Robots Learning To Understand Their Surroundings

November 6, 2020 by Roger Cheng 1 Comment

Today it is pretty easy to build a robot with an onboard camera and have fun manually driving through that first-person view. But builders with dreams of autonomy quickly learn there is a lot of work between camera installation and autonomously executing a “go to chair” command. Fortunately we can draw upon work such as View Parsing Network by [Bowen Pan, Jiankai Sun, et al]

When a camera image comes into a computer, it is merely a large array of numbers representing red, green, and blue color values and our robot has no idea what that image represents. Over the past years, computer vision researchers have found pretty good solutions for problems of image classification (“is there a chair?”) and segmentation (“which pixels correspond to the chair?”) While useful for building an online image search engine, this is not quite enough for robot navigation.

A robot needs to translate those pixel coordinates into real-world layout, and this is the problem View Parsing Network offers to solve. Detailed in Cross-view Semantic Segmentation for Sensing Surroundings (DOI 10.1109/LRA.2020.3004325) the system takes in multiple camera views looking all around the robot. Results of image segmentation are then synthesized into a 2D top-down segmented map of the robot’s surroundings. (“Where is the chair located?”)

The authors documented how to train a view parsing network in a virtual environment, and described the procedure to transfer a trained network to run on a physical robot. Today this process demands a significantly higher skill level than “download Arduino sketch” but we hope such modules will become more plug-and-play in the future for better and smarter robots.

[IROS 2020 Presentation video (duration 10:51) requires free registration, available until at least Nov. 25th 2020. One-minute summary embedded below.]

Continue reading “Robots Learning To Understand Their Surroundings” →

Jetson Emulator Gives Students A Free AI Lesson

October 26, 2020 by Tom Nardi 4 Comments

With the Jetson Nano, NVIDIA has done a fantastic job of bringing GPU-accelerated machine learning to the masses. For less than the cost of a used graphics card, you get a turn-key Linux computer that’s ready and able to handle whatever AI code you throw at it. But if you’re trying to set up a lab for 30 students, the cost of even relatively affordable development boards can really add up.

Which is why [Tea Vui Huang] has developed jetson-emulator. This Python library provides a work-alike environment to NVIDIA’s own “Hello AI World” tutorials designed for the Jetson family of devices, with one big difference: you don’t need the actual hardware. In fact, it doesn’t matter what kind of computer you’ve got; with this library, anything that can run Python 3.7.9 or better can take you through NVIDIA’s getting started tutorial.

So what’s the trick? Well, if you haven’t guessed already, it’s all fake. Obviously it can’t actually run GPU-accelerated code without a GPU, so the library [Tea] has developed simply pretends. It provides virtual images and even “live” camera feeds to which randomly generated objects have been assigned.

The original NVIDIA functions have been rewritten to work with these feeds, so when you call something like net.Classify(img) against one of them you’ll get a report of what faux objects were detected. The output will look just like it would if you were running on a real Jetson, down to providing fictitious dimensions and positions for the bounding boxes.

If you’re a hacker looking to dive into machine learning and computer vision, you’d be better off getting a $59 Jetson Nano and a webcam. But if you’re putting together a workshop that shows a dozen people the basics of NVIDIA’s AI workflow, jetson-emulator will allow everyone in attendance to run code and get results back regardless of what they’ve got under the hood.

NVIDIA Announces $59 Jetson Nano 2GB, A Single Board Computer With Makers In Mind

October 5, 2020 by Tom Nardi 47 Comments

NVIDIA kicked off their line of GPU-accelerated single board computers back in 2014 with the Jetson TK1, a $200 USD development system for those looking to get involved with the burgeoning world of so-called “edge computing”. It was designed to put high performance computing in a small and energy efficient enough package that it could be integrated directly into products, rather than connecting to a data center half-way across the world.

The TK1 was an impressive piece of hardware, but not something the hacker and maker community was necessarily interested in. For one thing, it was fairly expensive. But perhaps more importantly, it was clearly geared more towards industry types than consumers. We did see the occasional project using the TK1 and the subsequent TX1 and TX2 boards, but they were few and far between.

Then came the Jetson Nano. Its 128 core Maxwell CPU still packed plenty of power and was fully compatible with NVIDIA’s CUDA architecture, but its smaller size and $99 price tag made it far more attractive for hobbyists. According to the company’s own figures, the number of active Jetson developers has more than tripled since the Nano’s introduction in March of 2019. With the platform accessible to a larger and more diverse group of users, new and innovative applications for machine learning started pouring in.

Cutting the price of the entry level Jetson hardware in half was clearly a step in the right direction, but NVIDIA wanted to bring even more developers into the fray. So why not see if lightning can strike twice? Today they’ve officially announced that the new Jetson Nano 2GB will go on sale later this month for just $59. Let’s take a close look at this new iteration of the Nano to see what’s changed (and what hasn’t) from last year’s model.

Continue reading “NVIDIA Announces $59 Jetson Nano 2GB, A Single Board Computer With Makers In Mind” →

Making Music With A Go Board Step Sequencer

October 5, 2020 by Adam Zeloof 3 Comments

Ever wonder what your favorite board game sounds like? Neither did we. Thankfully [Sara Adkins] did, and created a step sequencer called Let’s Go that uses the classic board game Go as input.

In the game Go, two players place black and white tokens on a grid, vying for control of the board. As the game progresses, the configuration of game pieces gets more complex and coincidentally begins to resemble Conway’s Game of Life (or a weird QR Code). Sara saw music in the evolving arrangement of circles and transformed the ancient board game into a modern instrument so others could hear it too.

To an observer, [Sara’s] adaptation looks fairly indistinguishable from the version played in China 2,500 years ago — with the exception of an overhead webcam and nearby laptop, of course. The laptop uses OpenCV to digitize the board layout. It feeds that information via Open Sound Control (OSC) into popular music creation software Max MSP (though an open-source version could probably be implemented in Pure Data), where it’s used to control a step sequencer. Each row on the board represents an instrumental voice (melodic for white pieces, percussive for black ones), and each column corresponds to a beat.

Every new game is a new piece of music that starts out simple and gradually increases in complexity. The music evolves with the board, and adds a new dimension for players to interact with the game. If you want to try it out yourself, [Sara] has the project fully documented on her website, and all of the code is available on GitHub. Now we’re just left wondering what other games sound like — [tinkartank] already answered that question for chess, but what about Settlers of Catan?

Continue reading “Making Music With A Go Board Step Sequencer” →

TOBOT Is Your Tic Tac Toe Opponent With A Bad Attitude

September 16, 2020 by Al Williams 4 Comments

[3dprintedlife] is apparently a little bored. Instead of whiling away the time playing tic tac toe, he built an impressive tic tac toe robot named TOBOT. The robot uses a Rasberry Pi Zero and a Feather to control a two-axis robot arm that can draw the board and make moves using a pen. It also uses a simple computer vision system to look at the board to understand your move, and it has a voice too.

The other thing TOBOT has is a bad attitude. The robot wants to win. Badly. Check out the video below and you’ll see what we mean.

Continue reading “TOBOT Is Your Tic Tac Toe Opponent With A Bad Attitude” →

OAK Vision Modules Help You See The Forest And The Trees

August 9, 2020 by Roger Cheng 13 Comments

OpenCV is an open source library of computer vision algorithms, its power and flexibility made many machine vision projects possible. But even with code highly optimized for maximum performance, we always wish for more. Which is why our ears perk up whenever we hear about a hardware accelerated vision module, and the latest buzz is coming out of the OpenCV AI Kit (OAK) Kickstarter campaign.

There are two vision modules launched with this campaign. The OAK-1 with a single color camera for two dimensional vision applications, and the OAK-D which adds stereo cameras for that third dimension. The onboard brain is a Movidius Myriad X processor which, according to team members who have dug through its datasheet, have been massively underutilized in other products. They believe OAK modules will help the chip fulfill its potential for vision applications, delivering high performance while consuming low power in a small form factor. Reading over the spec sheet, we think it’s fair to call these “Ultimate Myriad X Dev Boards” but we must concede “OpenCV AI Kit” sounds better. It does not provide hardware acceleration for the entire OpenCV library (likely an impossible task) but it does cover the highly demanding subset suitable for Myriad X acceleration.

Since the campaign launched a few weeks ago, some additional information have been released to help assure backers that this project has real substance. It turns out OAK is an evolution of a project we’ve covered almost exactly one year ago that became a real product DepthAI, so at least this is not their first rodeo. It is also encouraging that their invitation to the open hardware community has already borne fruit. Check out this thread discussing OAK for robot vision, where a question was met with an honest “we don’t have expertise there” from the OAK team, but then ArduCam pitched in with their camera module experience to help.

We wish them success for their planned December 2020 delivery. They have already far surpassed their funding goals, they’ve shipped hardware before, and we see a good start to a development community. We look forward to the OAK-1 and OAK-D joining the ranks of other hacking friendly vision modules like OpenMV, JeVois, StereoPi, and AIY Vision.

Pinball Machine Needs No Wizard

May 18, 2020 by Kristina Panos 15 Comments

Ever since he was a young boy, [Tyler] has played the silver ball. And like us, he’s had a lifelong fascination with the intricate electromechanical beasts that surround them. In his recently-completed senior year of college, [Tyler] assembled a mechatronics dream team of [Kevin, Cody, and Omar] to help turn those visions into self-playing pinball reality.

You can indeed play the machine manually, and the Arduino Mega will keep track of your score just like a regular cabinet. If you need to scratch an itch, ignore a phone call, or just plain want to watch a pinball machine play itself, it can switch back and forth on the fly. The USB camera mounted over the playfield tracks the ball as it speeds around. Whenever it enters the flipper vectors, the appropriate flipper will engage automatically to bat the ball away.

Our favorite part of this build (aside from the fact that it can play itself) is the pachinko multi-ball feature that manages to squeeze in a second game and a second level. This project is wide open, and even if you’re not interested in replicating it, [Tyler] sprinkled a ton of good info and links to more throughout the build logs. Take a tour after the break while we have it set on free play.

[Tyler]’s machine uses actual pinball machine parts, which could quickly ramp up the cost. If you roll your own targets and get creative with solenoid sourcing, building a pinball machine doesn’t have to be a drain on your wallet.

Continue reading “Pinball Machine Needs No Wizard” →