https://community.element14.com/products/arduino/Find articles, links to purchase the latest products and projects using the popular brand Arduino on the element14 Communityen-USTelligent Community 12https://community.element14.com/products/arduino/arduino-projects/b/blog/posts/mearm-rl-pybulletThu, 29 Oct 2026 12:36:00 GMT93d5dcb4-84c2-446f-b2cb-99731719e767:d2d4d00a-05ac-4f02-bcea-3843f6f4c478lucaeffe03A 4DOF Keyestudio KS0198X robotic arm trained in simulation using reinforcement learning to reach a target, and transferred via serial to the physical arm. Task: reach — moving the tip of the arm (tool) towards a red dot generated within the arm's real workspace, using PPO (Proximal Policy Optimization, Stable-Baselines3) on a PyBullet model built from the real URDF/meshes of the mechanism. Devices & Components 1 Arduino Uno Rev3 1 4DOF Robot Arm Kit Mearm_real_env.py Gymnasium environment for the MeArm/Keyestudio KS0198X robotic arm, simulated in PyBullet from the real URDF (URDF and mashes available on GitHub). Neural network (view code on GitHub): An input layer with 17 neurons (one for each observation value: 4 (positions) + 4 (velocities) + 3 (ee_pos) + 3 (target_pos) + 3 (delta_pos)) An output layer with 4 neurons (one for each motor). Serial_bridge.py Sim-to-real bridge: reads a trained policy and sends the corresponding servo angles to the physical Keyestudio arm via serial. Train.py PPO training (with linear reward) of the 'reach' task on the real MeArm model.Run on an M1 for 1M steps across 4 parallel environments (you can use even more steps if necessary for your specific case). PPO takes the data from all 4, averages it, and updates the weights much more stably.To monitor training progress with TensorBoard, open the terminal:tensorboard --logdir ./tb_logs/" Evaluate.py Loads the trained model and shows it in action within the PyBullet GUI. CODE MeArm-RL-PyBullethttps://community.element14.com/products/arduino/arduino-projects/b/blog/posts/mearm-computervisionThu, 29 Oct 2026 12:29:00 GMT93d5dcb4-84c2-446f-b2cb-99731719e767:372259e9-c0cb-476f-9d23-8861d38f64d3lucaeffe03A webcam watches your hands. Python (using mediapipe) tracks the landmarks of both hands in real-time, translates them into angles for the 4 servomotors of the arm, and sends them via serial port to an Arduino which applies them. Devices & Components 1 Arduino Uno Rev3 1 Keyestudio 4DOF Robot Arm Kit Instructions Control.py Left hand: Thumb-index pinch → BASE rotation (pin A1) Right hand: Hand height in the frame → arm extension: moves SHOULDER (pin A0) and ELBOW (pin 6) together in a coordinated way (hand high = arm extended forward, hand low = arm retracted) Thumb-index pinch → GRIPPER control (pin 9) Safety If a hand leaves the frame, its axis remains locked at the last commanded value (no sudden jumps) Spacebar → full pause of all servo motors 'q' → exit CODE MeArm-computer-visionhttps://community.element14.com/products/arduino/f/arduino-forum/57396/ventuno-q--getting-started/238808Wed, 28 Oct 2026 17:59:00 GMT93d5dcb4-84c2-446f-b2cb-99731719e767:d79ad01e-fccb-4621-a268-d341db033fbbveluv01Well, the best place to get started is the official documentation by Arduino! After Qualcomm's acquisition, the documentation got much better and there's always new tutorials updated every now and then for the new hardware. For Uno Q the official docs were quite enough even for advanced use cases too. So just refer the official docs for Ventuno Q too. Here's the getting started guide : https://docs.arduino.cc/tutorials/ventuno-q/first-setup/ And there's a lot of tutorials too , https://docs.arduino.cc/hardware/ventuno-q/#tutorials Or you can even ask your favourite LLM too (do use the max reasoning) , it provides better info than those books on Amazon for Ventuno Q.https://community.element14.com/products/arduino/f/arduino-forum/57396/ventuno-q--getting-started/238806Wed, 28 Oct 2026 17:13:00 GMT93d5dcb4-84c2-446f-b2cb-99731719e767:6a63ddb6-171a-44b9-bd88-494d78088f06SensoredHacker0There is a lot of trash media hitting Amazon. Publishing seems to have gotten much easier? YAY? Advanced topics, on specific hardware is a pretty small market for publishers. So youll find a million books for beginners, a far less for complex tasks. Its all changing rapidly, so by the time a book goes to print, its material is irrelevant. It was like this before AI, and is exacerbated by it. Its an MCU on an embedded Linux. While I can agree