Robots category

Nvidia’s Jetson Xavier is an AI Computer boasting a $10,000 Worth Of Power For Your Machines and Robots

NVIDIA Jetson Xavier is the latest addition to the Jetson platform. It’s an AI computer for autonomous machines, delivering the performance of a GPU workstation in an embedded module for a consumption under 30W. With multiple operating modes at 10W, 15W, and 30W, Jetson Xavier has greater than 10x the energy efficiency and more than 20x the performance of its predecessor, the Jetson TX2.

Nvidia Jetson Xavier Computer On Module
Nvidia Jetson Xavier CoM

Jetson is a product of Nvidia (Nvidia Jetson) and one of the most powerful embedded platforms for computer vision applications and AI on edge. The Jetson platform is a range of computation processor boards which consists of the Jetson TK1, TX1, and TX2. They’re powered by a Nvidia Tegra which utilizes the ARM Central Processing Unit (CPU). Various operating systems can run on them, such as Linux distros and QNX which is a commercial Real-Time Operating System (RTOS) designed primarily for embedded systems. Nvidia is adding now a new more powerful member to the Jetson Platform.

Nvidia is very excited to announce the release of Jetson Xavier, an Artificial Intelligence computer that works with autonomous machines giving off a GPU workstation in an embedded module and now available in a Jetson Xavier Developer Kit $1299 (USD). It has a super high performance of close to 30 trillion operations per second (TOPS).

The Nvidia Jetson Xavier Developer Kit
Jetson Xavier Developer Kit

Jetson Xavier is designed for robots, drones and other autonomous machines that need maximum compute at the edge to run modern AI workloads and solve problems in manufacturing, logistics, retail, service, agriculture and more. Jetson Xavier is also suitable for smart city applications and portable medical devices. Launched at Computex 2018 in Taiwan by Nvidia CEO Jensen Huang, the Nvidia Isaac Platform includes new hardware, software, and a virtual-world robot simulator that makes it easy for developers to create new kinds of robots.

Jensen Huang said at Nvidia’s Monday press conference at Computex in Taiwan,

This is the single longest processor project we have ever done in our company, Xavier has roughly the same processing power as a $10,000 workstation equipped with a graphics processing units. Plus, it’s easy on the power consumption, he added.

Jetson Xavier is capable of more than 30 TOPS (trillion operations per second) for deep learning and computer vision tasks. The 512-core Volta GPU with support for Tensor Cores and mixed-precision compute is capable of up to 10 TFLOPS FP16 and 20 TOPS INT8. Jetson Xavier’s dual NVDLA engines are capable of up to 5 TOPS each. It also has high-performance eight-core ARM64 CPU, a dedicated image processor, a video processor and a vision processor for accelerating computer vision tasks.

It also announced an “Isaac” software development platform for robots and other autonomous machines that run on its Linux-friendly octa-core “Jetson Xavier” module. The NVIDIA Isaac Software Development Kit (SDK) gives you a comprehensive set of frameworks, tools, APIs, and libraries to accelerate development of robotics algorithms and software.

The Isaac robotics software consists of:

  • Isaac SDK — a collection of APIs and tools to develop robotics algorithm software and runtime framework with fully accelerated libraries
  • Isaac IMX — Isaac Intelligent Machine Acceleration applications, a collection of NVIDIA-developed robotics algorithm software
  • Isaac Sim — a highly realistic virtual simulation environment for developers to train autonomous machines and perform hardware-in-the-loop testing with Jetson Xavier

The Jetson Xavier Developer Kit will be available for early access in August and open to the public in October. Developers using a Jetson TX2 or TX1 to develop autonomous machines using the JetPack SDK can sign up to be notified when they can apply for early access by completing a survey. More information may be found in the Xavier product page.

Robby – A Simple and Powerful Robot to Learn Electronics and Programming

Robby Robot

Over the years we have seen a significant interest in people wanting to learn electronics and programming but are mostly handicapped with what they could build. Over time, learning has been proven to be more reliable when learning is more practical, and we can quickly grasp the concept if one is seeing what he or she is building in real-time and promptly learn why it works the way it works.

Lego Education robotics which has been around for a while, has allowed students to become active leaders in their education as they build everything from animals for a robotic zoo to robots that play children’s games. Lego has been tremendous, and it has quite helped students grasped the concept of engineering and programming, but one of the significant drawbacks with Lego is; it has not been fully developed for the makers open source movement and also comes with a high-cost price, unlike some Arduino based development environments.

The Arduino has caused a revolution in bringing artists into the world of robotics. It has spawned numerous offshoots from very small to wearable processors. Building something with Arduino requires some necessary electronic circuity skills and basic programming which sometimes could be intimidating for the complete novice. Robby from Mr. Robotics is a new education robot for anyone interested in learning more about robotics while also learning about robotics and programming. Robby is based on the Arduino ecosystem.

The team from Mr. Robotics based in Lille, France are crowdfunding their new educational robot called Robby, a tool to learn electronics and programming while having fun. The team at Mr. Robotics believe in this technologically advancing world, everyone should have the opportunity to be imaginative and use it for creation and development. That will need to provide the enabling environment for grooming interest in programming while cultivating natural curiosity, Robby could be the tool to bridge those gaps.

“The creativity is the intelligence having fun.”

Albert Einstein

ROBBY robot is entirely hackable and adaptable with Plug & Play modules for any design scenario. So, today you can design to plug in a particular sensor and decide tomorrow you want another sensor in that position. Just unplug and plug back. The robot kit is fully programmable and allows you to add your own modules and sensors as well as choose your own architecture providing an open source scalable system complete with plug and play sensors. The robot kit is ideal for educational applications as well as keen hobbyists and makers.

At the heart of Robby is the ARM Cortex-M4F 32-bit microcontroller running up to 120 Mhz, and comes with three 12V DC precise motors and incremental encoders for direction, position and speed measurement. It includes a 12V extra Lipo 3S battery, Wi-Fi, USB and Bluetooth, buzzer and an open chassis for adding modules, sensors, components, and breadboard. Robby can be programmed with Blocky (graphical drag and drop block like programming) and with the Arduino IDE.

The Robby Robot is available to back via Kickstarter with pledges starting from €179 for the starter kit, €199 for the Explorer Kit, and €289 for the Creator kit. Mr. Robotics is offering the option of personalized kits costing up to €550 and some other customized packages. If Robby is successfully funded, worldwide shipping is expected to take place during August 2018.

More information about Robby can be found on their website here and their Kickstarter campaign.

Pulurobots

Pulurobot – An Open Source Heavy Load Bearing Application Robot Powered by the Raspberry Pi

If you have seen the starship delivery robots by Starship Technologies, you will know how cool delivery robot can be. Pulurobotics have released a set of low-cost opensource robots that are capable of carrying heavy loads and can be reconfigured to do several tasks.

Pulurobots
Pulurobots

Application robots are robots that can be configured to do several tasks. The Finish based company Pulurobotics have launched the Pulu set of robots called Pulurobots. Just like the way we have the Starship robot and other delivery robot, Pulurobots are low cost (low cost as compared to other robots), load bearing (can carry a payload of over 100kg), and are autonomous robots. Pulurobot can be used as – a delivery boy, a recycle bin, a nightguard, telepresence, shopping carrier, and many more.

The Affordable autonomous open source mobile robot is set to be published at Fosdem 2018, at the ULB Solbosch Campus in Belgium on Sunday 4th February 2018. At the heart of pulurobots is the Raspberry Pi, it needs one Raspberry Pi for navigation and communication with RobotBoard but can feed up to five Raspberries if you need more power or multiple Operating Systems to your application. The robot does Simultaneous Localization and Mapping (SLAM), charges automatically and fulfills the definition of an autonomous mobile robot.

