cs.ROOct 26, 2026

VisGeo-PipeTrack: A Visual Geometric Servo Control Framework with MPC-RCAPID Control for UAV-Based Dynamic Pipes Tracking

Authors: Zhenyang Gao, Jianlin Chen, Yang Yu, Honghao Shan, Jiale Gao, Ziyan Jia

Organizations: School of Civil Aviation, Northwestern Polytechnical University, 127 West Youyi Road, Xi’an Shaanxi, 710072, P. R. China. · School of Aeronautics and Astronautics, Shanghai Jiao Tong University, Shanghai 200240, P. R. China.

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

While unmanned aerial vehicles (UAVs) are increasingly deployed for pipeline inspection, prevailing research predominantly assumes static pipes. In real-world industrial environments, pipes often exhibit dynamic movements, such as vibrations. This imposes more stringent requirements on UAVs' adaptive control and computational efficiency than in static scenarios. Therefore, this paper proposes a servo control framework named VisGeo-PipeTrack, which utilizes geometric constraints to enable UAV tracking of dynamic pipes. To achieve efficient UAV positioning, YOLOv5 is employed to detect labels on the pipe. The positions are derived from visual geometric constraints based on these detected labels to enable precise localization. To address tracking control challenges, a model predictive control based real-time corrected adaptive PID (MPC-RCAPID) controller is proposed. This controller employs the Recursive Least Squares method for real-time model estimation and integrates rolling horizon optimization to dynamically adjust PID parameters. Experiments conducted on both the AirSim simulator and the Tello UAV platform validate the effectiveness of the proposed framework. Simulation comparisons with standard PID, fractional-order PID, adaptive PID, and fuzzy PID demonstrate that MPC-RCAPID achieves the shortest settling time (3.26 s) and the lowest average tracking error (3.52%). In physical experiments on the Tello platform, compared with standard PID control, MPC-RCAPID reduces the average tracking error by 55.52%, 26.72%, and 26.52% across the three test dimensions. These results demonstrate that VisGeo-PipeTrack facilitates efficient autonomous tracking in dynamic pipe environments.

Figures & tables

Fig. 1: This paper proposes a servo control framework for the dynamic pipes tracking based on visual geometry named VisGeo-PipeTrack. The framework consists of a YOLOv5-based lightweight visual positioning servo system and an MPC-based real-time corrected adaptive PID control strategy, which includes three key components: MPC-FPMM (MPC Forward Prediction Model Modification), PMM (Prediction Model Modification), MPC-RO (MPC Rolling Optimization), and PID. This framework can enhance the performance of UAVs in tracking dynamic pipes.
Fig. 2: The application of variable speeds to the pipe induces positional changes, thereby simulating pipes vibrations under actual operating conditions.
Fig. 3: Guide the UAV to track the pipe and achieve relative positioning using the four labels attached to the pipe.
Fig. 4: The YOLOv5 object detection algorithm identifies the positions of four labels for subsequent localization calculations.
Fig. 5: The intersection point of the two groups of intersecting lines indicates the position where the UAV must remain inside the pipe.
Fig. 6: By combining the positions of the four labels detected by YOLOv5, the intersection point where the UAV needs to stabilize inside the pipe can be calculated.
Fig. 7: The position error between the UAV’s current location and the target location. This error is used for subsequent adjustments to the UAV’s flight attitude.
Fig. 8: The Tello UAV platform used in experiments. Key components include the propeller, guard circle, flight control unit, and 720P onboard camera. The UAV dimensions are 9.8 cm (length) × 9.25 cm (width).
Fig. 9: Simulation of UAV pipe tracking based on the Airsim and UE4 platforms, comparing the performance of the proposed method with the baseline method.
Fig. 10: As shown in the figure, the positions of the UAV’s visual center and the intersection of the two label pairs during tracking are illustrated. The green point denotes the intersection of the two label pairs, and the yellow point denotes the UAV’s visual center. It can be observed that the visual center remains consistently close to the intersection, indicating good tracking performance.
CategoriesAdjustment TimeMax ErrorAverage Error
MPC-RCAPID3.26s10.91%3.52%
PID5.16s14.19%6.96%
FO-PID8.14s13.14%7.44%
A-PID13.62s16.40%6.61%
F-PID11.83s16.32%6.36%
TABLE I: Comparison of Simulation Results
CategoriesParameters
Tello UAV Size9.8cm ×\times 9.25cm ×\times 4.1cm
The Pipe Radius60cm
The Pipe Length70cm
The Pipe Movement Speed30±5cm/s
UAV Camera Pixels720P
Experimental Site Width320cm
TABLE II: Experimental Parameters
Fig. 11: The experimental setup includes the observation camera, the Tello UAV platform, the ground station, pipe, and the vehicle for moving the pipe.
Fig. 12: The experimental process can be observed through both the global viewing and the UAV camera viewing to monitor the UAV’s flight attitude.
CategoriesSchemeAverage TimeMax ErrorAverage Error
DPISMPC-RCAPID7.41s17.34%6.73%
PID7.35s35.12%15.13%
DPEFMPC-RCAPID106.19s36.27%5.87%
PID121.80s43.79%8.01%
SPISMPC-RCAPID3.82s9.84%7.26%
PID7.82s11.92%9.88%
TABLE III: Comparison of Tello UAV Experimental Results
Fig. 13: Experimental comparison of the proposed MPC-RCAPID controller against the standard PID controller under three testing scenarios: DPIS (Dynamic Pipes Internal Shuttle), DPEF (Dynamic Pipes External Following), and SPIS (Static Pipes Internal Shuttle). In DPIS and SPIS, the pipe undergoes a brief motion disturbance then remains stationary. In DPEF, the pipe moves continuously throughout the UAV’s traversal. The three metrics reported are: Average Time (seconds, time from disturbance start until error stays below 10% threshold), Max Error (peak percentage error during the transient), and Average Error (mean percentage error over the whole trial). The corresponding numerical results are listed in TABLE III .
Fig. 14: Evaluating the performance of the MPC-RCAPID method versus the traditional PID method under three testing schemes: DPIS, DPEF, and SPIS. The figure shows the posture of the drone during tracking under these three testing schemes.
More in this topic

Quadrotor Control

Quadrotor control studies how to stabilize, guide, and adapt aerial robots under demanding flight conditions and physical constraints.

