arXiv subjects

Zhiying Song

Publications and source records attributed to Zhiying Song.

9 recordsLinked to original sources

arXiv2026

V2X-Radar: A Multi-modal Dataset with 4D Radar for Cooperative Perception

Modern autonomous vehicle perception systems often struggle with occlusions and limited perception range. Previous studies have demonstrated the effectiveness of cooperative perception in extending the perception range and overcoming occlusions, thereby enhancing the safety of autonomous driving. In recent years, a series of cooperative perception datasets have emerged; however, these datasets primarily focus on cameras and LiDAR, neglecting 4D Radar, a sensor used in single-vehicle autonomous driving to provide robust perception in adverse weather conditions. In this paper, to bridge the gap created by the absence of 4D Radar datasets in cooperative perception, we present V2X-Radar, the first large-scale, real-world multi-modal dataset featuring 4D Radar. V2X-Radar dataset is collected using a connected vehicle platform and an intelligent roadside unit equipped with 4D Radar, LiDAR, and multi-view cameras. The collected data encompasses sunny and rainy weather conditions, spanning daytime, dusk, and nighttime, as well as various typical challenging scenarios. The dataset consists of 20K LiDAR frames, 40K camera images, and 20K 4D Radar data, including 350K annotated boxes across five categories. To support various research domains, we have established V2X-Radar-C for cooperative perception, V2X-Radar-I for roadside perception, and V2X-Radar-V for single-vehicle perception. Furthermore, we provide comprehensive benchmarks across these three sub-datasets. We will release all datasets and benchmark codebase at https://huggingface.co/datasets/yanglei18/V2X-Radar and https://github.com/yanglei18/V2X-Radar.

cs.CV↗

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

Three-dimensional Simulation of Surface Charging in Meteorite Craters on Rotating Asteroids

Meteorite craters on the asteroid surface obstruct the horizontal flow of solar wind, forming a plasma wake that modulates the particle fluxes and the electrostatic environment far downstream. In this study, surface charging properties of asteroids with nontrivial terrain are simulated based on neural network and the finite element method. Key factors such as the location, size and depth-to-width ratio of craters are all considered. Under normal conditions, as the latitude of the crater increases, the potential variation at its floor during a rotation gradually becomes smoother, finally stabilizing around -3V with minor fluctuations as the crater approaches the poles. For craters with a depth-to-width ratio greater than 0.5, because of the diverging motions of electrons and the less deflected trajectories of ions, completely different charging results are observed under parallel and perpendicular solar wind incidence, the potential around the crater floor decreases and increases with the rising depth-to-width ratio, respectively. While the surface potential appears indifferent to changes in crater size, only during solar storms, the floor of large-scale craters, such as those with a diameter of 800m, perform a 9.13V decrease in potential compared to small craters of 50m. Both studies of localized plasma flow field and the surface charging phenomenon of asteroids have substantial influence on the future safe landing and exploration missions.

astro-ph.EP↗

arXiv2024

Dynamic Three-dimensional Simulation of Surface Charging on Rotating Asteroids

Surface charging phenomenon of asteroids, mainly resulting from solar wind plasma and solar radiation, has been studied extensively. However, the influence of asteroid's rotation on surface charging has yet to be fully understood. Here neural network is established to replace numerical integration, improving the efficiency of dynamic three-dimensional simulation. We implement simulation of rotating asteroids and surrounding plasma environment under different conditions, including quiet solar wind and solar storms, various minerals on asteroid's surface also be considered. For asteroids with rotation periods comparable to orbital period, effect of orbital motion and obliquity also be studied. Results show that under typical solar wind, the maximum and minimum potential of asteroids will gradually decrease with their increasing periods, especially when solar wind is obliquely incident. For asteroid has period longer than one week, this decreasing trend will become extremely slow. During solar storm passing, solar wind plasma changes sharply, the susceptibility of asteroid's surface potential to rotation is greatly pronounced. Minerals on surface also count, plagioclase is the most sensitive mineral among those we explored, while ilmenite seems indifferent to changes in rotation periods. Understanding the surface charging of asteroid under various rotation periods or angles, is crucial for further research into solar wind plasma and asteroid's surface dust motion, providing a reference for safe landing exploration of asteroids.

astro-ph.EP↗

arXiv2024

The Effect of Work Function on Dust Charging and Dynamics on the Airless Celestial Body

The charged dust on the surface of airless celestial bodies, such as the moon and asteroids, is a threat to space missions. Further research on the charged dust will contribute to the success of space missions. In this paper, we study the charging and dynamics of dust particles with different work functions. By integrating the photoelectron energy distribution function over four illuminated areas with different work functions, we evaluated the photoelectron concentration in these four areas. At each area, using the photoelectron concentration, we solve the dust charging and dynamics equations with two different gravitational acceleration values. The results reveal that the dust with a larger work function can reach higher equilibrium states. These states include dominant photoelectron-related charging currents, charge numbers, and levitation heights. We suggest that the equilibrium states all hold a clear inverse relationship with the work functions of dust particles when the solar zenith angle varies from 0 to 90 degrees, displaying consistent trends under different gravitational accelerations. We also find that dust particles seem unable to stably levitate at a critical solar zenith angle. The value of this critical SZA follows the same rule subjected to the work function.

astro-ph.EP↗

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

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↗