IROS 2025: Robots Calling the Shots: Using Multiple Ground Robots for Autonomous Tracking in Cluttered Environments

Weijian Zhang, Charlie Street, Masoumeh Mansouri

University of Birmingham

Overview

The source code for the paper "Robots Calling the Shots: Using Multiple Ground Robots for Autonomous Tracking in Cluttered Environments".

Features

• A novel sequential greedy viewpoint planning approach to generate collision-free paths that optimize camera coverage and minimize occlusions.

• A trajectory optimization method that refines the initial planned paths into smooth, kinodynamically feasible trajectories while considering the motion constraints of gimbal-mounted cameras.

Requirements

• ROS Noetic or later
• Ubuntu 20.04 or later
• Gurobi 10.0.1 or later

Installation

1. Create a new workspace:

$ mkdir -p ~/visFormationPlanner/src
$ cd ~/visFormationPlanner/src
$ catkin_init_workspace

2. Clone the package into the workspace:

$ git clone git@github.com:HyPAIR/visFormationPlanner.git

3. Install dependencies:

$ cd ~/visFormationPlanner/src/visFormationPlanner/vis_formation_planner
$ rosdep install --from-paths src --ignore-src --rosdistro noetic -r -y

4. Build the workspace:

$ cd ~/visFormationPlanner
$ catkin_make

Test in Rviz

Launch the simulation to trajectory optimisation result (3 robots in a simple scenario):

$ roslaunch vis_formation_planner vis_test.launch
$ roslaunch vis_formation_planner animation_demo.launch

Test in Gazebo

Write the obstacles to the yaml file, and launch the simulation in Gazebo:

$ roslaunch vis_formation_planner write_obs_to_world.launch
$ roslaunch vis_formation_planner heterogeneous_triangle.launch

Video

A simulation video demonstrating our proposed framework can be found at bilibili/youtube.

Citation

If you find this work useful, please cite (paper):

@INPROCEEDINGS{11247464,
  author={Zhang, Weijian and Street, Charlie and Mansouri, Masoumeh},
  booktitle={2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, 
  title={Robots Calling the Shots: Using Multiple Ground Robots for Autonomous Tracking in Cluttered Environments}, 
  year={2025},
  volume={},
  number={},
  pages={12667-12674},
  keywords={Target tracking;Robot vision systems;Green products;Cinematography;Cameras;Planning;Safety;Collision avoidance;Robots;Trajectory optimization},
  doi={10.1109/IROS60139.2025.11247464}}