This little gem came to me courtesy of my friend Greg Baker, who is a lecturer in Computer Science at Simon Fraser University. Thanks Greg! This one was too cool to pass up.

Gåågle - It’s not as weird to pronounce as you’d think. It’s actually pronounced like Google and you’ll begin to see why soon enough. Gåågle Bot is a modified remote-control Roomba that bears a webcam, fueled by real-time AJAX calls that zips around taking pictures and indexing the real world as it sees it. Vacuum, index. I love efficiency!

The name GåågleBot is a play on the words gÃ¥ and google bot. The Swedish word for go is gåå. Googlebot, is the name of Google’s web indexer. If you don’t know what Google is, you are either lying or out of luck. Hence GåågleBot is a “going” indexer, indexing the real world around us while vacuuming your home at the same time! Can’t find that library book that is due tomorrow? Relax, just Gåågle it!

Excited about this bot? Head over here and give it a try. There is also a pretty nifty video as well showing the bot in action. The main site has all of the components listed, the source code, and other tidbits to get you started building your own remote-control crawler.

Roborealm has an interesting tutorial on using machine vision for obstacle avoidance in ground-based vehicles. The tutorial shows a series of image processing steps which can be chained together to detect the “highest” point in an image, based on the ground color. Presumably, that highest point is indicative of the best path to take in order to avoid the most obstacles.

The … algorithms will refer to aspects of this images and exploit attributes that are common in obstacle avoidance scenarios. For example, the ground plane assumption states that the robot is placed on a relatively flat ground (i.e. no offroading for these robots!) and that the camera is placed looking relatively straight ahead or slightly down (but not up towards the ceiling).

RoboRealm is a fascinating and powerful tool for exploring machine vision without difficult programming or an in depth knowledge of the field. It is free for personal use and comes with a number of plugins for using it with various robotic kits. If you’re curious about machine vision, it’s worth a look.

Shown below is a video of a robot that uses the perceived vanishing point of an image to navigate through a corridor. The robot, based on an iRobot Create, uses a standard webcam and video processing to locate the vanishing point of what it sees, and navigates towards that point. Such navigation works very well in office-like environments with straight walls, windows, and ceilings. The robot also uses visual clues, like orange traffic cones, to recognize specific locations.

I was responsible for vision-based navigation of the robot within the hallways. I used the vanishing points from the parallel lines present indoors to compute the robot heading. This was then fed into a controller to control the direction of the robot for navigation. The computation was made robust to change in light conditions, false detections, occlusions by a layered filtering approach that included RANSAC and least squares filtering among others.

Such navigation has some very interesting implications for simple navigation through common environments (houses, offices, shopping malls, etc.). Has anyone tried this using RoboRealm? You can read the project report (PDF) here.

[Via Hackzine]

Howard Gordon who runs Surveyor Corporation just sent me details on their latest product, the Surveyor Stereo Vision System, or SVS for short. The system allows you to record high-resolution full-frame video using two video cameras for a complete stereo vision system. Better yet, the whole set-up is 2.5″ x 6.0″ and only weighs 5 oz.

 

The SVS is open source, and it is intended for researchers, educators and developers interested in enabling depth perception in their applications without the need for an array of active sensors (e.g. laser scanners, ultrasonics, infrared, etc).

The SVS uses two beefy Blackfin DSP’s from Analog devices to do video processing, and can also simultaneously control 8 servos and has a built-in dual motor driver capable of supplying up to 1 Amp per motor. Also included is WiFi connectivity via a Lantronix MatchPort.

The firmware for the SVS is GPL Open Source and comes functional with basic image processing features like, “histogram, pixel sampling, mean, frame difference, blob, scan, count, [and] find”. Currently in development are stereo correspondence and image rectification functions.

Surveyor is targeting this device to the educational and hobbiest crowd, and is selling the SVS for a (very) modest $550. It looks like a great new gadget for robot builders to stick on their creations. Toss on some goofy 3D glasses, and that autonomous aerial footage will really come to life!

Update: Howard has mounted the SVS system to a robotic blimp. You can check out some video after the jump.

(more…)

A new Japanese robotics magazine, Robot Life, has polled 500 Japanese females to ask them who was their favorite commercial robot. The grand winner was the PaPeRo robot, pictured at left, built by NEC. Also making the top 10 list (though, at a dismal 10th), is our friend Robonova. Wakamaru and Manoi were also in the list. Judging from the list, it appears that young Japanese females prefer style over substance – any surprises here?

Here’s the complete list:

1. PaPeRo
2. Ifbot
3. Wakamaru
4. Robofie VS-1
5. Nuvo
6. Manoi PF01
7. Vision Nexta
8. KHR-2HV
9. RB 1000
10. Robonova I

I have to say, though, that I’m surprised Plen and Asimo didn’t make it on the list.

From Loving the Machine and Engadget

Related:

• Japanese Company to Rent Hello Kitty Robo and Ifbot
• Chinese Huitong Robot Does Swordplay!
• Wakamaru Is Coming to Live with an Elderly Japanese Near You!
• Robofie Will Give RoboNova a Run For Its Money
  
• World’s First Robot Department Store to Open in Japa
• e-Nuvo, Nuvo for Educators
• Take Servo Magaine’s Readers Survey and Enter to Win A RoboNova
• Kyosho Announces Manoi AT01
  
  

(more…)