Jie Huang

ORCID: 0000-0003-2158-8168
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Robotic Path Planning Algorithms
  • Optimization and Search Problems
  • Distributed Control Multi-Agent Systems
  • Robotics and Sensor-Based Localization
  • Innovative Energy Harvesting Technologies
  • Guidance and Control Systems
  • Advanced Manufacturing and Logistics Optimization
  • Wireless Power Transfer Systems
  • Time Series Analysis and Forecasting
  • Anomaly Detection Techniques and Applications
  • Energy Harvesting in Wireless Networks
  • Network Security and Intrusion Detection
  • Reinforcement Learning in Robotics

Northeastern University
2020-2024

State Key Laboratory of Synthetical Automation for Process Industries
2024

Xidian University
2019-2020

Universidad del Noreste
2019

This paper mainly studies the obstacle avoidance and rapid reconstruction of UAV formations. A hybrid trajectory planning algorithm based on potential field fluid dynamic model bidirectional fast search random tree is proposed to improve ability formation adapt complex environment. Firstly, a system mathematical energy proposed; function between formations modify disturbance flow field. Secondly, IBi-directional Rapidly Exploring Random Tree (IBi-RRT) with adaptive step size scheduled solve...

10.1109/access.2019.2961632 article EN cc-by IEEE Access 2019-12-23

ACO (ant colony algorithm) is a kind of bionic optimization algorithm developed in recent decades, which has shown its excellent performance and great development potential solving many complex problems. Q-learning, type reinforcement learning, gained increasing popularity autonomous mobile robot path recently. In order to effectively solve planning problem obstacle avoidance environment, model search based on improved ant are proposed. The incentive learning mechanism introduced with the...

10.23919/ccc50068.2020.9189320 article EN 2020-07-01

The constant parameter is usually set in adaptive function with traditional mobile robot path planning problem. Q-learning, a type of reinforcement learning, has gained increasing popularity autonomous recently. In order to effectively solve problem obstacle avoidance environment, model and search algorithm based on improved learning are proposed. incentive mechanism introduced selection strategy, modifying dynamic reward setting. group intelligent iterative process global position local...

10.1145/3366715.3366717 article EN 2019-10-16
Coming Soon ...