Skip to content

Surface Normals Costmap

Ali Ryckman edited this page Nov 15, 2023 · 5 revisions

Context: URC rules indicate a significant obstacle will obstruct the water bottle during the auton mission.

The second object will be a standard 1 L wide-mouthed plastic water bottle of unspecified color/markings (approximately 21.5 cm tall by 9 cm diameter). The second object may have obstacles in the way that require autonomous avoidance.

Problem: When navigating during the auton mission, we assume the ground is flat enough for the rover to drive over any obstacles. This is not a realistic assumption for driving to the water bottle so perception must provide information about surrounding obstacles so navigation can avoid them.

Solution: Perception will construct a local costmap using the ZED's point cloud surface normals. This costmap will be stitched together over time in the map frame and allow navigation to autonomously path plan.


Interface (subject to change)

Node: point_cloud_projection

Subscribes: sensor_msgs/PointCloud2

Publishes: nav_msgs/OccupancyGrid

Note: This will have to run as a nodelet under the perception_nodelet_manager

Rough Steps:

  1. Create subscriber for the point cloud topic
  2. Compute surface normals from the point cloud using PCL

Clone this wiki locally