XHXingshuo Hai

Xingshuo Hai

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xingshuo Hai has a total of 37 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Collaborative Multiobjective Decisions for Cyber-Physical Production Systems Under Time-Varying Demands

    by Meng Liu, Qiang Feng, Xingshuo Hai, Qianming Zhang, Changyun Wen, Andy W. H. Khong

    The advent of cyber-physical production systems (CPPSs) has greatly improved production responsiveness. However, effective control and decision-making in CPPSs remain challenging due to the dynamic nature of both internal operations and external environments. We present a multiobjective optimization approach for managing operation, maintenance, and support decisions in CPPSs under time-varying demands. Specifically, a decision-making framework is developed to enable collaborative control, incorporating reliability-based risk assessment and multiobjective optimization techniques. To facilitate continuous decision-making in response to uncertainties, a biobjective optimization model is formulated using a receding horizon control architecture, addressing conflicting objectives simultaneously. An enhanced multiobjective pigeon-inspired optimization algorithm is proposed to generate Pareto-optimal solutions by co-minimizing the production risks and costs. Experimental validations are carried out through both numerical simulations and real-world experiments on a subsea production system in the South China Sea, involving two support sites, six production sites, thirty-six machines, and 288 components.


  • Resilient Real-Time Decision-Making for Autonomous Mobile Robot Path Planning in Complex Dynamic Environments

    by Xingshuo Hai, Ziming Zhu, Yuan Liu, Andy W. H. Khong, Changyun Wen

    We propose a hierarchical dual-layer decision-making framework to address challenges associated with autonomous mobile robot (AMR) path planning in complex and dynamic campus environments. The upper-layer global planning is formulated as a multiobjective optimization model, where a multiobjective sheep flock migrate optimization algorithm (MOSFMO) is proposed to generate Pareto front solutions by optimizing path length and path safety jointly. In the lower layer, the autonomy of the AMR is enhanced through deep reinforcement learning (DRL) training with a composite reward scheme designed to enable resilient real-time decisions for avoiding unexpected pedestrians while achieving global objectives. Effective coordination is achieved through the availability of multiple candidate paths and a time-oriented deadlock detection mechanism, enabling uninterrupted task execution despite encountered blockage challenges. The proposed methods are validated through numerical simulations and real-world experiments, achieving on-time arrival rates of up to 99% in dynamic environments.


  • Top Cited Papers

    Capability-Oriented Decision-Making in Multi-UAV Deployment and Task Allocation: A Hierarchical Game-Based Framework

    by Xingshuo Hai, Qiang Feng, Weike Chen, Changyun Wen, Andy W. H. Khong

    High-level decision-making for multiple uncrewed aerial vehicles (multi-UAV) mission planning is crucial, especially with the rising demand for long-term services in geo-distributed environments. However, the interrelated issues of multi-UAV deployment and task allocation are often addressed separately. This article integrates these two problems and introduces a hierarchical framework for effective decision-making. This is achieved by proposing balanced capability (BC), a customized metric tailored for long-term multi-UAV missions with geographically dispersed targets. By considering the global objective and self-organized coordination, a joint optimization model is established from a game-theoretical perspective. Additionally, a novel tangent and cotangent search algorithm (TCSA) is proposed to steer cooperative players toward the global objective in the upper layer, while in the lower layer, a modified distributed task allocation algorithm (MDT2A) incentivizes each autonomous player to efficiently maximize their individual benefits. Simulations validate the effectiveness of the proposed method, with comparative results highlighting the superiority of the algorithms.


  • Top Cited Papers

    Replanning-Oriented Framework for Efficient Real-Time Decision-Making in Multi-UAV Systems

    by Xingshuo Hai, Longyan Tan, Qiang Feng, Haibin Duan, Changyun Wen

    Efficient real-time decision-making for long-term multiple unmanned aerial vehicles (multi-UAV) missions in geo-distributed environments requires an integrated approach to manage dynamic task demands. We propose a hierarchical dual-layer decision-making framework for multi-UAV mission replanning. The upper layer optimizes multi-UAV deployment using the density-constrained K-medoids clustering and simulated annealing algorithm, achieving globally optimal solutions. The lower layer addresses task assignment via the goal-oriented belief space multiagent reinforcement learning algorithm, which leverages updated belief distributions to mitigate sparse reward and enhance training efficiency. Coordination between the two layers ensures comprehensive coverage of predefined demands while adapting to dynamic events. The effectiveness of the proposed methods is validated through a real-world case study using the 911 call dataset from city emergency services.


