Self-Corrective Sensor Fusion for Drone Positioning in Indoor Facilities

TL;DR

This work addresses accurate indoor drone positioning for automated car quality control by proposing a self-corrective sensor fusion framework that combines independent Kalman filtering on UWB data, stream-clustering for stopping-point denoising, and cumulative-correction vectors to adjust visual odometry when sensors diverge. By exploiting the complementary strengths of UWB at static stopping points and visual odometry for straight trajectories, the method demonstrates superior robustness to mutual sensor errors compared to Kalman fusion, achieving approximately $5$ cm stopping-point accuracy in realistic indoor scenarios. The approach maintains high path fidelity and outperforms Kalman-based fusion when the visual odometer loses references, offering a practical, deployment-friendly solution for Industry 4.0 quality-control workflows. Future work includes integrating fused outputs with independent filtering and validating the method in real industrial environments, such as car production lines.

Abstract

Drones may be more advantageous than fixed cameras for quality control applications in industrial facilities, since they can be redeployed dynamically and adjusted to production planning. The practical scenario that has motivated this paper, image acquisition with drones in a car manufacturing plant, requires drone positioning accuracy in the order of 5 cm. During repetitive manufacturing processes, it is assumed that quality control imaging drones will follow highly deterministic periodic paths, stop at predefined points to take images and send them to image recognition servers. Therefore, by relying on prior knowledge about production chain schedules, it is possible to optimize the positioning technologies for the drones to stay at all times within the boundaries of their flight plans, which will be composed of stopping points and the paths in between. This involves mitigating issues such as temporary blocking of line-of-sight between the drone and any existing radio beacons; sensor data noise; and the loss of visual references. We present a self-corrective solution for this purpose. It corrects visual odometer readings based on filtered and clustered Ultra-Wide Band (UWB) data, as an alternative to direct Kalman fusion. The approach combines the advantages of these technologies when at least one of them works properly at any measurement spot. It has three method components: independent Kalman filtering, data association by means of stream clustering and mutual correction of sensor readings based on the generation of cumulative correction vectors. The approach is inspired by the observation that UWB positioning works reasonably well at static spots whereas visual odometer measurements reflect straight displacements correctly but can underestimate their length. Our experimental results demonstrate the advantages of the approach in the application scenario over Kalman fusion.

Figures (9)

• Figure 1: Quality control protocol of a car in a production chain (courtesy PSA Mangualde Portugal). The elements in the sequential protocol are highlighted in red.
• Figure 2: Drone LIDAR.
• Figure 3: Laboratory testbed indicating the locations of Pozyx anchors B1 - B4, surface X and reinforced concrete columns Y.
• Figure 4: Drone sensor platform. Left: front view. Right: rear view.
• Figure 5: Worst case in the laboratory testbed with severe loss of RealSense references. Stopping points marked as “+”. Pozyx anchors marked as “x”. Ideal path marked as straight segments. Scales in mm.