR) can provide richer information even under a very low penetration rate. This paper aims to develop a cooperative data collection system, which integrates Lidar point cloud data from both infrastructure and CAVs to create a cooperative perception environment for various transportation applications. The state-of-the-art 3D detection models are applied to detect vehicles in the merged point cloud. We test the proposed cooperative perception environment with the max pressure adaptive signal control model in a co-simulation platform with CARLA and SUMO. Results show that very low penetration rates of CAV plus an infrastructure sensor are sufficient to achieve comparable performance with 30% or higher penetration rates of connected vehicles (CV). We also show the equivalent CV penetration rate (E-CVPR) under different CAV penetration rates to demonstrate the data collection efficiency of the cooperative perception environment.

cs.RO↗

arXiv2021

A Learning-based Stochastic Driving Model for Autonomous Vehicle Testing

In the simulation-based testing and evaluation of autonomous vehicles (AVs), how background vehicles (BVs) drive directly influences the AV's driving behavior and further impacts the testing result. Existing simulation platforms use either pre-determined trajectories or deterministic driving models to model the BVs' behaviors. However, pre-determined BV trajectories can not react to the AV's maneuvers, and deterministic models are different from real human drivers due to the lack of stochastic components and errors. Both methods lead to unrealistic traffic scenarios. This paper presents a learning-based stochastic driving model that meets the unique needs of AV testing, i.e. interactive and human-like. The model is built based on the long-short-term-memory (LSTM) architecture. By incorporating the concept of quantile-regression to the loss function of the model, the stochastic behaviors are reproduced without any prior assumption of human drivers. The model is trained with the large-scale naturalistic driving data (NDD) from the Safety Pilot Model Deployment(SPMD) project and then compared with a stochastic intelligent driving model (IDM). Analysis of individual trajectories shows that the proposed model can reproduce more similar trajectories to human drivers than IDM. To validate the ability of the proposed model in generating a naturalistic driving environment, traffic simulation experiments are implemented. The results show that the traffic flow parameters such as speed, range, and headway distribution match closely with the NDD, which is of significant importance for AV testing and evaluation.

eess.SY↗

arXiv2021

Experimental Validation of Eco-Driving and Eco-Heating Strategies for Connected and Automated HEVs

This paper presents experimental results that validate eco-driving and eco-heating strategies developed for connected and automated vehicles (CAVs). By exploiting vehicle-to-infrastructure (V2I) communications, traffic signal timing, and queue length estimations, optimized and smoothed speed profiles for the ego-vehicle are generated to reduce energy consumption. Next, the planned eco-trajectories are incorporated into a real-time predictive optimization framework that coordinates the cabin thermal load (in cold weather) with the speed preview, i.e., eco-heating. To enable eco-heating, the engine coolant (as the only heat source for cabin heating) and the cabin air are leveraged as two thermal energy storages. Our eco-heating strategy stores thermal energy in the engine coolant and cabin air while the vehicle is driving at high speeds, and releases the stored energy slowly during the vehicle stops for cabin heating without forcing the engine to idle to provide the heating source. To test and validate these solutions, a power-split hybrid electric vehicle (HEV) has been instrumented for cabin thermal management, allowing to regulate heating, ventilation, and air conditioning (HVAC) system inputs (cabin temperature setpoint and blower flow rate) in real-time. Experiments were conducted to demonstrate the energy-saving benefits of eco-driving and eco-heating strategies over real-world city driving cycles at different cold ambient temperatures. The data confirmed average fuel savings of 14.5% and 4.7% achieved by eco-driving and eco-heating, respectively, offering a combined energy saving of more than 19% when comparing to the baseline vehicle driven by a human driver with a constant-heating strategy.

eess.SY↗