  • Hierarchical Decision-Making Framework for Multi-UAV Task Assignment via Enhanced Pigeon-Inspired Optimization

    by Weike Chen, Xingshuo Hai, Yanming Hu, Qiang Feng, Zili Wang

    Effective task assignment decisions are paramount for ensuring reliable task execution in multi-UAV systems. However, in the development of feasible plans, challenges stemming from extensive and prolonged task requirements are encountered. This paper establishes a decision-making framework for multiple unmanned aerial vehicles (multi-UAV) based on the well-known pigeon-inspired optimization (PIO) algorithm. By addressing the problem from a hierarchical structural perspective, the initial stage involves minimizing the global objective of the flight distance cost after obtaining the entire task distribution and task requirements, utilizing the global optimization capability of the classical PIO algorithm to allocate feasible task spaces for each UAV. In the second stage, building upon the decisions made in the preceding stage, each UAV is abstracted as an agent maximizing its own task execution benefits. An improved version of the PIO algorithm modified with a sine-cosine search mechanism is proposed, enabling the acquisition of the optimal task execution sequence. Simulation experiments involving two different scales of UAVs validate the effectiveness of the proposed methodology. Moreover, dynamic events such as UAV damage and task changes are considered in the simulation to validate the efficacy of the two-stage framework.


  • Resilience Measure and Formation Reconfiguration Optimization for Multi-UAV Systems

    by Qiang Feng, Meng Liu, Bo Sun, Hongyan Dui, Xingshuo Hai, Yi Ren, Chen Lu, Zili Wang

    Multiple unmanned aerial vehicle (multi-UAV) system is a type of dynamic spatiotemporal Internet of Things and susceptible to destruction from the external environment. Meanwhile, resilience theory has been introduced to describe the ability of unmanned aerial vehicles (UAVs) faced with disturbances. However, the existing methods do not fully reflect the dynamic spatiotemporal characteristics of multi-UAV systems. Therefore, we proposed a novel resilience metric that integrates mission coverage area and communication status to describe the dynamic spatiotemporal characteristics of multi-UAV systems. On the basis, a combination of importance measures for vulnerability, recoverability, and resilience is presented to support the analysis and identification of weaknesses for the system in whole process. Furthermore, a structure design method is given to improve system resilience by considering both importance measures and trajectory optimization methods simultaneously. Finally, a typical formation topology with six UAVs is simulated as a case study to verify the proposed approach.


  • Reliability Modeling of Dynamic Spatiotemporal IoT Considering Autonomy and Cooperativity Based on Multiagent

    by Qiang Feng, Xing Guo, Bo Sun, Hongyan Dui, Yi Ren, Xingshuo Hai, Dezhen Yang, Zili Wang

    Reliability modeling in the context of the Internet of Things (IoT) has received considerable attention from researchers to ensure the safety and stable operation of the relevant systems. However, current methods of reliability modeling are incapable of adequately characterizing the autonomy and cooperativity of the Dynamic Spatiotemporal IoT (DSIoT). To solve this problem, this study proposes an agent-based method of reliability modeling. The authors discuss the autonomy and cooperativity of the DSIoT in case of failure and summarize 11 typical failure states of its functional components. We then develop a multiagent-based framework for the reliability modeling of the DSIoT. Methods of failure modeling are analyzed to describe the propagation of failure within a node and among multiple nodes. Two kinds of criteria of failure are proposed for IoT systems with dynamic spatiotemporal characteristics, and a Monte Carlo simulation-based approach is given to evaluate the reliability of the DSIoT. We also illustrate the uses and effectiveness of the proposed method by using a case study involving a swarm of 16 intelligent unmanned aerial vehicles.


  • Open Access

    The Influence of the Uncertainty on Drones’ Cognition in Unmanned Aerial Vehicles Communication Network

    by Xingshuo Hai, Xinrui Ma, Weidong Zhang

    This paper analyzes the one-leader-multi-followers unmanned aerial vehicles (UAV) security game with misperception. In the leader-follower UAV security game, the solution concept under misperceptions can be defined as Misperception Strong Stackelberg Equilibrium (MSSE). However, by observing other strategies, players may realize the misperception, which makes players not trust their current cognition any longer. Therefore, this paper proposes a model that the leader drone is aware of the observed differences but all follower drones do not realize, and give the concrete definition of Hyper Best Response Equilibrium (HBRE). Besides, this paper analyzes the relation between the two equilibria in the one-leader-multi-followers UAV security game with misperception to reveal a sufficient condition for cognitive stability and strategy stability. Moreover, this paper verifies our conclusion by constructing several experiments.