Benchmarking Multi-Sensor Multi-People Tracking for Ground Robots

We contribute a novel dataset to benchmark people tracking modules designed for ground robots. We consider a scenario where a robot moves, in a socially compliant manner, among people, tracking them accurately using multiple diverse sensors. The sequences recorded in the dataset are varied (e.g., in terms of people density, people behaviours, presence of obstacles, and robot movements) to cover a wide set of application scenarios. 

An article accompanying the dataset and including instructions and software is under submission at Data in Brief.