Enable people tracking in the simulator with simulation_follow_me

For more information, see the simulation_follow_me on GitHub.

Simulated warehouse in Gazebo where the robot detects a walking person and follows them along the aisle.

Pipeline flow for `simulation_follow_me`

The following figure shows the pipeline flow for simulation_follow_me.

The simulation_follow_me pipeline linking Gazebo camera and depth nodes to the tracker, controller, and robot base node. — The simulation_follow_me pipeline.

ROS nodes used in the `simulation_follow_me` pipeline

The following table lists the ROS nodes used in the simulation_follow_me pipeline and describes what each node does.

ROS node	Description
`camera node`	Publishes camera frames RGB image data to a ROS topic in Gazebo.
`depth camera node`	Publishes camera frames depth image data to a ROS topic in Gazebo.
`Root base node`	Subscribes to control commands and coordinates motion with the autonomous mobile robot (AMR) in Gazebo.
`Follow me Tracker`	Subscribes to camera information and runs a model to target detection on the device.
`Follow me Controller`	Publishes the movement execution `/cmd_vel` commands on the device.

ROS topics used in the `simulation_follow_me` pipeline

The following table lists the ROS topics used in the simulation_follow_me pipeline, with the message type, the publisher or subscriber, and a description of each topic.

ROS topic	Message type	Published by/Subscription	Description
`/image_raw`	`sensor_msgs.msg.Image`	Subscribes to images from other nodes.	Indicates the image for processing.
`/camera/depth/image_raw`	`sensor_msgs.msg.Image`	Published by `camera node`.	Publishes the image depth topic.
`/cmd_vel`	`geometry_msgs.msg.Twist`	Published by `Follow me Controller`	Publishes the movement execution topic.

Prerequisites

You have set up the device, installed ROS2 Jazzy and the Qualcomm Intelligent Robotics (QIR) SDK on the device according to Install the QIR SDK.

Ensure you have connected the board to the simulation host using an Ethernet cable. Otherwise, the sample’s performance may degrade due to data transmission issues.

Run out-of-the-box `simulation_follow_me`

On the device, run the follow-me function

On the device, run the follow-me function according to Run out-of-the-box follow_me.

In a terminal of the host computer, set up and run the simulation_follow_me sample application

On the host, run QRB Robot Base AMR according to the README of QRB ROS Simulation. Ensure that the device and the host are on the same local network and can communicate with each other through ROS communication.

Run the following command in the simulation environment.

Run the sample in Gazebo

# Run samples in Gazebo
git clone https://github.com/qualcomm-qrb-ros/qrb_ros_samples.git
cd robotics/simulation_follow_me

export ROS_DOMAIN_ID=123
ros2 launch qrb_ros_sim_gazebo gazebo_robot_base_mini.launch.py world_model:=warehouse_followme_path2  rgb_camera_config_file:=$(pwd)/followme_rgb_camera_params.yaml enable_laser:=false enable_imu:=false

​Pipeline flow for simulation_follow_me

​ROS nodes used in the simulation_follow_me pipeline

​ROS topics used in the simulation_follow_me pipeline

​Prerequisites

​Run out-of-the-box simulation_follow_me

Pipeline flow for `simulation_follow_me`

ROS nodes used in the `simulation_follow_me` pipeline

ROS topics used in the `simulation_follow_me` pipeline

Prerequisites

Run out-of-the-box `simulation_follow_me`