Advancing Robot Person Following with Multi-Object Tracking and Dynamic ID Switching

Existing Robot Person Following usually assumes that the object is selected in the initial frame, which renders it incapable of switching the tracking object in subsequent frames. In this context, traditional methods such as object selection, person re-identification, or pose tracking that rely solely on the initial frame fall short of meeting the requirements of complex human-computer interaction applications. To address these limitations, this paper proposes a comprehensive framework for mobile robot person following based on multi-object tracking (MOT-RPF). Firstly, the framework integrates the improved OC-SORT tracking algorithm with gesture detection technology, enabling dynamic selection and precise identification and location estimation of multiple objects. Secondly, by planning the Dubins path and proposing a Lateral and Longitudinal Control Model based on the omnidirectional wheel robot, precise path tracking on the omnidirectional wheel mobile robot can be achieved. The proposed improved OC-SORT tracking algorithm was evaluated on public datasets such as DanceTrack and Person Tracking, demonstrating tracking and location accuracies of 60.5HOTA and 98.1% respectively, surpassing existing multi-object tracking OC-SORT and single-object tracking ODFS. The proposed robot person following framework operates on embedded systems equipped with NVIDIA Jetson Xavier NX. It has demonstrated its effectiveness in real-time tracking and following of individuals, as evidenced by its performance on a custom Person Following dataset and its successful application in real-world scenarios. Code and models are available at https://github.com/djdodsjsjx/MOT-RPF/.