SLAM for hobbyist robots - it's time.

Translate This Thread From English to

Threaded View


    Hobbyist robots are still too dumb.  We're still seeing battery-motor-wheels,
maybe with a few sonars.  I had one of those 25 years ago.  CPUs have advanced
only from the Basic Stamp to the Atmel AVR, often in Arduno cult form.
This is too lame for 2010.

    A logical next step is to get visual Simultaneous Location and Mapping
("SLAM") onto hobbyist robots.  Then they know where they are and what
the environment is like.  A cell phone with a camera has enough CPU
power for this.  The published papers are out there.  Willow Robotics
gives out some SLAM code.

    Anybody doing this?

                        John Nagle

Re: SLAM for hobbyist robots - it's time.



On 02/13/2010 01:08 PM, John Nagle wrote:

As I understand it, the SLAM systems in many commercial mobile robots
aren't overly robust.  Many rely on a 2D or 3D sick laser or the like.
  So its not surprising this hasn't infiltrated hobby systems.

The best resource I know of is
http://openslam.org/
but its been a year or two since I last looked very hard.

- Daniel

Re: SLAM for hobbyist robots - it's time.



John Nagle wrote:

At the last HBRC (Home Brew Robotics Club meeting, somebody
(alas I'm not good at names), showed up with a robot that
was going to do camera vision based SLAM.

One of our members showed up with a pre production version of
the Neato floor cleaning robot, which uses a laser range
finder (not Lidar) to perform SLAM.  The environment at CMU-SV
(Carnegie Mellon Silicon Valley) was pretty hostile, so it
lots of problems with chairs everybody was sitting in.
The chairs have 4 thin chrome plated steel legs, so they
behave like small cylindrical mirrors at visual wave lengths.
The Neato does have a bump sensor, so it did not totally fail.

What is enabling all of this is the deployment of low
cost and low power 32-bit platforms that can be placed
on the robot.  OpenCV (originally from Intel, not maintained
by Willow Garage) is getting a lot of traction these days.

I keep hoping that one of the low cost 32-bit platforms
out there will get some traction like the Arduino did.
32-bit CPU, Linux, Wi-Fi, some USB ports, and some lower
level stuff like Serial, I2C, SPI, some A/DC, should be
less than $50 these days.

-Wayne

Re: SLAM for hobbyist robots - it's time.



waynegramlich wrote:

    The Willow Garage people have cleaned up OpenCV. See
"http://www.willowgarage.com/pages/software/opencv" .  A few years ago,
I tried OpenCV's stereo code, and it was awful.  For example, about 10% of the
time, the camera calibration program would produce total garbage. The
stereo algorithm never worked very well.  The LK tracker was good, though.

    Willow Garage has been doing a lot of work on "astereomatching.cpp".
It's worth looking at that again.

                John Nagle

Re: SLAM for hobbyist robots - it's time.



John Nagle wrote:

I meant to say "now maintained" rather than "not maintained".


We have two or three people in the club having some level of success
with OpenCV these days.


-Wayne

Re: SLAM for hobbyist robots - it's time.




is there any psuedo code showing how SLAM works?  I'd like to code it
in 6502 assembly language


Re: SLAM for hobbyist robots - it's time.




u,mmmm   how about starting this project and revive this group?

maybe we can flood it with REAL hobbyist and professional posts
and ignore the spammers?

Site Timeline