This lesson demonstrates how MOV.AI’s autonomous navigation flow enables a robot to know where it is on the map, know the destination to which it has to travel (goal) and to autonomously determine the path to reach that destination, as well as to handle dynamic obstacles (such as people walking by) along the way.
The flow in this lesson demonstrates the localization that is enabled by the map that was saved when the robot scoped out its environment, as described in Quick Tour – Mapping Application.
During the installation of MOV.AI, two ready-made maps were provided that will be used in this lesson – the map of the warehouse environment, as well as a Depot world map (which is similar to the localization map that was created in the previous lesson).
This lesson is accompanied by a flow that we prepared for you named husky_autonomous_navigation. During this lesson, you’ll open that flow and watch how the flow guides the robot in the simulator through the global localization map.
This flow demonstrates autonomous navigation of a Husky robot (a similar flow is also provided for a Tugbot robot). The depot map is used with ROS amcl and ekf_odom nodes for localization. The ROS move_base node is also used with the global_planner and teb_local_planner, as well as global_costmap and local_costmap to navigate the robot. In the flow, the go_to node is used to send a goal (destination) to move_base. After being localized, the robot will travel to a preset destination in the map, which can be configured using the parameters of the go_to node.
This demonstration also shows the usage of RViz, which is a 3D visualization tool for ROS applications that provides a view of your robot model and the sensor information that is captured by the robot’s sensors in the Ignition Gazebo world.
Updated almost 2 years ago