Skip to content

Simultaneous localization and planning for biped robot and texture mapping. Uses LIDAR scans; IMU roll, pitch, yaw data; gyro; and Kinect for RGB-Depth images for texture map

License

Notifications You must be signed in to change notification settings

RajatBhageria/Visual-SLAM

Repository files navigation

SLAM:

The entire SLAM program is in the SLAM.py file. To run it, you simply have to pass in the full filepath of the
lidar scan data and the joint data. When it's done, it'll show the completed map. Please be patient though since the
MapUtils functions were slow and thus with large scan data, this process can take up to an hour. To make sure it's working
you can print out what iteration the program is on.

To test SLAM, simply put the fileNames into the testSLAM.py file and then run the script.

Texture Mapping:

All the texture mapping is happening in the file textureMap.py. To test, run textTextureMap.py. Remember that you
have to run SLAM before textureMap works (because running SLAM saves a map and poses pickle file that textureMap uses!
I was very close to being done -- the only thing I was not able to figure
out was how to actually paint the pixels in space since I've never used ROS.

I've also included files that I used at the beginning before integrating into SLAM.py.
* createMap.py that uses the odometry and dead reckoning to create the map
* deadReckoningOnly.py that only does dead reckoning on raw odometry to test

About

Simultaneous localization and planning for biped robot and texture mapping. Uses LIDAR scans; IMU roll, pitch, yaw data; gyro; and Kinect for RGB-Depth images for texture map

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages