PeopleFlow

A Gazebo-based simulator designed to model context-sensitive human-robot spatial interactions in shared workspaces. It features realistic human and robot trajectories influenced by contextual factors such as time, environment layout, and robot state, and can simulate a large number of agents. It involves a TIAGo robot and multiple pedestrians modelled using the pedsim_ros ROS library.

Citation

If you find this repo useful for your research, please consider citing the following paper:

@misc{castri2025causalityenhanceddecision,
      title={Causality-enhanced Decision-Making for Autonomous Mobile Robots in Dynamic Environments}, 
      author={Luca Castri and Gloria Beraldo and Nicola Bellotto},
      year={2025},
      eprint={2504.11901},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2504.11901}, 
}

Features

• Customisable world
• Customisable people behaviours
• Customisable HRI scenario
• Customisable plans for the TIAGo robot
• Possibility to add context factors influencing human and TIAGo behaviours.

How to use

Build and Run with Docker Compose

After cloning the repository, navigate to the directory and use the docker-compose scripts to manage the container.

1. Build the Image: First, build the Docker images defined in the docker-compose.yml file.

   cd /path/to/PeopleFlow
   ./docbuild.sh 

2. Run the Container: Once the images are built, start the services in detached mode (in the background).

   ./docrun.sh 

---

Managing the Container

Two additional scripts are provided to help you interact with and stop the running container:

• Access the Container Shell: To open a BASH terminal inside the running container (for debugging or running commands):

  ./docshell.sh

• Stop the Container: To stop and remove the containers and network created by docker-compose:

  ./docstop.sh

Building ROS workspace

Once inside the container using ./docshell, you can build the ros_ws workspace with the following command:

catkin build

Scenario setup and launch

Once inside the Docker container, run the following command to view the .tmule file containing all simulator parameters:

roscd hrisim_tmule/tmule
cat hrisim_bringup.yaml

Parameters:

• TIAGO_TYPE - specifies the type of TIAGo robot;
• INIT_BATTERY - initial battery level of the robot. Default 100;
• STATIC_DURATION - battery duration (hours) when robot is idle. Default 5;
• DYNAMIC_DURATION - battery duration (hours) when robot is moving. Default 4;
• CHARGING_TIME - battery charging time (hours). Default 2;
• ABORT_TIME_THRESHOLD - Task completion deadline (seconds). Default 45;
• WORLD - name of world and map to load. Default "warehouse"
  If you want to add your own WORLD, you can include your .world file in hrisim_gazebo/worlds and your map in hrisim_gazebo/tiago_maps.
  Note that the map must have the same name as the .world file;
• SCENARIO - pedsim scenario to load. Default "warehouse"
  If you want to add your own SCENARIO, you can include your .xml file in /pedsim_ros/pedsim_simulator/scenarios;
• ALLOW_TASK - if True, allows pedestrians to perform tasks when they reach their target position;
• MAX_TASKTIME - maximum task duration (seconds);
• GUI - if False, disables the Gazebo gui;
• MAX_STEP_SIZE - time (seconds) in the simulation to be simulated in one step;
• FORCE_OBSTACLE - social force model parameter (Helbing et. al);
• SIGMA_OBSTACLE - social force model parameter (Helbing et. al);
• FORCE_SOCIAL - social force model parameter (Helbing et. al);

If you want to modify any of these parameters, you can edit the hrisim_bringup.yaml file by:

roscd hrisim_tmule/tmule
nano hrisim_bringup.yaml

Once the tmule file is configured, you can start the simulator with the following command:

tstart

to visualise the tmule session

tshow

once inside the tmule, run the following command to change panel:

Ctrl+b
panel number [0-N]

and finally to stop it

Ctrl+b
panel number 0
tstop

Planning

The ROS-Causal_HRISim includes the PetriNetPlans to define predefined plans for the TIAGo robot. The plan is a combination of actions and conditions that can be defined to create your own plan. Three different folders have been pre-created for plans, actions, and conditions, and they are:

• hrisim_plans
• hrisim_actions
• hrisim_conditions

For more details on how to define plans, actions, and conditions, visit the PetriNetPlans GitHub reposity.

Recent changes

Version	Changes
1.1.0	docker optimised
1.0.0	package released