Event
VisGeo-PipeTrack: A Dynamic Pipeline Tracking Framework for UAVs
1 reports · 1 sources
Zhenyang Gao and other authors proposed the VisGeo-PipeTrack servo control framework, enabling UAVs to track pipelines with dynamic motion such as vibration. On the detection side, YOLOv5 is used to recognize pipeline tags and locate them in combination with visual geometric constraints; on the control side, a model predictive control-based real-time correction adaptive PID (MPC-RCAPID) is adopted, which estimates the model online via recursive least squares and adjusts PID parameters through rolling optimization. The authors state that experiments in AirSim simulation and on the Tello UAV platform verified the effectiveness of the framework; in the Tello physical experiments, compared with standard PID, MPC-RCAPID reduced the average tracking error by 55.52%, 26.72%, and 26.52% across three test dimensions, respectively. These results come from the authors' report and await independent verification.
Report timeline
- VisGeo-PipeTrack: A visual-geometric servo control framework for UAV dynamic pipe tracking
The paper proposes the VisGeo-PipeTrack servo control framework, which uses YOLOv5 to detect pipe labels and combines visual geometric constraints for localization, enabling UAVs to track pipes with dynamic motion such as vibration. On the control side, it adopts a model predictive control-based real-time corrected adaptive PID (MPC-RCAPID), which estimates the model online via recursive least squares and adjusts PID parameters through rolling optimization.
arXiv cs.RO ·