Searcharxiv⌕ Search

arXiv subjects

Fuxi Wen

Publications and source records attributed to Fuxi Wen.

17 recordsLinked to original sources
arXiv2026

DriveVer: Lightweight Trajectory Evaluator as Test-Time Verifier for Autonomous Driving

End-to-end autonomous driving models often encounter performance bottlenecks, as training-time scaling leads to high computational costs and diminishing marginal returns. Existing planners typically adopt a one-shot generation paradigm, lacking secondary validation and active correction mechanisms to detect and revise suboptimal or unsafe trajectories during inference. To address this issue, we propose DriveVer, a lightweight, plug-and-play Test-Time Verifier that leverages the test-time scaling paradigm to enable autonomous driving systems to validate and refine trajectories without costly and heavy training. We construct a dedicated trajectory dataset based on the NAVSIM benchmark through condition-driven clustering and balanced sampling according to ego-vehicle states and navigation commands. Employing a dual-head architecture, DriveVer efficiently fuses candidate trajectories with multi-view visual representations and ego-vehicle kinematic features to simultaneously predict a safety confidence score and an absolute geometric refinement vector. Extensive experiments on the NAVSIM benchmark show that DriveVer significantly improves the performance of base planning models. Notably, as an extremely compact model with only 34M parameters, DriveVer introduces minimal computational overhead, achieving competitive results while maintaining real-time inference efficiency.

cs.CV↗
arXiv2026

LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving

While Vision-Language-Action (VLA) models have revolutionized autonomous driving by unifying perception and planning, their reliance on explicit textual Chain-of-Thought (CoT) leads to semantic-perceptual decoupling and perceptual-symbolic conflicts. Recent shifts toward latent reasoning attempt to bypass these bottlenecks by thinking in continuous hidden space. However, without explicit intermediate constraints, standard latent CoT often operates as a physics-agnostic representation. To address this, we propose the Latent Spatio-Temporal VLA (LaST-VLA), a framework shifting the reasoning paradigm from discrete symbolic processing into a physically grounded Latent Spatio-Temporal CoT. By implementing a dual-feature alignment mechanism, we distill geometric constraints from 3D foundation models and dynamic foresight from world models directly into the latent space. Coupled with a progressive SFT training strategy that transitions from feature alignment to trajectory generation, and refined via Reinforcement Learning with Group Relative Policy Optimization (GRPO) to ensure safety and rule compliance. \method~setting a new record on NAVSIM v1 (91.3 PDMS) and NAVSIM v2 (87.1 EPDMS), while excelling in spatial-temporal reasoning on SURDS and NuDynamics benchmarks.

cs.CV↗
arXiv2026

Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from Failures

Vision-Language-Action (VLA) models for autonomous driving often hit a performance plateau during Reinforcement Learning (RL) optimization. This stagnation arises from exploration capabilities constrained by previous Supervised Fine-Tuning (SFT), leading to persistent failures in long-tail scenarios. In these critical situations, all explored actions yield a zero-value driving score. This information-sparse reward signals a failure, yet fails to identify its root cause -- whether it is due to incorrect planning, flawed reasoning, or poor trajectory execution. To address this limitation, we propose VLA with Explicit Learning from Failures (ELF-VLA), a framework that augments RL with structured diagnostic feedback. Instead of relying on a vague scalar reward, our method produces detailed, interpretable reports that identify the specific failure mode. The VLA policy then leverages this explicit feedback to generate a Feedback-Guided Refinement. By injecting these corrected, high-reward samples back into the RL training batch, our approach provides a targeted gradient, which enables the policy to solve critical scenarios that unguided exploration cannot. Extensive experiments demonstrate that our method unlocks the latent capabilities of VLA models, achieving state-of-the-art (SOTA) performance on the public NAVSIM benchmark for overall PDMS, EPDMS score and high-level planning accuracy.

