DOFBOT AI Vision Robotic Arm 6 Axis Robot Arm Assembled w/ ROS Without Mainboard For JETSON NANO

DOFBOT AI Vision Robotic Arm 6 Axis Robot Arm Assembled w/ ROS Without Mainboard For JETSON NANO

Tutorial:
Link for http://www.yahboom.net/study/Dofbot-Jetson_nano

Description:
Dofbot Al vision robot arm is controlled by a mainboard for JETSON NANO (optional), for OpenSource CV is the image processing library, the mainstream for Jupyter Lab is the development tool, and for Python3 is the main programming language.

The camera is integrated with the body of the robotic arm, and the visual recognition makes the robotic arm more flexible. It can not only realize color recognition, tracking and grabbing, but also recognize and interact with human body features, and even train garbage classification models for garbage sorting. Through the ROS robot control system, the complex motion control of the 6-DOF serial bus servo is simplified. The official provides a guided quick-start tutorial to help you easily control the Dofbot AI vision robotic arm.

Advantages:
- AI (Artificial Intelligence)
- FPV (First Person View)
- ROS (Robot Operating System)
- Machine Vision
- Cross-Platform Control
- For Python programming
- Six DOF Control
- Smart serial bus servo
- Anodized aluminum alloy
- Mobile tracking
- Garbage sorting
- Hand eye integration

Features:
- DOFBOT AI Vision Robotic Arm: Artificial Intelligence, the unity of hand and eye. Artificial intelligence, eyes follow hands. Movement tracking, visual recognition. Model training, garbage sorting.
- Optional mainbaord for JETSON NANO, powerful AI computing capabilities. For NVIDIA Jetson Nano is a small but powerful computer that allows you to run multiple neural networks, object detection, segmentation and speech processing applications in parallel. It is equipped with a quad-core cortex-A57 processor, 128-core for Maxwell GPU and 4GB LPDDR memory brings enough AI computing power, provides 472GFLOP computing power, and supports a series of popular AI frameworks and algorithms, for TensorFlow, Pytorch, caffe/caffe 2, Keras, MXNET, etc.
- The first-person perspective controls the robotic arm, making visual recognition more flexible. Three-dimensional simulation modeling, complex and powerful algorithm, FPV vision, stronger experience. FPV HD video control.
- Cross-platform interconnection control. Multifunctional mobile phone APP for IOS/Android: Built-in multiple AI gameplays, real-time viewing of robot arm recognition screen, and support gesture interaction, movement tracking, garbage sorting and other gameplays at the same time. PC host computer control: In addition to the FPV camera video screen, the host computer has also added a 3D simulation model of the robotic arm. The 3D model and the entity rotate synchronously, allowing the robotic arm control theory and practice to be combined. USB gamepad remote control: In addition to mobile phone APP and computer control, there is also a USB gamepad to experience the fun of combining multiple degrees of freedom and multiple keys.
- Color recognition interaction. 1) Color recognition and tracking: In addition to standard colors, custom colors can also be extracted for robotic arm color recognition and tracking. 2) You let me catch: Place the wood block in the map recognition area. The robotic arm will automatically distinguish the current color and clip the wood block to the corresponding color area of the map. 3) Color grabbing: Put the wooden block in front of the camera, and after the robotic arm recognizes the color of the wooden block, it clamps the wooden block in the corresponding color area to the middle area. 4) Color interaction: Choose DOFBOT's favorite color, it will follow the target color forward and backward.
- Train garbage sorting. 1. Basic function: There are multiple wooden blocks with garbage patterns in the DOFBOT kit. By loading the garbage classification model, the type of garbage on the wood block can be identified, the garbage name and classification data are returned to the APP, and the robotic arm sorts the "garbage" to the corresponding classification area on the map. 2. Developer function: You can also identify the area by calibrating the map, place multiple "junk" blocks in the identification area for real-time recognition, and continuously sort multiple "junks" to the corresponding classification area on the map.
- Human feature recognition and interaction: DOFBOT can recognize human features such as gestures and faces through the camera screen, and complete interactive actions such as grabbing, recognition and tracking. 1. Gesture interaction: DOFBOT can recognize a variety of gestures and perform corresponding actions for interaction. 2. Gesture grabbing: Recognize digital gestures, stack the corresponding layers, and finally push down the stacked wooden blocks under the "fist" gesture. 3. Face recognition and tracking: Detect whether there is a face in the current picture. After recognizing the face, mark it and follow the movement.
- Robot motion control: 01. Robotic arm custom learning action group: Thanks to the intelligent serial bus servo, DOFBOT can read and record the angle of each rotation after entering the action learning mode to realize learning and repeat the action group. 02. Interesting fixed action groups: 8 kinds of fixed action groups are provided in the APP. You can click the serial number to preview and click to run, and then start to execute. 03. Simultaneous teaching of robotic arms: This game requires two DOFBOT for teaching control. Read the joint angle of servos on the master side of DOFBOT, and transmit it to the slave side in real time, so that the slave can rotate synchronously according to the attitude of the master. 04. 6-DOF inverse kinematics control: decompose the servo motion control of the robot arm with 6-DOF. Calculate the theoretical motion angle of each servo by inputting the target coordinates, and simultaneously control the motion of each servo of DOFBOT in combination with the servo control protocol. 05. ROS operating system: The ROS robot operating system is a collection of tools, libraries and protocols. It aims to simplify the DOFBOT robot platform and build complex and powerful robots.
- Powerful hardware configuration: intelligent serial bus servos, anodized aluminum alloy, intelligent temperature control fan, optional mainboard for JETSON NANO, full-featured expansion board.
- Guided teaching, quick use of APP operation. 1) Scan and match the network: DOFBOT connects to WIFI by scanning the QR code and pairing. 2) Servo calibration: By reading the angle of the servos, the angle calibration of the robotic arm is performed. 3) Color calibration: For beginners and developers, we provide basic color calibration and professional color calibration functions to prevent environmental factors from affecting the robotic arm.
- Multiple remote control methods: APP remote control: for IOS and Android system. Support for PC host computer, Jupyter Lab webpage online programming control, ROS system, PS2 controller.
- Massive learning materials, providing open course source code, AI vision courses, etc.

