Yuexing Hao

Dr. Yuexing Hao

orcid

Research Focus & Metrics

Representative Publications

View All Publications
16 May 2021 in Sensors
Verified
Journal Article
Open access
PDF file
HDHuaBin Diao
HuaBin Diao
YHYuexing Hao
Yuexing Hao
SXShaoyun Xu
Shaoyun Xu
GLGongyan Li
Gongyan Li
Convolutional neural networks (CNNs) have achieved significant breakthroughs in various domains, such as natural language processing (NLP), and computer vision. However, performance improvement is often accompanied by large model size and computation costs, which make it not suitable for resource-constrained devices. Consequently, there is an urgent need to compress CNNs, so as to reduce model size and computation costs. This paper proposes a layer-wise differentiable compression (LWDC) algorithm for compressing CNNs structurally. A differentiable selection operator OS is embedded in the model to compress and train the model simultaneously by gradient descent in one go. Instead of pruning parameters from redundant operators by contrast to most of the existing methods, our method replaces the original bulky operators with more lightweight ones directly, which only needs to specify the set of lightweight operators and the regularization factor in advance, rather than the compression rate for each layer. The compressed model produced by our method is generic and does not need any special hardware/software support. Experimental results on CIFAR-10, CIFAR-100 and ImageNet have demonstrated the effectiveness of our method. LWDC obtains more significant compression than state-of-the-art methods in most cases, while having lower performance degradation. The impact of lightweight operators and regularization factor on the compression rate and accuracy also is evaluated.

17 May 2024
Verified
Conference Paper
Open access
YWYang Wang
Yang Wang
YHYuexing Hao
Yuexing Hao
YQYanbo Qu
Yanbo Qu
YMYingxue Ma
Yingxue Ma
A collaborative problem of multi AGVs scheduling and path planning for dynamic arrival of task is extracted from an automated warehouse. In this problem, it is necessary to consider the balanced allocation of task to AGVs and simultaneously plan conflict-free paths for AGVs. Firstly, a mathematical model was established with the goal of minimizing the total driving time; secondly, a two-stage solution method was designed. At first stage, we design AGV balancing scheduling algorithm to solve the scheduling problem between AGVs and tasks, with the goal for balancing the use of AGVs; at second stage, we focus on planning conflict-free paths, design a multi AGV path collaborative planning algorithm with three traffic rules for congestion situations and a hierarchical reservation table; finally, the effectiveness of the method was verified at different scale experiments.

10 April 2023 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
MLMeiling Lin
Meiling Lin
GLGongyan Li
Gongyan Li
YHYuexing Hao
Yuexing Hao
SXShaoyun Xu
Shaoyun Xu

23 October 2026 in Robotics
Verified
Journal Article
Open access
PDF file
YHYuexing Hao
Yuexing Hao
SXShaoyun Xu
Shaoyun Xu
GLGuotao Li
Guotao Li
Multi-Agent Reinforcement Learning (MARL) provides an effective paradigm for distributed Multi-Agent Path Finding (MAPF) under partial observability. Due to frequent local interactions among agents, action decisions based on limited local information can induce potential collision risks and may further lead to action conflicts, posing challenges to efficient multi-agent coordination. In this paper, we propose CPH, a value-based MARL framework that proactively mitigates collision risks during path decision-making and resolves unavoidable action conflicts before execution. Specifically, we introduce a collision-risk-driven communication mechanism that selects partners according to potential collision relationships and integrates collision-aware spatial contexts with agent-centric observations via cross-attention. Moreover, we propose a potential-inspired aggregation reward shaping method, which encourages agents to disperse from collision-prone aggregation states. Additionally, we present a conflict-aware hybrid post-processing strategy that adaptively resolves different conflict scenarios through local action adjustment. Experimental results show that CPH outperforms the compared distributed MARL-based MAPF methods, while ablation studies confirm the effectiveness of all three components. These results indicate that combining proactive collision-risk mitigation with adaptive conflict resolution before execution improves path reachability and planning efficiency in distributed MAPF.

22 November 2024
Verified
Conference Paper
Open access
YWYang Wang
Yang Wang
SXShaoyun Xu
Shaoyun Xu
YMYingxue Ma
Yingxue Ma
YHYuexing Hao
Yuexing Hao
YQYanbo Qu
Yanbo Qu
SZShu Zhang
Shu Zhang