cs.CV↗
arXiv2026

An Empirical Analysis of Cooperative Perception for Occlusion Risk Mitigation

Occlusions present a significant challenge for connected and automated vehicles, as they can obscure critical road users from perception systems. Traditional risk metrics often fail to capture the cumulative nature of these threats over time adequately. In this paper, we propose a novel and universal risk assessment metric, the Risk of Tracking Loss (RTL), which aggregates instantaneous risk intensity throughout occluded periods. This provides a holistic risk profile that encompasses both high-intensity, short-term threats and prolonged exposure. Utilizing diverse and high-fidelity real-world datasets, a large-scale statistical analysis is conducted to characterize occlusion risk and validate the effectiveness of the proposed metric. The metric is applied to evaluate different vehicle-to-everything (V2X) deployment strategies. Our study shows that full V2X penetration theoretically eliminates this risk, the reduction is highly nonlinear; a substantial statistical benefit requires a high penetration threshold of 75-90%. To overcome this limitation, we propose a novel asymmetric communication framework that allows even non-connected vehicles to receive warnings. Experimental results demonstrate that this paradigm achieves better risk mitigation performance. We found that our approach at 25% penetration outperforms the traditional symmetric model at 75%, and benefits saturate at only 50% penetration. This work provides a crucial risk assessment metric and a cost-effective, strategic roadmap for accelerating the safety benefits of V2X deployment.

cs.RO↗
arXiv2025

TruckV2X: A Truck-Centered Perception Dataset

Autonomous trucking offers significant benefits, such as improved safety and reduced costs, but faces unique perception challenges due to trucks' large size and dynamic trailer movements. These challenges include extensive blind spots and occlusions that hinder the truck's perception and the capabilities of other road users. To address these limitations, cooperative perception emerges as a promising solution. However, existing datasets predominantly feature light vehicle interactions or lack multi-agent configurations for heavy-duty vehicle scenarios. To bridge this gap, we introduce TruckV2X, the first large-scale truck-centered cooperative perception dataset featuring multi-modal sensing (LiDAR and cameras) and multi-agent cooperation (tractors, trailers, CAVs, and RSUs). We further investigate how trucks influence collaborative perception needs, establishing performance benchmarks while suggesting research priorities for heavy vehicle perception. The dataset provides a foundation for developing cooperative perception systems with enhanced occlusion handling capabilities, and accelerates the deployment of multi-agent autonomous trucking systems. The TruckV2X dataset is available at https://huggingface.co/datasets/XieTenghu1/TruckV2X.

cs.RO↗
arXiv2025

Wireless Communication as an Information Sensor for Multi-agent Cooperative Perception: A Survey

Cooperative perception extends the perception capabilities of autonomous vehicles by enabling multi-agent information sharing via Vehicle-to-Everything (V2X) communication. Unlike traditional onboard sensors, V2X acts as a dynamic "information sensor" characterized by limited communication, heterogeneity, mobility, and scalability. This survey provides a comprehensive review of recent advancements from the perspective of information-centric cooperative perception, focusing on three key dimensions: information representation, information fusion, and large-scale deployment. We categorize information representation into data-level, feature-level, and object-level schemes, and highlight emerging methods for reducing data volume and compressing messages under communication constraints. In information fusion, we explore techniques under both ideal and non-ideal conditions, including those addressing heterogeneity, localization errors, latency, and packet loss. Finally, we summarize system-level approaches to support scalability in dense traffic scenarios. Compared with existing surveys, this paper introduces a new perspective by treating V2X communication as an information sensor and emphasizing the challenges of deploying cooperative perception in real-world intelligent transportation systems.

cs.OH↗
arXiv2025

TraF-Align: Trajectory-aware Feature Alignment for Asynchronous Multi-agent Perception

Cooperative perception presents significant potential for enhancing the sensing capabilities of individual vehicles, however, inter-agent latency remains a critical challenge. Latencies cause misalignments in both spatial and semantic features, complicating the fusion of real-time observations from the ego vehicle with delayed data from others. To address these issues, we propose TraF-Align, a novel framework that learns the flow path of features by predicting the feature-level trajectory of objects from past observations up to the ego vehicle's current time. By generating temporally ordered sampling points along these paths, TraF-Align directs attention from the current-time query to relevant historical features along each trajectory, supporting the reconstruction of current-time features and promoting semantic interaction across multiple frames. This approach corrects spatial misalignment and ensures semantic consistency across agents, effectively compensating for motion and achieving coherent feature fusion. Experiments on two real-world datasets, V2V4Real and DAIR-V2X-Seq, show that TraF-Align sets a new benchmark for asynchronous cooperative perception.

