This package contains work completed during my research internship at Indian Institute of Technology, Kanpur.
Tensorflow library was used along with ROS and MoveIt! package to mimic an RRT motion planner using a Deep Recurrent Neural Network.
The input passed to the network consists of the goal, and joint angles(t) and it is trained against labels of joint angles(t+1) with synthetic datasets generated from a script which randomly places feasible goals for a UR5 simulated robot running in the Gazebo simulator using an RRT path planner from the MoveIt! package.
Report: https://drive.google.com/file/d/1Rkf6Qb2YONkkqD4pKJyYoBoICHxpD8P3/view?usp=sharing
-
Notifications
You must be signed in to change notification settings - Fork 0
raoshashank/RNN_for_Motion_Planning
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Motion Planning on ur5 using recurrent neural networks
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published