Pulurobot was built from the ground up and doesn’t use ROS (Robots Operating System), even though it is compatible with it. Pulurobot comes in three models:

  • Pulurobot S
  • Pulurobot M
  • Pulurobot L

The Pulurobot S is the smallest version of the robot family with a footprint of about 400 x 300mm, Pulurobot S is capable of carrying over 50Kg of load, tested with 58Kg. Based on the same software and controller board that powers the other robots, Pulurobot S is ideal for applications that require small spaces or offices and a perfect fit for homes.

pulurobots parts
pulurobots parts

Pulurobot M is a medium size agile robot and comes in size of 650mm x 470mm with height 230mm and 304mm from the ground. It is powered by 2 pcs of 300W 24V BLDC wheel hub motor, uses LIDAR for navigating and mapping, 4 x 3D TOF (Timer of Flight) cameras and sonar sensors for obstacles. Pulurobot M is capable of carrying over 90 Kg of load, tested with about 118Kg and found no mechanical problems. It is meant to be an application platform. If you need more batteries for your application, you can stack it onto the robot. Inside the robot is a space for 240Wh 18650 battery array, but can easily accommodate around 1KWh on the chassis.

Pulurobots Sonar Sensors and Controller Board
Pulurobots Sonar Sensors and Controller Board

The following are some specification of the Pulurobot M:

  • Controller board
    • MCU – STM32 microcontroller for sensor management & low-level navigation
    • SBC – Slot for Raspberry Pi 2 or 3 for running mapping (SLAM)
    • Connectivity – WiFi and/or 3G/4G
    • Sensor –  MEMS gyroscope, accelerometer, compass
    • Motor controllers –   4pcs BLDC motor controllers, 700W peak, to support four-wheel drive computation
    • Power Supply – 5V/10A
    • Charger – 100W Lithium-ion charger
  • Vision
    • 2D 360 degree LIDAR
    •  Low-cost off-the-shelf 3D Time-of-Flight camera (SoftKinetic DepthSense) for mapping close obstacles
  • Chassis
    • Riveted, laser-cut aluminum chassis
    • Robust suspension: always four wheels on the ground
    • Two-wheel drive, BLDC hub motors (similar to hoverboards)
    • Supports at 90kg when moving, mechanical structure can withstand a lot more 
  • Battery – 18650-based lithium ion battery
  • Charging –  Can find and mount to its charger automatically

Pulurobot L is the largest of all the Pulurobot series and is expected to carry around 300Kg load. Pulurbot is currently not yet available, still on the drawing board. Pulurobot L will find applications in industries.

While most of the robots are still under development and labeled to be open source, they haven’t yet released their SW-HW design to the public domain yet. It is quite possible that their design could be available after the publication on 4th of February.  The Pulu S is available and will be available for pre-order for 999.00 EUR only during the Fosdem event, the Pulu M is available for purchase at about 3000 EUR, with delivery taking about 2 months.

Pulurobots could be a game changer in the robotics industries and could help foster more innovation, with the hope of bringing down the cost of building small but yet powerful robots in the future.

Researcher Create More Lifelike Soft Robots That Can Mimic Biological Muscle

A group of researchers from the University of Colorado in Boulder (US) is working on the next generation of robots. Instead of the metallic droids concept, these robots are made from soft materials that are more similar to biological systems. Such soft robots hold a huge potential for future applications. They can adjust to dynamic environments and also suitable for close human interaction. Christoph Keplinger from the University of Colorado said,

We draw our inspiration from the astonishing capabilities of biological muscle,

The soft devices, including the muscle actuator, can perform a variety of tasks
The soft robots, including the muscle actuator, can perform a variety of tasks

The newly developed class of soft, electrically activated devices are capable of simulating the expansion and contraction of actual muscles. These devices can be constructed from a wide range of low-cost materials. They are able to self-sense their movements and self-heal from electrical damage.

