STC-Tracker: Spatiotemporal-Consistent Multi-Robot Collaboration Framework for Long-Term Dynamic Object Tracking

Multi-robot cooperative tracking, as a vital sub-field of multi-robot collaboration, exhibits significant potential in areas such as military reconnaissance and emergency rescue. Conventional dynamic object tracking methods often face issues of incomplete target detection and even loss in complex scenes, owing to variations in viewpoint or occlusion. To address these problems, this paper proposes STC-Tracker, a multi-robot collaborative tracking system aimed at extending the lifecycle of dynamic objects. On the one hand, the system restores the original appearance of objects by retracing historical point clouds from keyframes while monitoring their motion trajectories in real time. On the other hand, by estimating the motion model of each target, our system is capable of maintaining the lifecycle of specific objects, even in cases of brief disappearance. Experiments are conducted on public and self-collected datasets. The results demonstrate that our algorithm outperforms SOTAs in both single-robot and multi-robot configurations while exhibiting low computational resource consumption. In addition, our algorithm supports LiDARs of different scanning patterns, including spinning LiDARs and solid-state LiDARs, and is capable of real-time dynamic object tracking and global map construction.

Authors

• Yanchao Dong
• Yuhao Liu
• Jinsong Li
• Bin He 0003

Keywords

• Hands
• Laser radar
• Target tracking
• Heuristic algorithms
• Dynamics
• Collaboration
• Reconnaissance
• Real-time systems
• Trajectory
• Object tracking
• Dynamic Objects
• Dynamic Tracking
• Dynamic Object Tracking
• Multi-robot Collaboration
• Point Cloud
• Global Map
• Motion Model
• Multi-agent Systems
• Object Appearance
• Viewpoint Variations
• Real-time Trajectory
• Deep Neural Network
• Observed Values
• Clustering Algorithm
• Bounding Box
• Model Weights
• Velocity Vector
• Motion Detection
• Data Layers
• Dynamic Point
• Large Objects
• Dynamic Clustering
• Deep Learning-based Methods
• Multi-object Tracking
• Multiple Frames
• Factor V
• Transfer Stations
• Single Robot
• Edge Clustering