Specifications:
- Microprocessor: For Quad-core ARM A57 + for 128-core NVIDIA Maxwell
- AI computing power: 472GFLOPs
- Operating system: For Ubuntu 18.04LTS + ROS_Melodic
- Programming language: For Python
- Servo scheme: 15kg*5+6kg*1 serial bus intelligent servo
- Input: wide-angle camera, emergency stop button, network distribution button, reset button, 2*IIC interface, 5V fan interface
- Output: RGB indicator, OLED display, buzzer, 6 bus servo interfaces, 6 PWM servo interfaces
- Power solution: 12V5A power adapter
- Power interface: T plug interface
- Remote control method: mobile phone APP, PC upper computer, for PS2 controller (PC terminal)
- Communication method: WiFi network
- Safety protection: overcurrent protection, reverse connection protection
- Manipulator material: anodized aluminum
- Size after assembly: 303*135*473mmss
- Weight after assembly: 1256g
- Degree of freedom (DOF) of robotic arm: 5 degrees of freedom + gripper
- Effective load: 200g (the weight can be clamped straight out)
- Load: 500g (clamping and handling weight)
- Arm span: 350mm
- Effective grabbing range: radius ≤30cm, the area with the central axis as a semicircle
- Repeat positioning accuracy: ±0.5mm
- Power supply voltage: 100~240V, 50/60Hz
- Camera: 300,000 pixels, 110° wide-angle camera
- Resolution: 480p (640*480)
- Frame rate: 30fps
- Focus mode: manually adjust the focus

Package Included:
- 1 x DOFBOT Robot Arm Assembled
- 1 x Map For Robot Arm
- 1 x USB Game Joystick
- 1 x Power Adapter
- 1 x Expansion Board For Robot Arm
- 1 x 40PIN Cable
- 1 x Micro USB Data Cable
- 6 x Black Ribbons
- 4 x Building Blocks
- 6 x Suction Cups
- 1 x Screwdriver
- 1 x 32G TF Card
- 1 x OLED Display
- 1 x Camera
- 1 x Camera Connection Cable
- 1 x Set of Wireless Network Card
- 2 x Fixing Brackets
- 6 x Bags of Screws, Nuts, Copper Pillars
- 1 x Instructions

Note:
- Other items pictured are not included, for demonstration purposes only. Thank you for your understanding!