Search | Engineering

Subscribe Submit

Home Journals Focus Achievement Fronts About Us 中文版

Resource Type

Journal Article 4

Year

2020 1

2019 3

Keywords

Motion planning 2

Quadrotor 2

Unmanned aerial vehicle 2

Approximate dynamic programming 1

Decision making 1

Fault detection and diagnosis 1

Fault-tolerant control 1

Model reference adaptive control 1

Neural network 1

Reinforcement learning 1

open ︾

Search scope:

排序： Display mode:

Proximal policy optimization with an integral compensator for quadrotor control Research

Huan Hu, Qing-ling Wang,qlwang@seu.edu.cn

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 5, Pages 649-808 doi: 10.1631/FITEE.1900641

Abstract: algorithm to optimize the stochastic control strategy to achieve speed control of the “model-free” quadrotor

Keywords：强化学习；近端策略优化；四旋翼控制；神经网络

HTML PDF Collect

Safe navigation of quadrotorswith jerk limited trajectory None

Shu-peng LAI, Meng-lu LAN, Ya-xuan LI, Ben M. CHEN

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 1, Pages 107-119 doi: 10.1631/FITEE.1800719

Abstract:

Many aerial applications require unmanned aerial systems operate in safe zones because of the presence of obstacles or security regulations. It is a non-trivial task to generate a smooth trajectory satisfying both dynamic constraints and motion limits of the unmanned vehicles while being inside the safe zones. Then the task becomes even more challenging for real-time applications, for which computational efficiency is crucial. In this study, we present a safe flying corridor navigation method, which combines jerk limited trajectories with an efficient testing method to update the position setpoints in real time. Trajectories are generated online and incrementally with a cycle time smaller than 10 μs, which is exceptionally suitable for vehicles with limited onboard computational capability. Safe zones are represented with multiple interconnected bounding boxes which can be arbitrarily oriented. The jerk limited trajectory generation algorithm has been extended to cover the cases with asymmetrical motion limits. The proposed method has been successfully tested and verified in flight simulations and actual experiments.

Keywords： Quadrotor Unmanned aerial vehicle Motion planning

HTML PDF Collect

Motion planning of a quadrotor robot game using a simulation-based projected policy iteration method Regular Papers

Li-dong ZHANG, Ban WANG, Zhi-xiang LIU, You-min ZHANG, Jian-liang AI

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 4, Pages 525-537 doi: 10.1631/FITEE.1800571

Abstract: We propose a formulation of a velocity varying one-on-one quadrotor robot game problem in the threedimensionaldecision strategy can generate effective and efficient motion policies that can contend with the opponent quadrotor

Keywords： Reinforcement learning Approximate dynamic programming Decision making Motion planning Unmanned aerial vehicle