that reductionist views omit details, approaching it from that perspective widens the scope of available documentation. OpenCV has some very good documentation to get yourself familiar with Image Processing. https://www.hlevkin.com/hlevkin/45MachineDeepLearning/ML/Learning-OpenCV.pdf core concepts. "TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers" is a good book though not focused on your target hardware. Make Your Own Neural Network by Tariq Rashid is a good book if you're trying to learn about operational principles of AI. Arduino used to have amaxing documentation, and for the old hard ware, it still does. For the since Qualcomm bought Arduino, I haven't seen nearly the same level of excellent documentation, although it may well exist. you might try starting here: https://docs.arduino.cc/tutorials/ventuno-q/npu-guidehttps://community.element14.com/products/arduino/f/arduino-forum/57396/ventuno-q--getting-started/238805Wed, 28 Oct 2026 12:40:00 GMT93d5dcb4-84c2-446f-b2cb-99731719e767:fb06b11b-9ab3-4819-9ac1-02424d0c6007cstantonHey Lokeye , I would also be doubtful of anything on amazon at present unless it was licensed by Arduino. Have you tried the webinar we hosted: Arduino VENTUNO Q: Building Local LLMs and Physical AI at the Edge or the resources listed on: https://community.element14.com/products/roadtest/rt/roadtests/728/test-ai-controlled-robotics-actuation-on-the-arduino-ventuno-qhttps://community.element14.com/products/arduino/f/arduino-forum/57396/ventuno-q--getting-startedWed, 28 Oct 2026 11:38:00 GMT93d5dcb4-84c2-446f-b2cb-99731719e767:f6ee5dee-07e7-4005-a7ee-bda55bbaaeb6LokeyeHi. I managed to get hold of an Arduino Ventuno Q and have the new Arduino usb camera coming soon. I am looking for a book or good learning materials. I am looking to use it for robotics and Edge AI. All the Ventuno Q books on Amazon don’t seem to be very genuine as the image doesn’t show the right board on the covers. can anyone recommend a good place to get started please or any genuine books?https://community.element14.com/products/arduino/arduino-projects/b/blog/posts/mearm-pickplaceWed, 28 Oct 2026 11:10:00 GMT93d5dcb4-84c2-446f-b2cb-99731719e767:82070a2f-f758-46be-abcc-3982aebd8e08lucaeffe03The project involves the development of an autonomous robotic system based on a 4-degree-of-freedom (4DOF) arm. Devices & Components 1 Arduino Uno Rev3 1 Keyestudio 4DOF Robot Arm Kit Project description The project involves the development of an autonomous robotic system based on a 4-degree-of-freedom (4DOF) arm with a parallelogram structure (MeArm). The system is capable of identifying objects (colored balls) on a workspace using a webcam, calculating their real coordinates in millimeters, and commanding the robotic arm to grab and deposit them into a predefined 'drop zone'. The software is written in Python and communicates with a microcontroller (Arduino R3) via Serial or Bluetooth Low Energy (BT-24 module). CALIBRATE_COLOR.PY Opens the webcam with trackbars to find the correct min/max HSV values for YOUR ball's color, under YOUR lighting conditions. Move the trackbars until ONLY the ball appears white in the "Mask" window (everything else black), then copy the values printed in the console into config.COLOR_RANGES. The values will be printed in the console after pressing 'q'. CALIBRATE.PY Camera -> table calibration via 4-point homography. INSTRUCTIONS: Fix the camera above the table, framing the arm's entire workspace (top-down view; it is fine if it is not perfectly perpendicular, the software will adjust it automatically).Fix the camera above the table, framing the arm's entire workspace (top-down view; it is fine if it is not perfectly perpendicular, the software will adjust it automatically).Place 4 markers at 4 points where you know the REAL coordinates in mm relative to the arm's base (measure them with a ruler: x = left/right of the base, y = forward from the base).Place 4 markers at 4 points where you know the REAL coordinates in mm relative to the arm's base (measure them with a ruler: x = left/right of the base, y = forward from the base).Run this script, click the 4 points on the image IN THE SAME ORDER you defined them below in REAL_POINTS_MM, then press 's' to save (for example, I defined them clockwise: top-left -> top-right -> bottom-right -> bottom-left).Run this script, click the 4 points on the image IN THE SAME ORDER you defined them below in REAL_POINTS_MM, then