Author name cluster

Hao Ye

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

TCS Journal 2025 Journal Article

Dynamic path finding for multi-load agent pickup and delivery problem

Yifei Li
Ruixi Huang
Hao Ye
Hejiao Huang
Hongwei Du

Recently, the Multi-Agent Pickup and Delivery (MAPD) problem has attracted widespread attention from both academia and industry. In the MAPD problem, each task has its pickup and delivery locations, and the agent needs to pick this task up from the pickup location and deliver it to its delivery location. Therefore, existing works consider the MAPD problem as the core problem in industrial scenarios, e. g. , logistics warehouse. Note that the agents considered in the MAPD problem are single-load agents that complete tasks one by one. However, many commercial companies have deployed agents with multi-load instead of single-load agents to improve efficiency and reduce costs. The agents with multi-load can complete multiple tasks at once, so existing solutions cannot work well with the MAPD problem for multi-agents. To solve this issue, we investigate a novel problem in this paper, namely the Multi-Load Agent Pickup and Delivery (MLAPD) problem, where the agents with multi-load not only need to complete assigned real-time tasks but also need to avoid conflicts with each other and the goal is to minimize the total cost in the warehouse. To address this novel problem, we develop a task assignment to complete the assignments between multi-load agents and online tasks in real-time and a dynamic path finding problem that enables multi-load agents to move along conflict-free paths. Finally, extensive experiments in two different warehouses examine the effectiveness of our solutions.

Details DOI

TCS Journal 2025 Journal Article

Task group allocation for multi-load agent pickup and delivery problem

Yifei Li
Hao Ye
Hejiao Huang

This paper focuses on the Multi-Load Agent Pickup and Delivery (MLAPD) problem, in which the multi-load agent set needs to complete a set of dynamically arriving tasks while minimizing the service time. Compared with the general Multi-Agent Pickup and Delivery problem, in which each agent only completes one task once time, multi-load agents in the MLAPD problem can carry multiple tasks simultaneously, which greatly improves work efficiency in practice. However, the different completion times of multiple tasks will affect each other, which makes it difficult to find reasonable schedules for multi-load agents. Existing works ignore such influence among different tasks. To address this issue, in this paper, we propose a Task Group Allocation (TGA) algorithm to assign suitable tasks to the multi-load agents while considering the influence between these tasks. Specifically, we first quantify the carpooling scores among multiple tasks by using the Get Carpooling Scores (GCS) algorithm. Then, we present a K-Capacity Hierarchical Clustering (KCHC) algorithm to divide the set of tasks into groups with guarantee, in which tasks in the same group have little influence on each other. Finally, we use the TGA algorithm to allocate task groups to suitable agents to minimize the service time. Experimental results show that the TGA algorithm outperforms the state-of-the-art task allocation algorithms in terms of service time and makespan.

Details DOI

EAAI Journal 2023 Journal Article

CVT on-line error measurement hybrid-driven by domain knowledge and Stacking Model

Jingping Wang
Ying Shi
Rui Zhang
Zhonghua Wu
Hao Ye
Shenwei Li

The performance of Capacitive Voltage Transformer (CVT) degrades over time, making measurement error monitoring a research hotspot in the field of smart grid. At present, these are several challenges such as complex data features, a lack of criteria for selecting optimal measurement models, and low precision. CVT measurement errors can be classified into ideal error and additional one. The former is typically evaluated via mutual information and redundancy within the topology-level transformer group. Considering that a single model cannot process the time series, strong randomness and nonlinearity of the additional error, the Stacking model is selected. Based on the principle of heterogeneity and high-quality, correlation coefficient and feature contribution degree, Random Forest, eXtreme Gradient Boosting, Ridge Regression, K Nearest Neighbors, Support Vector Regression, and Long Short-Term Memory are chosen as base learners through correlation and feature contribution analysis; while extra-trees with strong generalization and robustness is chosen as the meta learner. To improve the measurement precision, the attention-like mechanism is used to scale time and accuracy weights. Finally, according to the power domain knowledge, a linear superposition model is developed to fuse the ideal and additional errors, and thus realize online error measurement for CVTs. The experimental results indicate that the improved Stacking model outperforms mainstream measurement models by an average reduction of 59. 47%, and 52. 58% in the root mean squared error and the mean absolute error with the best R 2 closest to 1. It not only effectively improves the accuracy but also meets speed requirement for online error measurement.

Details DOI

ICLR Conference 2023 Conference Paper

WiNeRT: Towards Neural Ray Tracing for Wireless Channel Modelling and Differentiable Simulations

Tribhuvanesh Orekondy
Kumar Pratik
Shreya Kadambi
Hao Ye
Joseph Soriaga
Arash Behboodi

In this paper, we work towards a neural surrogate to model wireless electro-magnetic propagation effects in indoor environments. Such neural surrogates provide a fast, differentiable, and continuous representation of the environment and enables end-to-end optimization for downstream tasks (e.g., network planning). Specifically, the goal of the paper is to render the wireless signal (e.g., time-of-flights, power of each path) in an environment as a function of the sensor's spatial configuration (e.g., placement of transmit and receive antennas). NeRF-based approaches have shown promising results in the visual setting (RGB image signal, with a camera sensor), where the key idea is to algorithmically evaluate the 'global' signal (e.g., using volumetric rendering) by breaking it down in a sequence of 'local' evaluations (e.g., using co-ordinate neural networks). In a similar spirit, we model the time-angle channel impulse response (the global wireless signal) as a superposition of multiple paths. The wireless characteristics (e.g., power) of each path is a result of multiple evaluations of a neural network that learns implicit ray-surface interaction properties. We evaluate our approach in multiple indoor scenarios and demonstrate that our model achieves strong performance (e.g., $<$0.33ns error in time-of-flight predictions). Furthermore, we demonstrate that our neural surrogate whitens the `black-box' wireless simulators, and thus enables inverse rendering applications (e.g., user localization).

Details

IJCAI Conference 2017 Conference Paper

Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks

Jun Xiao
Hao Ye
Xiangnan He
Hanwang Zhang
Fei Wu
Tat-Seng Chua

Factorization Machines (FMs) are a supervised learning approach that enhances the linear regression model by incorporating the second-order feature interactions. Despite effectiveness, FM can be hindered by its modelling of all feature interactions with the same weight, as not all feature interactions are equally useful and predictive. For example, the interactions with useless features may even introduce noises and adversely degrade the performance. In this work, we improve FM by discriminating the importance of different feature interactions. We propose a novel model named Attentional Factorization Machine (AFM), which learns the importance of each feature interaction from data via a neural attention network. Extensive experiments on two real-world datasets demonstrate the effectiveness of AFM. Empirically, it is shown on regression task AFM betters FM with a 8. 6% relative improvement, and consistently outperforms the state-of-the-art deep learning methods Wide&Deep [Cheng et al. , 2016] and DeepCross [Shan et al. , 2016] with a much simpler structure and fewer model parameters. Our implementation of AFM is publicly available at: https: //github. com/hexiangnan/attentional_factorization_machine

PDF Details