cs.CV↗
arXiv2024

A Spatial Calibration Method for Robust Cooperative Perception

Cooperative perception is a promising technique for intelligent and connected vehicles through vehicle-to-everything (V2X) cooperation, provided that accurate pose information and relative pose transforms are available. Nevertheless, obtaining precise positioning information often entails high costs associated with navigation systems. {Hence, it is required to calibrate relative pose information for multi-agent cooperative perception.} This paper proposes a simple but effective object association approach named context-based matching (CBM), which identifies inter-agent object correspondences using intra-agent geometrical context. In detail, this method constructs contexts using the relative position of the detected bounding boxes, followed by local context matching and global consensus maximization. The optimal relative pose transform is estimated based on the matched correspondences, followed by cooperative perception fusion. Extensive experiments are conducted on both the simulated and real-world datasets. Even with larger inter-agent localization errors, high object association precision and decimeter-level relative pose calibration accuracy are achieved among the cooperating agents.

cs.RO↗
arXiv2023

Integrated Sensing and Channel Estimation by Exploiting Dual Timescales for Delay-Doppler Alignment Modulation

For integrated sensing and communication (ISAC) systems, the channel information essential for communication and sensing tasks fluctuates across different timescales. Specifically, wireless sensing primarily focuses on acquiring path state information (PSI) (e.g., delay, angle, and Doppler) of individual multi-path components to sense the environment, which usually evolves much more slowly than the composite channel state information (CSI) required for communications. Typically, the CSI is approximately unchanged during the channel coherence time, which characterizes the statistical properties of wireless communication channels. However, this concept is less appropriate for describing that for wireless sensing. To this end, in this paper, we introduce a new timescale to study the variation of the PSI from a channel geometric perspective, termed path invariant time, during which the PSI largely remains constant. Our analysis indicates that the path invariant time considerably exceeds the channel coherence time. Thus, capitalizing on these dual timescales of the wireless channel, in this paper, we propose a novel ISAC framework exploiting the recently proposed delay-Doppler alignment modulation (DDAM) technique. Different from most existing studies on DDAM that assume the availability of perfect PSI, in this work, we propose a novel algorithm, termed as adaptive simultaneously orthogonal matching pursuit with support refinement (ASOMP-SR), for joint environment sensing and PSI estimation. We also analyze the performance of DDAM with imperfectly sensed PSI.Simulation results unveil that the proposed DDAM-based ISAC can achieve superior spectral efficiency and a reduced peak-to-average power ratio (PAPR) compared to standard orthogonal frequency division multiplexing (OFDM).

cs.IT↗
arXiv2023

A Cooperative Perception System Robust to Localization Errors

Cooperative perception is challenging for safety-critical autonomous driving applications.The errors in the shared position and pose cause an inaccurate relative transform estimation and disrupt the robust mapping of the Ego vehicle. We propose a distributed object-level cooperative perception system called OptiMatch, in which the detected 3D bounding boxes and local state information are shared between the connected vehicles. To correct the noisy relative transform, the local measurements of both connected vehicles (bounding boxes) are utilized, and an optimal transport theory-based algorithm is developed to filter out those objects jointly detected by the vehicles along with their correspondence, constructing an associated co-visible set. A correction transform is estimated from the matched object pairs and further applied to the noisy relative transform, followed by global fusion and dynamic mapping. Experiment results show that robust performance is achieved for different levels of location and heading errors, and the proposed framework outperforms the state-of-the-art benchmark fusion schemes, including early, late, and intermediate fusion, on average precision by a large margin when location and/or heading errors occur.

cs.MA↗
arXiv2022

An Iterative 5G Positioning and Synchronization Algorithm in NLOS Environments with Multi-Bounce Paths