press 's' to save (for example, I defined them clockwise: top-left -> top-right -> bottom-right -> bottom-left). SCAN_BLE.PY Diagnostic script to understand how to communicate with the BT-24 module via BLE. INSTRUCTIONS: Run: python scan_ble.pyRun: python scan_ble.pyIt will show all BLE devices found nearby (name + address). Identify the one for the arm (it is probably named "DX-BT24" or "BT24").It will show all BLE devices found nearby (name + address). Identify the one for the arm (it is probably named "DX-BT24" or "BT24").Run the script again, passing the address as an argument: python scan_ble.py AA:BB:CC:DD:EE:FF (Windows/Linux)python scan_ble.py 44BAD4C8-18F8-FAE0-ED97-FFFC3A69A296 (macOS uses UUID instead of MAC) It will connect and print ALL services and characteristics, along with their respective properties (read/write/notify).Run the script again, passing the address as an argument: python scan_ble.py AA:BB:CC:DD:EE:FF (Windows/Linux)python scan_ble.py 44BAD4C8-18F8-FAE0-ED97-FFFC3A69A296 (macOS uses UUID instead of MAC) It will connect and print ALL services and characteristics, along with their respective properties (read/write/notify).What to look for in the result of step 3:A characteristic with "write" or "write-without-response" properties -> this is the one the PC writes to in order to SEND data to the arm (equivalent to PC TX / module RX).A characteristic with "write" or "write-without-response" properties -> this is the one the PC writes to in order to SEND data to the arm (equivalent to PC TX / module RX).A characteristic with the "notify" property -> this is the one the module uses to NOTIFY data to the PC (equivalent to module TX / PC RX), useful for reading "OK"/"ERR" ACKs.A characteristic with the "notify" property -> this is the one the module uses to NOTIFY data to the PC (equivalent to module TX / PC RX), useful for reading "OK"/"ERR" ACKs.Note down the UUIDs of these two characteristics: you will need them for config.py (BLE_WRITE_CHAR_UUID and BLE_NOTIFY_CHAR_UUID) and to create ble_link.py.Many inexpensive modules of this type use a SINGLE characteristic for both writing and notifying (e.g., a UUID ending in "FFE1"): if you see a single characteristic with BOTH write+notify properties, use it for both directions. MAIN Multithreading + Semicircular Trajectory. The main thread handles smooth 30fps video. The secondary thread moves the arm using predetermined safe angles (you need to upload arduino sketch on the board and decide if communicate via serial or bluetooth in Config.PY). CODE ON MY GITHUB Robot_Pick_Placehttps://community.element14.com/products/arduino/arduino-projects/b/blog/posts/mearm-tictactoeWed, 28 Oct 2026 11:05:00 GMT93d5dcb4-84c2-446f-b2cb-99731719e767:01bbf433-1617-48c7-860b-60cb5bcdd393lucaeffe03An interactive robotic system (MeArm) capable of challenging a human to a game of Tic-Tac-Toe Devices & Components 1 Arduino Uno Rev3 1 Robot Arm Kit TrisVision MeArm Mixed Reality and Computer Vision Introduction The project consists of the development of an interactive robotic system based on a 4 degrees of freedom (4DOF) arm with a parallelogram structure (MeArm). The system is capable of challenging a human to a game of Tic-Tac-Toe, identifying moves (X) on a sheet of paper via a webcam and physically responding on the board (O).The software is written in Python and communicates with a microcontroller via a BT-24 Bluetooth Low Energy module. Software The architecture is modular, separating the vision logic, artificial intelligence, and hardware communication:Vision/Main (`trisvision.py`): Uses OpenCV to track the playing field, recognize symbols (X and O), and render graphics in Mixed Reality.Logic (`tris_logica.py`): Contains the algorithm (Minimax) to calculate the robot's move.Communication (`ble_link.py`, `config.py`): Interface using the `bleak` library for asynchronous sending of commands (servo motor angles) to the Arduino via Bluetooth. Calibration To allow the robot to interact accurately with the real world, several calibration phases were necessary. Spatial Calibration Since the camera frames the table, the image has perspective distortions. The software dynamically searches for the 4 sides of the white paper and applies perspective correction (`warpPerspective`). By pressing the 'B'*key (Memory Lock), the system freezes the transformation matrix, allowing the robot to enter the scene without disrupting the geometric recognition