Skip to Content

 

 Fu Changhong

  PhD student

  Universidad Politécnica Madrid

 


Personal

Publications

Projects

Research

 

On-board Light Low-cost Efficient ARM Architecture Pre-processing System for UAVs

On-board Light Low-cost Efficient ARM Architecture Pre-processing System for UAVs

Robust Stereo Visual Odometry and SLAM for Unmanned Aerial Vehicles

Robust Stereo Visual Odometry and SLAM for Unmanned Aerial Vehicles

Robust Dynamic RGB-D Localization and Mapping for UAVs

This reseach aims to provide the fast and robust visual algorithm for UAV to fly in the GPS-denied environment with high speed. The whole system consists of Asctec Pelican or DJI F550 UAV platform (hexcopter), Pixhawk, IntelNUC (Odroid) and RGB-D Sensor (Asus Xtion Pro Live). The real-time 6D pose is estimated by visual SLAM-based algorithm. The test environment includes: (1) Corridors; (2) Square with Obstacles; (3) Lab (Long-term); (4) School Entrance (Long-term); (5) Parking Places et al. The comparison with VICON and real flight show that the visual SLAM algorithm is accurate and robust.

Fuzzy Control Optimization using Cross-Entropy: Tuning the Membership Functions and Rules’ Weight to Control a UAV for See and Avoid

Define and tune a controller is a hard task to accomplish. Soft-Computing based controllers are little bit easier because they can be defined without knowing the model of the system to control. These type of controllers are defined using heuristic information, or based on expert knowledge. Classical method of optimization and definition are presented in the literature, as neural networks or genetic algorithms. The recently developed Cross-Entropy (CE) optimization method is a general Monte-Carlo approach to combinatorial and continuous multi-extremal optimization and importance sampling. This work presents a novel approach of this method to tune Fuzzy Logic Controllers (FLC). The control system to optimize is a vision based heading controller of an unmanned aerial vehicle (UAV) for See and avoid. The optimization process is focused on modify the size and the position of the membership functions’ sets of each variable and the rules’ weight to adapt the control system for this specific task. This has done in a simulated environment developed using Matlab. Two optimized controllers at different stages were tested in indoor tests with an AR.Drone at different speeds. The obtained results show the powerful performance of this technique to be apply for Fuzzy controller optimization. Not only the behavior of the controller was improved in few iterations, but also a big reduction of the Fuzzy controller’s rules was obtained

Cross-Entropy Optimized Fuzzy Logic Controllers for UAVs

Cross-Entropy Optimized Fuzzy Logic Controllers for UAVs 1. Scaling Factors 2. Membership Functions 3. Rule Weights