5G positioning is a very promising area that presents many opportunities and challenges. Many existing techniques rely on multiple anchor nodes and line-of-sight (LOS) paths, or single reference node and single-bounce non-LOS (NLOS) paths. However, in dense multipath environments, identifying the LOS or single-bounce assumptions is challenging. The multi-bounce paths will make the positioning accuracy deteriorate significantly. We propose a robust 5G positioning algorithm in NLOS multipath environments. The corresponding positioning problem is formulated as an iterative and weighted least squares problem, and different weights are utilized to mitigate the effects of multi-bounce paths. Numerical simulations are carried out to evaluate the performance of the proposed algorithm. Compared with the benchmark positioning algorithms only using the single-bounce paths, similar positioning accuracy is achieved for the proposed algorithm.

eess.SP↗
arXiv2021

Beamspace Multidimensional ESPRIT Approaches for Simultaneous Localization and Communications

Modern wireless communication systems operating at high carrier frequencies are characterized by a high dimensionality of the underlying parameter space (including channel gains, angles, delays, and possibly Doppler shifts). Estimating these parameters is valuable for communication purposes, but also for localization and sensing, making channel estimation a critical component in any joint communication and localization or sensing application. The high dimensionality make it difficult to use search-based methods such as maximum likelihood. Search-free methods such as ESPRIT provide an attractive alternative, but require a complex decomposition step in both the tensor and matrix version of ESPRIT. To mitigate this, we propose, develop, and analyze a reduced complexity beamspace ESPRIT method. Complexity is reduced both by beampace processing as well as low-complex implementation of the singular value decomposition. A novel perturbation analysis provides important insights for both channel estimation and localization performance. The proposed method is compared to the tensor ESPRIT method, in terms of channel estimation, communication, localization, and sensing performance, further validating the perturbation analysis.

eess.SP↗
arXiv2020

Exploiting Diffuse Multipath in 5G SLAM

5G millimeter wave (mmWave) signals can be used to jointly localize the receiver and map the propagation environment in vehicular networks, which is a typical simultaneous localization and mapping (SLAM) problem. Mapping the environment is challenging, due to measurements comprising both specular and diffuse multipath components, and diffuse multipath is usually considered as a perturbation. We here propose a novel method to utilize all available multipath signals from each landmark for mapping and incorporate this into a Poisson multi-Bernoulli mixture for the 5G SLAM problem. Simulation results demonstrate the efficacy of the proposed scheme.

eess.SP↗
arXiv2020

5G Positioning and Mapping with Diffuse Multipath

5G mmWave communication is useful for positioning due to the geometric connection between the propagation channel and the propagation environment. Channel estimation methods can exploit the resulting sparsity to estimate parameters(delay and angles) of each propagation path, which in turn can be exploited for positioning and mapping. When paths exhibit significant spread in either angle or delay, these methods breakdown or lead to significant biases. We present a novel tensor-based method for channel estimation that allows estimation of mmWave channel parameters in a non-parametric form. The method is able to accurately estimate the channel, even in the absence of a specular component. This in turn enables positioning and mapping using only diffuse multipath. Simulation results are provided to demonstrate the efficacy of the proposed approach.

cs.IT↗
arXiv2019

5G mmWave Downlink Vehicular Positioning

5G new radio (NR) provides new opportunities for accurate positioning from a single reference station: large bandwidth combined with multiple antennas, at both the base station and user sides, allows for unparalleled angle and delay resolution. Nevertheless, positioning quality is affected by multipath and clock biases. We study, in terms of performance bounds and algorithms, the ability to localize a vehicle in the presence of multipath and unknown user clock bias. We find that when a sufficient number of paths is present, a vehicle can still be localized thanks to redundancy in the geometric constraints. Moreover, the 5G NR signals enable a vehicle to build up a map of the environment.

eess.SP↗
arXiv2011

System Identification Using Reweighted Zero Attracting Least Absolute Deviation Algorithm

In this paper, the l1 norm penalty on the filter coefficients is incorporated in the least mean absolute deviation (LAD) algorithm to improve the performance of the LAD algorithm. The performance of LAD, zero-attracting LAD (ZA-LAD) and reweighted zero-attracting LAD (RZA-LAD) are evaluated for linear time varying system identification under the non-Gaussian (alpha-stable) noise environments. Effectiveness of the ZA-LAD type algorithms is demonstrated through computer simulations.

eess.SY↗