| ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | ros @ Robotics Stack Exchange |
Is it possible to run the navigation stack and navigate towards goals (ignoring obstacles) by combining odometry, IMU data and gps data? The robot is meant to drive in an open field where basically everything looks the same and there are barely any obstacles. Beacons or any kind of fixed frame of reference aside from gps isn't available.
As mentioned by @soldierofhell this is more a "localization" problem than a navigation problem. In order to combine odom, IMU, and GPS to generate an estimate of your position consider using the robot_localization package. This, as far as my experience is concerned, is the standard way to do what you want to do. Once you have your robot localized in the space then the ROS nav stack will be able to take you from waypoint to waypoint.
For the integration of GPS robot_localization provide the navsat_transform_node and a detailed tutorial on how to integrate this with the other sensors to generate a localization state estimate.
Asked: 2021-01-12 21:17:09 -0600
Seen: 980 times
Last updated: Jan 13 '21
ROS Answers is licensed under Creative Commons Attribution 3.0 Content on this site is licensed under a Creative Commons Attribution Share Alike 3.0 license.
