arXiv subjects

Zechuan Gong

Publications and source records attributed to Zechuan Gong.

3 recordsLinked to original sources

arXiv2026

Efficient Local-to-Global Collaborative Perception via Joint Communication and Computation Optimization

Autonomous driving relies on accurate perception to ensure safe driving. Collaborative perception improves accuracy by mitigating the sensing limitations of individual vehicles, such as limited perception range and occlusion-induced blind spots. However, collaborative perception often suffers from high communication overhead due to redundant data transmission, as well as increasing computation latency caused by excessive load with growing connected and autonomous vehicles (CAVs) participation. To address these challenges, we propose a novel local-to-global collaborative perception framework (LGCP) to achieve collaboration in a communication- and computation-efficient manner. The road of interest is partitioned into non-overlapping areas, each of which is assigned a dedicated CAV group to perform localized perception. A designated leader in each group collects and fuses perception data from its members, and uploads the perception result to the roadside unit (RSU), establishing a link between local perception and global awareness. The RSU aggregates perception results from all groups and broadcasts a global view to all CAVs. LGCP employs a centralized scheduling strategy via the RSU, which assigns CAV groups to each area, schedules their transmissions, aggregates area-level local perception results, and propagates the global view to all CAVs. Experimental results demonstrate that the proposed LGCP framework achieves an average 44 times reduction in the amount of data transmission, while maintaining or even improving the overall collaborative performance.

cs.DC↗

arXiv2026

SGCP: A Self-Organized Game-Theoretic Framework For Collaborative Perception

Collaborative perception holds great promise for improving safety in autonomous driving, particularly in dense traffic where vehicles can share sensory information to overcome individual blind spots and extend awareness. However, deploying such collaboration at scale remains difficult when communication bandwidth is limited and no roadside infrastructure is available. To overcome these limitations, we introduce a fully decentralized framework that enables vehicles to self organize into cooperative groups using only vehicle to vehicle communication. The approach decomposes the problem into two sequential game theoretic stages. In the first stage, vehicles form stable clusters by evaluating mutual sensing complementarity and motion coherence, and each cluster elects a coordinator. In the second stage, the coordinator guides its members to selectively transmit point cloud segments from perceptually salient regions through a non cooperative potential game, enabling efficient local fusion. Global scene understanding is then achieved by exchanging compact detection messages across clusters rather than raw sensor data. We design distributed algorithms for both stages that guarantee monotonic improvement of the system wide potential function. Comprehensive experiments on the CARLA-OpenCDA-NS3 co-simulation platform show that our method reduces communication overhead while delivering higher perception accuracy and wider effective coverage compared to existing baselines.

cs.DC↗

arXiv2025

SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptation

Graphs are able to model interconnected entities in many online services, supporting a wide range of applications on the Web. This raises an important question: How can we train a graph foundational model on multiple source domains and adapt to an unseen target domain? A major obstacle is that graphs from different domains often exhibit divergent characteristics. Some studies leverage large language models to align multiple domains based on textual descriptions associated with the graphs, limiting their applicability to text-attributed graphs. For text-free graphs, a few recent works attempt to align different feature distributions across domains, while generally neglecting structural differences. In this work, we propose a novel Structure Alignment framework for text-free Multi-domain Graph Pre-Training and cross-domain adaptation (SAMGPT). It is designed to learn multi-domain knowledge from graphs originating in multiple source domains, which can then be adapted to address applications in an unseen target domain. Specifically, we introduce a set of structure tokens to harmonize structure-based aggregation across source domains during the pre-training phase. Next, for cross-domain adaptation, we design dual prompts, namely, holistic prompts and specific prompts, which adapt unified multi-domain structural knowledge and fine-grained, domain-specific information, respectively, to a target domain. Finally, we conduct comprehensive experiments on seven public datasets to evaluate and analyze the effectiveness of SAMGPT.

cs.CL↗