A5029408136- Robotics and Sensor-Based Localization
- Robotic Path Planning Algorithms
- Adaptive Control of Nonlinear Systems
- Advanced Vision and Imaging
- Simulation Techniques and Applications
- Video Surveillance and Tracking Methods
- Advanced Image and Video Retrieval Techniques
- Adaptive Dynamic Programming Control
- Indoor and Outdoor Localization Technologies
- UAV Applications and Optimization
- Teleoperation and Haptic Systems
- Distributed Control Multi-Agent Systems
- Inertial Sensor and Navigation
- Robotic Locomotion and Control
- Simulation and Modeling Applications
Nanyang Technological University
2016-2024
Işık University
2012-2014
In this paper, we present a novel onboard robust visual algorithm for long-term arbitrary 2D and 3D object tracking using reliable global-local model unmanned aerial vehicle (UAV) applications, e.g., autonomous chasing moving target. The first main approach in is the use of global matching local approach. other words, initially finds feature correspondences way that an improved binary descriptor developed iterative Lucas–Kanade optical flow employed tracking. second module efficient...
Simultaneous Localization and Mapping (SLAM) is moving towards a robust perception age. However, LiDAR-and visual- SLAM may easily fail in adverse conditions (rain, snow, smoke fog, etc.). In comparison, based on 4D Radar, thermal camera IMU can work robustly. But only few literature be found. A major reason the lack of related datasets, which seriously hinders research. Even though some datasets are proposed radar past four years, they mainly designed for object detection, rather than SLAM....
Simultaneous Localization and Mapping (SLAM) is moving towards a robust perception age. However, LiDAR- visual- SLAM may easily fail in adverse conditions (rain, snow, smoke fog, etc.). In comparison, based on 4D Radar, thermal camera IMU can work robustly. But only few literature be found. A major reason the lack of related datasets, which seriously hinders research. Even though some datasets are proposed radar past four years, they mainly designed for object detection, rather than SLAM....
Teleoperation or remote operation is an important part of research in autonomous vehicles and robots. It serves as a useful backup option case the system encounters any issue human intervention needed. In heavy-duty for off-road applications, teleoperation also good alternative even without autonomy, it can help improve working conditions operators. either case, be quite challenging due number factors such network connectivity, lack natural visual perspective inability operator to judge...
In this work, we address fast and agile manoeuvre control problem of unmanned aerial vehicles (UAVs) using an artificial neural network (ANN)-assisted conventional controller. Whereas the need for having almost perfect accuracy UAVs pushes operation to boundaries performance envelope, safety reliability concerns enforce researchers be more conservative in tuning their controllers. As alternative solution aforementioned trade-off, a reliable yet accurate controller is designed trajectory...
Ground plane detection is essential for successful navigation of vision based mobile robots. We introduce a novel and robust ground algorithm using depth information acquired by Kinect sensor. Unlike similar methods from the literature, we do not assume that covers largest area in scene. Furthermore our handles two different conditions: fixed changing view angle show if whereas an additional procedure angles satisfactorily.