Skip to main content

Particle filter with NXT

My old boss, Dr Gordon Wyeth from the University of Queensland has implemented a 100 point particle filter onboard the NXT.

Basically the particle filter realizes that you won't have perfect odometery readings all the time, and so uses 3 ultrasonic sensors to 'correct' errors and stay on track.



"Localisation is the process of working out where you are, so localisation for a robot is having the robot work out where it is using the readings from its own sensors. Sounds easy, but it can be surprisingly challenging. The big problem stems from the fact that the robot's wheels have to slip to make the robot move (a fact of physics), so careful measurement of the motors' rotation sensors is not going to help you. Fitting streams of range readings from ultrasound or infrared sensors has problems with noise and error, too. So, over the last decade or so, roboticists have pretty well agreed that the best way to localise is to combine the all of robot's sensor readings over time using probability theory. Sounds challenging, but it can be surprisingly easy.

I've been using a probabilistic filter called a particle filter to localise a robot built around the NXT. The other name for this style of probabilistic localisation is Monte-Carlo Localisation, so called because it relies on finding the best odds from a series of seemingly random outcomes. All of the code is written in Robot-C and runs on-board the NXT in real time. This surprised me. Particle filters are supposed to be horribly computationally intensive with lots of floating point math, so surely you can't expect it to run on a LEGO brick ... but run it did."



He gives a great explanation of particle filters along with video of it in operation.


Source code in RobotC is provided for those that want to look under the hood.

--
Damien Kee

Popular posts from this blog

MINDSTORMS Retires!

2023 is the 25th Anniversary of the MINDSTORMS brand. For 25 years, MINDSTORMS has educated and inspired a generation of robot builders, both children and adults. Unfortunately, the LEGO Group decided to end the line on December 2022. Many ROBOTMAK3RS have been passionately involved with the development of MINDSTORMS through the MUP and MCP programs. Even with the newest Robot Inventor line, several ROBOTMAK3RS were invited to submit additional bonus models that were included in the official app. Regardless of the retirement of a major LEGO robotics product line, ROBOTMAK3RS continue to MAKE-SHARE-INSPIRE using all LEGO robotics platforms available to us. Here is the official statement from LEGO. Since its launch in September 1998, LEGO MINDSTORMS has been one of the core ‘Build & Code’ experiences in the company’s portfolio, carrying with it significant brand equity and becoming a stand-out experience for the early days of consumer robotics and leading to current Build & Code

Celebrating 25 Years of MINDSTORMS

In celebration of the 25th Anniversary of MINDSTORMS, we take a trip through history. Please also visit ROBOTMAK3RS Community every week as we highlight different projects all through 2023 in celebration of the anniversary. Some of the early history is based on the content shared by  Coder Shah  in our  MINDSTORMS EV3 Community Group . Some of the text and links may have been edited from his original posts for consistency and clarity.  1984 - Kjeld Kirk Kristiansen watched a TV program called "Talking Turtle," where MIT professor Seymour Papert demonstrated how children could control robot "turtles" using LOGO, a programming language he developed. 1988 - The collaboration between MIT and LEGO resulted in LEGO TC Logo in 1988, which allowed students to control LEGO models using computer commands. The video shows Papert demonstrating TC Logo. 1990 - LEGO TC Logo was hampered since the robots you built had to be tethered to a personal computer. LEGO and MIT

Celebrating MINDSTORMS with a Remix Part 1

In honor of the 25th Anniversary of MINDSTORMS, we asked ROBOTMAK3RS to combine a LEGO set of their choice with a MINDSTORMS set. Here is what these five ROBOTMAK3RS came up with.  MINDSTORMS Chess Assistant by Arvind Seshan Overview: When you are new to chess, it can be a challenge to remember which pieces go where. Now, you can use machine learning and LEGO MINDSTORMS Robot Inventor to build a tool to help you learn where all the chess pieces go on the chess board. Sets used: LEGO® Iconic Chess Set (40174) and MINDSTORMS Robot Inventor (51515) Review: I really like how the chess set base can store all the pieces underneath and that the board neatly splits in half for handy storage. The chess pieces themselves are very sturdy and well built. My only criticism is the building of the box itself. It was quite difficult to see what pieces to use and since the entire box is made mostly of thin plates, it took a lot of time and patience. I would have liked the storage area to be sliding dra