Xinli Xu

Xinli Xu

Auto-generated profile, based on publicly available information

Xinli Xu

School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, China

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
1 January 2022 in Neurocomputing
Verified
Journal Article
Closed access
XXXinli Xu
Xinli Xu
PCPeng Cai
Peng Cai
ZAZahoor Ahmed
Zahoor Ahmed
VYVidya Sagar Yellapu
Vidya Sagar Yellapu
WZWeidong Zhang
Weidong Zhang


5 February 2024 in Ocean Engineering
Verified
Journal Article
Closed access
XXXinli Xu
Xinli Xu
YCYunlong Cao
Yunlong Cao
PCPeng Cai
Peng Cai
WZWeidong Zhang
Weidong Zhang
HCHongtian Chen
Hongtian Chen

31 July 2025 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
XXXinli Xu
Xinli Xu
XLXinyu Liu
Xinyu Liu
YZYapeng Zhao
Yapeng Zhao
QCQi Chen
Qi Chen
Daqi ZhuDaqi Zhu
Daqi Zhu
Autonomous surface vessels (ASVs) play a crucial role in military, civilian and scientific research fields, and path planning technology is the foundation for ensuring the navigation of ASVs. However, reinforcement learning algorithms face challenges in path planning, such as low sample utilization efficiency and difficulties in collecting effective data. To address these issues, this paper proposes an efficient reinforcement learning path planning algorithm based on knowledge transfer. First, a state similarity model is introduced to measure the differences between source and target samples. By identifying and transferring similar samples, the learning speed for new tasks is significantly accelerated. Second, considering the complex rules of the International Regulations for Preventing Collisions at Sea (COLREGs), high-quality collision avoidance samples from the source task are selected as knowledge transfer objects, thereby reducing the failure rate of agents in the collision avoidance process. Finally, the impact of the proportion of source task samples in the total sample pool on algorithm performance is analyzed. A progressive exploration method based on sample proportion is established to mitigate the issue of negative transfer. Simulation results demonstrate that the collision avoidance success rate of the algorithm has been significantly improved, with an average success rate of 91% across five typical collision avoidance scenarios—an increase of over 30% compared to the traditional DDPG algorithm. The convergence speed of the reward value improved by 50% after 1000 training episodes. Real-world ship tests verified that it can achieve real-time collision avoidance in complex environments, with a path safety compliance rate of 100%. The algorithm effectively enhances the reliability and safety of autonomous navigation for ASVs.

1 April 2013
Verified
Conference Paper
Closed access
WWWanliang Wang
Wanliang Wang
LLLi Li
Li Li
XXXinli Xu
Xinli Xu
CXCheng Xu
Cheng Xu
YZYanwei Zhao
Yanwei Zhao
Considering that the standard particle swarm optimization has slow convergence speed and is easy to trap into local optimal solution, this paper proposed an improved algorithm with a dynamic neighborhood topology, where the connections between the particles are adjusted with a changing dynamical neighborhood structure of the particle. In the early stage of the algorithm, the impact of the optimal particle is weakened to maintain the diversity of the population and to prevent the algorithm from local optimum, then connections between particles are added to make the algorithm have more rapid convergence in the later stage. Focusing on hydropower optimal scheduling problems, we discussed relevant technologies, built the model of scheduling considering ecological water demand and studied the calculation of river Ecological Water Demand in the ecological operation of hydropower station. We combined ecological operation and generation scheduling taking maximum of power generation as the objective and taking into account constraints like ecological factors of the river, the balance of reservoir water, discharge volume restrictions, output restrictions etc., then we used an improved particle swarm algorithm to solve the optimization problem. The simulation scheduling results show that the algorithm has strong global search ability and rapid convergence speed, which can effectively solve such a multi-constrains, non-linearity problem in hydropower stations scheduling.

1 January 2017 in International Journal of Computer Applications in Technology
Verified
Journal Article
Closed access
XXXinli Xu
Xinli Xu
ZJZhen Jiang
Zhen Jiang
OHOsheng Hu
Osheng Hu
This paper presents a novel reconfigurable control method for an aircraft with potential actuator failures. A Variable Structure Model Reference Adaptive Control (VS-MRAC) scheme is deployed to counteract the adverse effects when the actuator failure occurs. Combined with exponential reaching law, the convergence rate is improved and the chattering is reduced. This approach ensures that the reference input value can be tracked rapidly and accurately. The safety and stability of the aircraft is much improved during the event of actuator failures. Finally, the simulation results are given to show the effectiveness and performance of the developed method.