They developed hydraulically amplified self-healing electrostatic (HASEL) actuators which eliminate the bulky, rigid pistons, valves, pumps and motors of conventional robots. The soft structures of HASEL react to applied voltage with a wide range of movement. According to the study published in the journal Science Robotics on January 5, these flexible robots can perform a variety of tasks. They can handle delicate objects like raspberry or raw egg, as well as lift heavy objects. Keplinger said,

HASEL actuators synergize the strengths of soft fluidic and soft electrostatic actuators, and thus combine versatility and performance like no other artificial muscle before,

He also added,

Just like a biological muscle, HASEL actuators can reproduce the adaptability of an octopus arm, the speed of a hummingbird and the strength of an elephant.

HASEL actuators can simulate the strength, speed, flexibility, and efficiency of biological muscle which may enable artificial muscles for human-like robots. HASEL can make next generation of prosthetic limbs more cost-effective and reliable. This is an important step forwards for soft robotics.

The team is already working on new HASEL actuators that would work with five times lower voltage levels than those described in the studies. The voltage published in the papers is similar to the low-current shock one might get from static electricity, and it’s not hazardous to humans.

The work of this researchers promises a huge improvement in the world of robotics and prosthetic limbs. Their dream is to create robotics that is lifelike. More information can be found in an article appeared in Science recently.

milliDelta Robot- High speed and Precision in a Compact Design

Delta robots are machines with three arms designed to move at high speeds and perform precise tasks. The three arms are connected to a universal join at the base, and the device uses parallelograms that restrict the movement avoiding rotation. As a result, they can move in x, y, and z plane and have high acceleration because it’s made of a light material. They gained popularity in factories for assembly and packaging, so modern devices have been designed to move in more degrees of freedom at accelerations as high as 100 g picking up to 300 items per minute.

The milliDelta robot designed by Harvard’s Wyss Institute measures 15 mm x 15 mm x 20 mm which makes it lighter. As it weights less, the force needed to move it is smaller causing a huge increase in speed. The device uses piezoelectric actuators that allow the milliDelta to move at up to 75 Hz, and the precision is down to 5 micrometers. The developing team proved that milliDelta can operate in a workspace of about 7 cubic millimeters and has a payload capacity of 3 times its mass which helps optimize spaces in factories where thousands of these devices are used to perform tasks in sequence.

The robot was designed for micro- assembly and microsurgery. Many times, in medical situations speed is a key factor for saving someone´s life, and the milliDelta can achieve speeds that humans cannot. The device is clearly not a replacement for medical professionals, it is a tool to perform faster and more precise procedures. Additionally, the precision could allow for less invasive operations. For electronics manufacturing, the milliDelta is a game changer in time spent a production, and in mistakes made in assembly. This delta robots could be used for 3d printing which for some applications requires micrometer precision, and could reduce printing times significantly.

The device has proven to be 15 to 20 times faster than commercial delta robots, and even though it cannot do any heavy lifting it could revolutionize the industries mentioned before. Delta robots are expanding to new industries which means that we may soon see them performing completely different tasks at different situations while maintaining their characteristics properties such as smooth, precise, and fast movement. Harvard’s delta robot is not currently for sale.

[source]

XMotion All In One Controller for Robotics

If there is a motion, it must have XMotion. Recreating Arduino & interface circuits user focused.

XMotion is Arduino Compatible all in one robot controller. Which designed specially for robotics, IOT and maker projects.

It includes powerful Motor drivers, switching mode regulator, interface circuits and more. With protected features, it is all in one board for lots of different type robot projects.

But not only this. Also we added some supporting materials, like starter codes, libraries. If you want to do line follower, mini-sumo or any basic robot we have ready-made codes for beginners.

XMotion All In One Controller for Robotics – [Link]

RoboBee – A Flying Microbot That Can Perform Search And Rescue Missions

Inspired by the biology of a bee, researchers at the Wyss Institute developed RoboBees, man-made microbots that could perform endless roles in agriculture or disaster relief. A RoboBee is about half the size of a paper clip, weighs less than one-tenth of a gram, and flies using materials that contract when an electric pulse is applied. Now, they progressed even further and designed a hybrid RoboBee that can fly, dive into water, swim, propel itself back out of the water, and safely land.

