Skip to content

vanshilshah97/humanoid_particle_filter_SLAM

Repository files navigation

Monte Carlo Localization Based SLAM

The data consists of the lidar scans from a THOR-OP Humanoid Robot. The lidar data is transoformed into the map co-ordinates by applying suitable transformations and the ground plane points are filtered. Suitable number of particles are initialized which indicate the pose of the robot. Based on the paricle filter approach the best particle with maximum correlation is chosen and the log odds of the map is updated.

Maps built for 3 datasets

About

Implementation of particle filter based SLAM from scratch on a humanoid robot

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages