Schlagwort-Archive: Code

AI Robot Kit 2023 All-around Upgrades: Elephant Robotics aims at Robotics Education and Research

Veröffentlicht am von
3

In 2021, Elephant Robotics launched the AI Kit. It is a robotic kit that integrates multiple functions including vision, positioning grabbing, and automatic sorting modules. For people who are new in robotics, AI Kit is a preferable tool to learn the knowledge about machine vision and AI knowledge.

With the continuous advancement of technology, Elephant Robotics has upgraded the AI Kit comprehensively, improving the quality of the hardware while optimizing the built-in algorithms and software to make the product more developable and scalable.

Machine vision is a technology that uses machines to replace the human eyes for target object recognition, judgment and measurement. Machine vision simulates human vision function by computer, and the main technology involves target image acquisition technology, image information processing technology, and target object measurement and recognition technology.

A typical machine vision system mainly consists of a vision perception unit, an image information processing and recognition unit, a processing result display unit and a vision system control unit.

Here we introduce what Elephant Robotics achieve in this upgraded AI Kit 2023.

Textbook and tutorials for robotics

To provide comphrehensive support to experimental and practical teaching, Elephant Robotics launches a textbook about machine vision programming and control. The book provides the knowledge about robotic arms, vision sensors, programming languages, etc. It is a perfect solution for K-12 edication, educational institudes, and colleges. With the help of the tutorials and textbooks, students will enjoy robotics through experiential learning with easier operation when using AI Kit 2023. And Elephant Robotics will launch the tutorials about programming the AI Kit 2023 on YouTube and Hackster continuously.

5 built-in mainstream algorithms

AI Kit 2023 uses eye-to-hand mode, it can achieve color localization by OpenCV, and frames out the colored objects, and calculates the spatial coordinate position of the objects relative to the robotic arm by the relevant point position. With the algorithms, the robotic arm on AI Kit 2023 will automatically recognize the color objects and classify to the corresponding bins.

Aruco codes are widely used to increase the amount of information mapped from the two-dimensional world to three-dimensional time. Elephant Robotics has added recognition algorithms to AI Kit 2023 to support the recognition of 4 different codes. It helps users to learn the related recognition algorithms and positioning applications.

Feature point refers to the ability to represent an image or target in an identical or very similar invariant form in other similar images containing the same scene or target. The feature points are determined by examining the differences between the pixel points and the 16 pixel points in the surrounding field, and the detection efficiency is greatly improved by the segmentation test algorithm.

This algorithm of AI Kit 2023 helps users understand the feature points of images, learn image segmentation, and save image features.

You Only Look Once (YOLO) is a very popular model architecture and object detection algorithm. Elephant Robotics builds this algorithm with the latest version in the AI Kit 2023, the YOLOv5. YOLOv5 makes further improvements on the basis of YOLOv4 algorithm, and the detectability including speed and accuracy are further enhanced. With YOLOv5, users can have a deeper understanding of artificial intelligence, such as the concept and function of neural networks and deep learning.

Shape recognition of objects is an important direction of pattern recognition. There are various representations of object shapes in computers. Based on different shapes, various shape recognition methods have been proposed, such as methods based on Fourier descriptors, principal component analysis, and invariance distance. In shape recognition, it is very important to identify the pattern features on which the recognition is based.

Hardware upgrades

In terms of hardware, AI Kit 2023 adds different sizes of parts boxes to assist the robotic arm to better classify objects. Secondly, AI Kit 2023 used the camera with higher accuracy and lightness adjustment to make the robotic arm more efficient in recognition. Elephant Robotics has also upgraded the suction pump installed at the end of the robotic arm, so that it has higher adaptability and stability when working with different robotic arms.

Software updates

Elephant Robotics develops a built-in visualization software and provides customization methods in the AI Kit 2023. In this software, users can directly select the different algorithms to perform different functions and change the coordinates. The visual interface helps users quickly identify, access and manipulate data, and enables interaction and manipulation in a variety of ways. AI Kit 2023 is more user-friendly now, evern beginner who are new in programming or has no knowledge of code can also use it with several clicks.

Also, Elephant Robotics enhances the adaptations of AI Kit 2023 to enable it to be paired with six robotic arms, including the M5Stack and RaspberryPi versions of myCobot 280, myPalletizer 260, and mechArm 270.

Many educational institutions and colleges have already adopted AI Kit 2023 as an educational tool for professional or laboratory use, enabling students to learn to better understand artificial intelligence, robotic programming, and automation. Elephant Robotics is focusing on developing more and better robotics solutions and kits to provide more comprehensive conditions for the technology and education industry and deepen the application of robotics in education and research.

Use Coupon Code „robotsblog“ to get a discount of 8% at https://shop.elephantrobotics.com/

Blaize Delivers First Open and Code-free AI Software Platform Spanning the Entire Edge AI Application Lifecycle

Veröffentlicht am von
Antworten


El DORADO HILLS, CA — December, 2020 — Blaize today fully unveiled the Blaize AI Studio offering, the industry’s first open and code-free software platform to span the complete edge AI operational workflow from idea to development, deployment and management. AI Studio dramatically reduces edge AI application deployment complexity, time, and cost by breaking the barriers within existing application development and machine learning operations (MLOps) infrastructure that hinder edge AI deployments. Eliminating the complexities of integrating disparate tools and workflows, along with the introduction of multiple ease-of-use and intelligence features, AI Studio reduces from months to days the time required to go from models to deployed production applications.



“While AI applications are migrating to the Edge with growth projected to outpace that of the Data Center, Edge AI deployments today are complicated by a lack of tools for application development and MLOps,” says Dinakar Munagala, Co-founder and CEO, Blaize. “AI Studio was born of the insights to this problem gained in our earliest POC edge AI hardware customer engagements, as we recognized the need and opportunity for a new class of AI software platform to address the complete end-to-end edge AI operational workflow.”



“AI Studio is open and highly optimized for the AI development landscape that exists across heterogeneous ecosystems at the edge,” says Dmitry Zakharchenko, VP Research & Development, Blaize. “With the AI automation benefits of a truly modern user experience interface, AI Studio serves the unique needs in customers’ edge use cases for ease of application development, deployment, and management, as well as broad usability by both developers and domain expert non-developers.”



The combination of AI Studio innovations in user interface, use of collaborative Marketplaces, end-to-end application development, and operational management, collectively bridge the operational chasm hindering AI edge ROI. Deployed with the Blaize AI edge computing hardware offerings that address unserved edge hardware needs, AI Studio makes AI more practical and economical for edge use cases where unmet application development and MLOps needs delay the pace of production deployment.



“In our work for clients, which may include developing models for quality inspection within manufacturing, identifying stress markers to improve drug trials or even predicting high resolution depth for autonomous vehicles, it is vital that businesses can build unique AI applications that prove their ideas quickly,” says Tim Ensor, Director of AI, Cambridge Consultants. “AI Studio offers innovators the means to achieve this confidence in rapid timeframes, which is a really exciting prospect.” Cambridge Consultants, part of Capgemini Group, helps the world’s biggest brands and most ambitious businesses innovate in AI, including those within the Blaize ecosystem.

Code-free assistive UI for more users, more productivity
The AI Studio code-free visual interface is intuitive for a broad range of skill levels beyond just AI data scientists, which is a scarce and costly resource for many organizations. “Hey Blaize” summons a contextually intelligent assistant with an expert knowledge-driven recommendation system to guide users through the workflow. This ease of use enables AI edge app development for wider teams from AI developers to system builders to business domain subject matter experts.

Open standards for user flexibility, broader adoption
With AI Studio, users can deploy models with one click to plug into any workflow across multiple open standards including ONNX, OpenVX, containers, Python, or GStreamer. No other solution offers this degree of open standard deployment support, as most are proprietary solutions that lock in users with limited options. Support for these open standards allows AI Studio to deploy to any hardware that fully supports the standards.



Marketplaces collaboration
Marketplace support allows users to discover models, data and complete applications from anywhere – public or private – and collaborate continuously to build and deploy high-quality AI applications.

AI Studio supports open public models, data marketplaces and repositories, and provides connectivity and infrastructure to host private marketplaces. Users can continually scale proven AI edge models and vertical AI solutions to effectively reuse across enterprises, choosing from hundreds of models with drag and drop ease to speed application development



Easy-to-Use application development workflow:
The AI Studio model development workflow allows users to easily train and optimize models for specific datasets and use cases, and deploy quickly into multiple formats and packages. With the click of a button, AI Studio’s unique Transfer Learning feature quickly retrains imported models for the user’s data and use case. Blaize edge-aware optimization tool, NetDeploy, automatically optimizes the models to the user’s specific accuracy and performance needs. With AI Studio, users can easily build and customize complete application flows other than neural networks, such as image signal processing, tracking or sensor fusion functions.



Ground-breaking edge MLOps/DevOps features
As a complete end-to-end platform, AI Studio helps users deploy, manage, monitor and continuously improve their edge AI applications. Built on a cloud-native infrastructure based on microservices, containers and Kubernetes, AI Studio is highly scalable and reliable in production.



Blaize AI Studio Early Adopter Customers Results
In smart retail, smart city and industry 4.0 markets, Blaize customers are realizing new levels of efficiency in AI application development and deployment using AI Studio. Examples include:

– Complete end-to-end AI development cycle reduction from months to days
– Reduction in training compute by as much as 90%

– Edge-aware efficient optimizations and compression of models with a < 3% accuracy drop

– New revolutionary contextual conversational interfaces that eclipse visual UI



Availability
AI Studio is available now to qualified early adopter customers, with general availability in Q1 2021. The AI Studio product offering includes licenses for individual seats, enterprise, and on-premise subscriptions, with product features and services suited to the needs of each license type.



About Blaize


Blaize leads new-generation computing unleashing the potential of AI to enable leaps in the value technology delivers to improve the way we all work and live. Blaize offers transformative computing solutions for AI data collection and processing at the edge of network, with focus on smart vision applications including automobility, retail, security, industrial and metro. Blaize has secured US$87M in equity funding to date from strategic and venture investors DENSO, Daimler, SPARX Group, Magna, Samsung Catalyst Fund, Temasek, GGV Capital, Wavemaker and SGInnovate. With headquarters in El Dorado Hills (CA), Blaize has teams in Campbell (CA), Cary (NC), and subsidiaries in Hyderabad (India), Manila (Philippines), and Leeds and Kings Langley (UK), with 300+ employees worldwide.

Kamibot Programmable Papercraft Robot Launches on Kickstarter

Veröffentlicht am von
Antworten

Daegu, Korea – February 16, 2016 – Kamibot, the first robot that makes learning to code truly fun for kids (and kidults), will launch on Kickstarter on Tuesday, February 16.

Kamibot is a cute, programmable edtech robot, about the size of a coffee mug. It is based around Arduino, so kids can easily program it by using a drag-and-drop programming language like Scratch. The programming skills kids learn with Kamibot are easily transferrable to real-world applications.

“Unless we make programming fun, kids are never going to stick with it,” said Alvin Chae, co-founder and CEO of 3.14, the company that makes Kamibot. “That’s why we put so much effort into the fun elements of Kamibot, creating colorful papercraft skins that let kids dress up Kamibot, and included the ability to control Kamibot with a smartphone or tablet.”

Papercraft Skins

Kami (紙) is the Japanese word for paper, and is at the root of the word origami (折り紙), literally folding paper. The Kamibot team have already created about half a dozen unique papercraft skins that kids can print out, color, and fold to customize Kamibot and give it character. These include The Count, Frankenstein’s monster, a warrior robot, a tank and a missile launcher tank. The company is also working on striking licensing deals for popular cartoon characters.

Hardware

While Kamibot is undeniably fun to play with, it also packs some serious hardware. It’s brain is an Arduino compatible board, based on the open-source standard widely used by the maker community around the world. It also includes front-facing ultrasonic sensors that help it recognize and avoid obstacles and navigate through mazes or around a room. Downward-facing IR sensors allow Kamibot recognize and race along a black line on the floor. DC motors power the wheels, and a servo motor allows the heads of the papercraft characters to rotate from side-to-side. Color changing LEDs brighten up Kamibot and make it even more colorful.

Programming Kamibot

Kids can program Kamibot to follow complex courses and do complex actions, using all of its motors and sensors. One example of how to program Kamibot is a treasure hunt. Kids can set up a table-sized treasure hunt map that includes obstacles like plastic alligators and a treasure chest. Then, using Scratch, kids can program Kamibot to wind its way through the course toward the treasure chest. Several programming project plans, including the treasure hunt, are included with Kamibot. Others will be released on the company’s website in the future. Kamibot can be programmed wirelessly via Bluetooth or while plugged in via micro-USB.

Launching on Kickstarter

Throughout 2015, Kamibot was tested in Korean classrooms and earned high marks both from students aged 10 to 17, and their teachers. Now Kamibot is ready to launch on Kickstarter on Tuesday, February 16 at 7:00 a.m. EST. Super earlybird prices start at $79 plus shipping. Pre-orders close after 30 days and Kamibot will ship to backers in June. For more information, visit Kickstarter and search for Kamibot.