New, hybrid RoboBee can fly, dive into water, swim, propel itself back out of water, and safely land.
New, hybrid RoboBee can fly, dive into water, swim, propel itself back out of the water, and safely land.

New floating devices allow this multipurpose air-water microrobot to stabilize on the water’s surface before an internal combustion system ignites to propel it back into the air. This latest-generation RoboBee is 1000 times lighter than any previous aerial-to-aquatic robot. This can be used for numerous applications, from search-and-rescue operations to environmental monitoring and biological studies. Yufeng Chen, Ph.D. and a Postdoctoral Fellow at the Wyss Institute, said:

This is the first microrobot capable of repeatedly moving in and through complex environments

The researchers have faced numerous challenges to design a millimeter-sized robot that moves in and out of the water. The robot’s wing flapping speed will vary widely between the two mediums as water is 1000 times denser than air. If the flapping frequency is too low, the RoboBee can’t fly. If it’s too high, the wing will snap off in the water. So, it requires a precise balancing as well as a smart multimodal locomotive strategy to overcome this problem.

RoboBee has four buoyant outriggers and a central gas collection chamber. Once the RoboBee swims to the surface, an electrolytic plate in the chamber converts water into oxyhydrogen, a highly combustible gas fuel. The gas increases the robot’s buoyancy and pushes the wings out of the water. The outriggers stabilize the RoboBee on the water’s surface. Elizabeth Farrell Helbling, a graduate student in the Microrobotics Lab, said:

Because the RoboBee has a limited payload capacity, it cannot carry its own fuel, so we had to come up with a creative solution to exploit resources from the environment.

The research team hopes that in future research the RoboBee can fly immediately upon propulsion out of the water, which is currently not possible due to the lack of onboard sensors and limitations in the current motion-tracking system.

vision processing

Role Of Vision Processing With Artificial Neural Networks In Autonomous Driving

In next 10 years, the automotive industry will bring more change than we have seen in the last 50, due to technological advancement. One of the largest changes will be the move to autonomous vehicles, usually known as the self-driving car. Scientists from many universities are striving to implement vision processing with the artificial neural network to provide driver assistance in self-driving cars.

vision processing
Vision processing using convolutional artificial neural networks

Vision processing, as well as artificial neural networks, have been around for many years. Convolutional artificial neural networks (CNN) are sets of algorithms that extract meaningful information from sensor input. CNN’s are very computationally efficient at analyzing a scene. They are also able to identify objects as cars, people, animals, road signs, road junctions, road marking etc. enabling them to determine the relevant reality of the scene. As this system runs in real-time, the decision can be made as soon as the sensing part is complete.

One of the major steps in visual environment understanding for automotive applications is key points tracking and estimating ego-motion and environment structure subsequently from the trajectories of these key points. A propagation based tracking (PBT) method is popularly used to obtain the 2D trajectories from a sequence of images in a monocular camera setup.

The inputs from one or all of the sensors like LIDAR, RADAR, camera, IR, etc. are evaluated and decisions are taken accordingly. For example, if a car in the front suddenly brakes, the onboard computer would instantly verify the distance and calculate the speed with help of the existing sensors. Then it would apply the brakes faster than any human would be able to do. This method helps to prevent an accident with 90% efficiency.

The use of vision processing with CNN is rapidly increasing in automotive applications to enable camera-based autonomous driving. This technology sets a new driving standard. With this technology in our hand, fewer accidents, fewer fatalities, and less pollution are experienced. Vision processing in autonomous driving also enables efficient journeys, reduced crowding, car sharing, and packing cars in more tightly via vehicle to vehicle communication.

Turtle Rover – World’s First Rover for Earth Exploration

A travel companion and a rover that can explore the entire planet with you

Society has a growing interest in space-related projects. The space industry is quickly beginning to grow and private companies are also entering the market, however it is still very difficult to send their own technology into space.

