ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | ros @ Robotics Stack Exchange |
1 | initial version |
I think you will find it challenging to implement without any perception of depth. You would have to "fabricate" the environment based on 2D-computervision, providing pointcloud / laserscan to the stack.
The RPi probably lacks the computing power also; but that is an assumption based on experiences working with depth perception - which implies the amount of data published by these devices.
Don't take my word for anything, I'm just a couple of months into ROS myself.