This shows you the differences between two versions of the page.
Next revision | Previous revision Next revision Both sides next revision | ||
cs:fusion:start [2019/04/13 23:16] Andrew Rink created |
cs:fusion:start [2019/04/16 21:43] Andrew Rink |
||
---|---|---|---|
Line 1: | Line 1: | ||
====== Fusion ====== | ====== Fusion ====== | ||
+ | |||
+ | ===== Overview ===== | ||
+ | The fusion node is responsible for taking the outputs of our SLAM system and the output of our object detection system, | ||
+ | combining them, and publishing the results to the /tf topic. | ||
+ | |||
+ | ===== Structure ===== | ||
+ | Subscribes to: | ||
+ | * /vision/left - Object detections for left camera | ||
+ | * /SLAMpoints - Points for objects detected in SLAM | ||
+ | |||
+ | Publishes to: | ||
+ | * /tf - Global coordinates provided by SLAM combined with the labels from object detection | ||
+ | |||
+ | ===== How to Run ===== | ||
+ | Relies on the orb_slam node and the object detection node, as well as all their dependencies. To run, execute the following command from any directory: | ||
+ | <code bash> | ||
+ | $ rosrun robosub fusion | ||
+ | </code> | ||
+ |