Xiaoxiao Guo

Ms. Xiaoxiao Guo


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 November 2025 in Sensors
Verified
Journal Article
Open access
PDF file
SGShuyuan Gao
Shuyuan Gao
YXYang Xu
Yang Xu
XGXiaoxiao Guo
Xiaoxiao Guo
CLChenchen Liu
Chenchen Liu
XWXiaobai Wang
Xiaobai Wang
Efficient and stable path planning in dynamic and obstacle-dense environments, such as large-scale structure assembly measurement, is essential for improving the practicality and environmental adaptability of mobile robots in measurement and quality inspection tasks. However, traditional reinforcement learning methods often suffer from inefficient use of experience and limited capability to represent policy structures in complex dynamic scenarios. To overcome these limitations, this study proposes a method named DPDQN-TER that integrates Transformer-based sequence modeling with a multi-branch parameter policy network. The proposed method introduces a temporal-aware experience replay mechanism that employs multi-head self-attention to capture causal dependencies within state transition sequences. By dynamically weighting and sampling critical obstacle-avoidance experiences, this mechanism significantly improves learning efficiency and policy performance and stability in dynamic environments. Furthermore, a multi-branch parameter policy structure is designed to decouple continuous parameter generation tasks of different action categories into independent subnetworks, thereby reducing parameter interference and improving deployment-time efficiency. Extensive simulation experiments were conducted in both static and dynamic obstacle environments, as well as cross-environment validation. The results show that DPDQN-TER achieves higher success rates, shorter path lengths, and faster convergence compared with benchmark algorithms including Parameterized Deep Q-Network (PDQN), Multi-Pass Deep Q-Network (MPDQN), and PDQN-TER. Ablation studies further confirm that both the Transformer-enhanced replay mechanism and the multi-branch parameter policy network contribute significantly to these improvements. These findings demonstrate improved overall performance (e.g., success rate, path length, and convergence) and generalization capability of the proposed method, indicating its potential as a practical solution for autonomous navigation of mobile robots in complex industrial measurement scenarios.

12 December 2025 in Aerospace
Verified
Journal Article
Open access
PDF file
CZChenchen Zhang
Chenchen Zhang
YWYifeng Wang
Yifeng Wang
HWHongfei Wang
Hongfei Wang
JZJingfei Zhang
Jingfei Zhang
SJShan Jin
Shan Jin
LZLu Zhang
Lu Zhang
With the advancement of China’s space sector, the China Space Station has transitioned from the research and construction phase to the application and development phase. This evolution signifies that payload missions in orbit are now being comprehensively executed. As a result, the management and control of payload operations face numerous challenges, including substantial workloads, extended timelines, complex operational requirements, multifaceted collaborations, and dynamic conditions. To ensure the safe and efficient implementation of extensive space science missions under the China Manned Space Program, as well as to optimize the utilization of space resources and enhance application outcomes, it is imperative to systematically assess and synthesize the requirements for in-orbit management of space applications. Employing a task-oriented framework, this study compares the organizational structures of both domestic and international space stations, providing a comprehensive overview of the operational management model for space application systems. It delineates strategies for in-orbit operation management encompassing task planning, operational supervision, anomaly detection, data analysis, and personnel coordination. Furthermore, the article evaluates the current status of in-orbit operation management and highlights significant scientific achievements. Finally, it addresses the challenges and future prospects, with particular emphasis on digitization, intelligent systems, and space–ground collaborative mechanism.