That said, we use electronic devices everyday; needless to say, they have become an integral part of our lives. Experts agree that we educate too few programmers. We also spend less and less time outdoors.We want to explore other celestial bodies while we still do not know our own planet.

Turtle is a four-wheeled mobile robot that will quickly become your best companion in discovering our planet. With a robotic arm, a waterproof case, the capability to take pictures and stream live video, along with the option to add your own software and hardware – all make Turtle a universal tool for both everyday walks and long hikes.

In August 2017 they plan to release Turtle for sale using the international crowdfunding platform – kickstarter.com. Their primary goal to start a production starts at 100,000 USD. During the campaign they plan to sell seventy up to three hundred rovers.

Update 24/08/2017: The campaign is live on kickstarter.com

Turtle Rover – World’s First Rover for Earth Exploration – [Link]

Romeo BLE

Romeo BLE – An Arduino Based Powerful Robot Control Board With Bluetooth 4.0

Romeo BLE is an all-in-one Arduino based control board specially designed for robotics applications from DFRobot. This platform is open source and it’s powered by thousands of publicly available open-sourced codes. Romeo BLE can easily be expanded using Arduino shields. The most important feature—Bluetooth 4.0 wireless communication, allows the board to receive commands via Bluetooth. So, users can now use their smartphone, tablet, or computer to interact with the control board.

Control Robot From Smartphones by Bluetooth 4.0
Control Robot From Smartphones by Bluetooth 4.0

Even the codes can be uploaded over Bluetooth a USB Bluno Link adapter, without requiring any wired USB connection between the board and a PC. This is a great advantage for mobile applications where codes are debugged and uploaded frequently.

The Romeo BLE also includes two integrated two-channel DC motor drivers and wireless sockets, which makes project development more hassle-free. One can start the project immediately without needing an additional motor driver circuitry. The motor driving section also supports extra servos which need more current.

There are two ways to power the Romeo BLE board. But, the polarity must be correct. Otherwise, the board may get permanently damaged as there exists no reverse polarity protection. The two powering methods are:

  • Power from USB: Plug in the USB cable to the Romeo controller from a power source (i.e. wall jack or computer). If the input voltage and current are sufficient, the Romeo BLE board should turn on and a LED should light up. While powered from USB, do NOT connect anything else like motor, servo etc. except LED. Because the USB can only provide 500mA current which is certainly not enough for driving loads like motors.
  • Power from External Power Supply: Connect the ground wire from your supply to the screw terminal labeled “GND” on Romeo board, and then connect the positive wire from your supply to the screw terminal labeled “VIN”. The maximum acceptable input voltage is 23 volts. Do not exceed this value anyway.
Romeo BLE Board Pin Diagram
Romeo BLE Board Pin Diagram

Specifications:

  • Microcontroller: ATmega328P
  • Bootloader: Arduino UNO
  • Onboard BLE chip: TI CC2540
  • 14 Digital I/O ports
  • 6 PWM Outputs (Pin11, Pin10, Pin9, Pin6, Pin5, Pin3)
  • 8 10-bit analog input ports
  • 3 I2Cs
  • 5 Buttons
  • Power Supply Port: USB or DC2.1
  • External Power Supply Range: 5-23V
  • DC output: 5V/3.3V
  • Size: 94mm x 80mm

Features:

  • Auto sensing/switching external power input
  • Transmission range: 70m in free space
  • Support Bluetooth remote update the Arduino program
  • Support Bluetooth HID
  • Support iBeacons
  • Support AT command to config the BLE
  • Support Transparent communication through Serial
  • Support the master-slave machine switch
  • Support USB update BLE chip program
  • Support Male and Female Pin Header
  • Two-way H-bridge motor Driver with 2A maximum current
  • Integrated sockets for APC220 RF Module

You can program Romeo BLE using Arduino IDE version 1.8.1 or above. Select Arduino UNO from Tools –> Boards in the IDE. Go to arduino.en.cc to download the latest version of Arduino IDE. Read the Romeo BLE wiki to learn more.