Research

Share    

Precision landing for unmanned aerial vehicle

Objective

To solve precise landing problem of a vertical takeoff and landing (VTOL) UAV using a cost-effective control system.

Description

Current progress includes the development of the vision-based landing algorithm for a Tricopter UAV with available payload below 600 g. The newly developed UAV is equipped with local and global positioning systems comprising an on-board computer, a low-cost camera and an autopilot system. 

Experimental tests have been successfully carried out for UAV’s landing on a predefined landing targets under different illumination (sunny and cloudy) and weather conditions (calm and breezy). 

In addition, the application of the visual algorithm has also been extended for undefined landing targets with unknown size and the target precision is set below 30 cm.

   

                                             Integration of the control algorithm in the Tricopter UAV



Demonstration     
        

                                              Landing test on moving (left) and static (right) targets  



Video



Publications

  1. Changhong Fu, Ran Duan, Dogan Kircali and Erdal Kayacan, "Onboard Robust Visual Tracking for UAVs Using a Reliable Global-Local Object Model" 19(9), Sensors, 2016
  2. Ran Duan, Changhong Fu, Erdal Kayacan, Danda Pani Paudel. "Recommended Keypoint-Aware Tracker: Adaptive Real-time Visual Tracking Using Consensus Feature Prior Ranking". 2016 IEEE International Conference on Image Processing (ICIP2016).
  3. Yiquan Dong, Changhong Fu, Erdal Kayacan. "RRT-based 3D Path Planning for Formation Landing of Quadrotor UAVs. 2016 International Conference on Control, Automation, Robotics and Vision" (ICARCV2016).
  4. Nursultan Imanberdiyev, Changhong Fu, Erdal Kayacan and I-Ming Chen, "Autonomous Navigation of UAV by Using Real-Time Model-Based Reinforcement Learning". 2016 International Conference on Control, Automation, Robotics and Vision (ICARCV2016).
  5. Ran duan, Changhong Fu, Erdal Kayacan, "Recoverable Recommended Keypoint-Aware Visual Tracking Using Coupled-Layer Appearance Modelling". 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2016).

​​

Principal Investigators


Assistant Prof. Erdal Kayacan (NTU)

Telephone: 6790 5585
Office: N3.2-02-28
Email: erdal@ntu.edu.sg
Mr. Paul Tan (STE)

Telephone: 6660 1052
Office: S1-B4a-03
Email: paultan@stengg.com
​​​​​​