See all 126 papers

Explore similar work

CardsList
Apr 21, 2026

Autonomous UAV Pipeline Near-proximity Inspection via Disturbance-Aware Predictive Visual Servoing

Reliable pipeline inspection is critical to safe energy transportation, but is constrained by long distances, complex terrain, and risks to human inspectors. Unmanned aerial vehicles provide a flexible sensing platform, yet reliable autonomous inspection remains challenging. This paper presents an autonomous quadrotor near-proximity pipeline inspection framework for three-dimensional scenarios based on image-based visual servoing model predictive control (VMPC). A unified predictive model couples quadrotor dynamics with image feature kinematics, enabling direct image-space prediction within the control loop. To address low-rate visual updates, measurement noise, and environmental uncertainties, an extended-state Kalman filtering scheme with image feature prediction (ESKF-PRE) is developed, and the estimated lumped disturbances are incorporated into the VMPC prediction model, yielding the ESKF-PRE-VMPC framework. A terrain-adaptive velocity design is introduced to maintain the desired cruising speed while generating vertical velocity references over unknown terrain slopes without prior terrain information. The framework is validated in high-fidelity Gazebo simulations and real-world experiments. In real-world tests, the proposed method reduces RMSE by 52.63% and 75.04% in pipeline orientation and lateral deviation in the image, respectively, for straight-pipeline inspection without wind, and successfully completes both wind-disturbance and bend-pipeline tasks where baseline method fails. An open-source nano quadrotor is modified for indoor experimentation.

Wen Li, Hui Wang, Jinya Su +3

School of Automation, Key Laboratory of Measurement and Control of CSE, Ministry of Education, Southeast University, Nanjing 210096, China · Department of Aeronautical and Automotive Engineering, Loughborough University, LE11 3TU, United Kingdom · Research Centre for Low Altitude Economy and the Department of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University, Hong Kong, China

UAV NavigationIndustrial InspectionModel Predictive ControlQuadrotor ControlVision-Based Robot Control
AskPDF
Jul 14, 2026

Autonomous Tracking and Terminal Guidance of Moving Targets for Fixed-Wing UAVs

This study introduces a unified control framework for fixed-wing unmanned aerial vehicles (UAVs) fitted with a pan-tilt (PT) camera, intended to perform an end-to-end mission spanning from initial target detection to accurate terminal engagement. The proposed system employs a three-phase strategy: a vision-based target acquisition phase, an NMPC-based tracking phase, and a terminal guidance phase. During tracking, the framework uses an Unscented Kalman Filter (UKF) to fuse YOLO-based visual detections with inertial measurements, enabling robust target state estimation under unknown dynamics. To ensure reliable visual contact, we introduce a constraint-aware Nonlinear Model Predictive Control (NMPC) strategy that incorporates Control Barrier Functions (CBFs) to explicitly prevent UAV self-occlusion -- a common limitation in fixed-wing tracking. Upon satisfying terminal engagement conditions, the system seamlessly transitions control to a quaternion-based Biased Proportional Navigation Guidance (BPNG) law, enforcing precise impact angle constraints. High-fidelity simulations demonstrate that the framework achieves stable, robust tracking and accurate terminal interception while strictly respecting the vehicle's dynamic limits and camera field-of-view constraints.

Wei-Hao Liou, Teng-Hu Cheng

Department of Mechanical Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan 30010

Nonlinear MPCVisual Object Tracking
AskPDF
Mar 1, 2026

Information-Theoretic Framework for Self-Adapting Model Predictive Controllers

Model Predictive Control (MPC) is a vital technique for autonomous systems, like Unmanned Aerial Vehicles (UAVs), enabling optimized motion planning. However, traditional MPC struggles to adapt to real-time changes such as dynamic obstacles and shifting system dynamics, lacking inherent mechanisms for self-monitoring and adaptive optimization. Here, we introduce Entanglement Learning (EL), an information-theoretic framework that enhances MPC adaptability through an Information Digital Twin (IDT). The IDT monitors and quantifies, in bits, the information flow between MPC inputs, control actions, and UAV behavior. By introducing new information-theoretic metrics we call entanglement metrics, it tracks variations in these dependencies. These metrics measure the mutual information between the optimizer's input, its control actions, and the resulting UAV dynamics, enabling a deeper understanding of their interrelationships. This allows the IDT to detect performance deviations and generate real-time adaptive signals to recalibrate MPC parameters, preserving stability. Unlike traditional MPC, which relies on error-based feedback, this dual-feedback approach leverages information flow for proactive adaptation to evolving conditions. Scalable and leveraging existing infrastructure, this framework improves MPC reliability and robustness across diverse scenarios, extending beyond UAV control to any MPC implementation requiring adaptive performance.

Wael Hafez, Amir Nazeri

Semarx Research LLC, Alexandria, VA, USA

Adaptive MPCModel Predictive ControlAdaptive Control
AskPDF