[ros-users] Capability of ARM dev board for ROS host

Tonu Samuel tonu at jes.ee
Fri Jan 20 08:40:50 UTC 2012

On 01/14/2012 02:17 AM, Austin Hendrix wrote:
> My personal robot is running the WG navigation stack with a Hokuyo 
> URG-04LX-UG01 on a pandaboard. I'm running significantly reduced 
> settings for update rates, map size and resolution, local and global 
> planners, and it performs moderately well. I don't have a vision 
> system yet, so I don't know how well it will perform with that 
> additional load.

I am running ROS and navigation stack on Pandaboard too (but no laser 
input). Slowest process is move_base which occupies 100% of CPU all 
time. All other nodes are idle. I had no motivation yet but at some 
point I dig into move_base sources and look what I can optimize and 
maybe I just throw some less needed functionality out.

My robot does most of decicions based on vision and I assumed 
transporting just images is something I can avoid. So I took existing 
camera node and injected all neccessary detection code in it. So my code 
publishes just ~10 coordinates for each frame which is piece of cake to 
handle for rest of system.

Whatever is slow for you, try to find exact stack and node and then 
problem becomes much easier.


More information about the ros-users mailing list