of the board. Color Calibration Target objects were isolated from the environment by adjusting the Min/Max thresholds for Hue (H), Saturation (S), and Value (V). In this case, the color of a yellow circle glued to the gripper was calibrated (`calibra_EE.py`), which is essential for visually tracking the position of the end-effector. Electromechanical Calibration The hardware (SG90 micro-servo motors) has significant mechanical tolerances. Instead of using complex kinematic calculations, the system uses a static mapping (`MAPPA_CASELLE`) where a safe combination of angles (Base, Shoulder, Elbow) has been saved for each of the 9 Tic-Tac-Toe squares. This decouples the mathematical model from the physical problem, offloading hardware imperfections onto a manually tunable configuration file (via `test_ble.py`). CODE ON MY GITHUB MeArm_Tic_Tac_Toehttps://community.element14.com/products/arduino/arduino-projects/m/managed-videos/151963Wed, 28 Oct 2026 10:58:00 GMT93d5dcb4-84c2-446f-b2cb-99731719e767:84ddebb9-5295-454c-b722-d46c7e0b46calucaeffe03https://community.element14.com/products/arduino/arduino-projects/b/blog/posts/4wd-slam-radar-2d-robot-carWed, 28 Oct 2026 10:55:00 GMT93d5dcb4-84c2-446f-b2cb-99731719e767:3efbcde8-eb76-431e-a11a-cf12fcbfe162lucaeffe03An autonomous 4-wheel drive explorer robot based on Arduino UNO R4 WiFi, designed to navigate through paths and mazes while detecting surrounding obstacles. The robot performs 180° radar scans via an ultrasonic sensor mounted on a servo motor and transmits real-time telemetry via Wi-Fi (Simultaneous Localization and Mapping) to an interactive Web dashboard, which reconstructs the 2D vector map of the surrounding walls. 3D Model -> 3D_Viewer community.element14.com/.../car.mp4 Devices & Components 1 Arduino® UNO R4 WiFi 4 Geared Motor 3 IR-Sensors 1 4WD chassis 1 2 x 18650 Battery Holder With DC Jack 1 4 x AA Battery Holder with Jumper Header Wires 1 Driver L298N 1 Sensor Shield V5.0 1 4-channel infrared module 1 Servo SG90 1 HC SR04 Wiring and Hardware Microcontroller : Arduino UNO R4 WiFi + Sensor Shield V5.0 Chassis & Motors: 4WD Chassis with 4 DC TT gear motors (yellow) Motor Driver: H-Bridge module L298N (with jumpers inserted on `ENA` and `ENB` to deliver 100% power) Radar Turret: HC-SR04 ultrasonic sensor mounted on an SG90 micro-servo motor Waypoint Odometry: Module with 3 Infrared (IR) Sensors positioned under the chassis for detecting configurable checkpoints (black tape at fixed intervals on the floor) Separate Dual Power Supply: Logic (Arduino, Wi-Fi, Sensors, Servo): Battery pack with 2 Li-Ion 18650 cells (7.4V – 8.4V) connected to the Arduino R4 Barrel Jack. Power (4 DC Motors): 4x AA battery holder connected to the 12V/VMS and GND terminals of the L298N driver (with shared `GND` reference with the Sensor Shield and the `+5V` line disconnected to isolate the two circuits). Pin Map on Sensor Shield | Component | Module Pin | Arduino Pin (Sensor Shield) | Function | | L298N Driver | `IN1` | Pin 4 | Left Motor Direction 1 | | L298N Driver | `IN2` | Pin 12 | Left Motor Direction 2 | | L298N Driver | `IN3` | Pin 13 | Right Motor Direction 1 | | L298N Driver| `IN4` | Pin 6 | Right Motor Direction 2 | | L298N Driver | `ENA` / `ENB` | *Black Jumpers* | Permanent 100% power enable | | SG90 Servo | VCC/GND/Signal | Column 7 | Radar turret rotation (`5°` – `175°`) | | HC-SR04 | `TRIG` | Pin 8 | Ultrasonic trigger pulse | | HC-SR04 | `ECHO` | Pin 9 | Ultrasonic echo return reading | | IR Sensors | `IR_SX` (`IN1`) | Pin 2 | Left IR Sensor (black tape reading) | | IR Sensors | `IR_CENTRO` (`IN3`) | Pin 10 | Center IR Sensor (black tape reading) | | IR Sensors | `IR_DX` (`IN4`) | Pin 11 | Right IR Sensor (black tape reading) | Instructions for Use Uploading the Arduino Sketch 1 - Open the `4wd.ino` file in the Arduino IDE. 2 - Enter your Wi-Fi network name (`ssid`) and password (`password`) in the first lines of the code. 3 - Connect the Arduino R4 WiFi to your computer via USB-C cable and upload the sketch to the board. Obtaining the IP Address from the Serial Monitor 1 - Once the upload is complete, open the Arduino IDE **Serial Monitor** and set the baud rate to **`115200 baud`**. 2 - Wait a few seconds until the Arduino connects to the Wi-Fi router. 3 - Copy the **local IP address** printed on the screen in the monitor. 4 - Disconnect the USB cable and turn on the batteries (18650 pack on Arduino + 4xAA pack on motors). Opening the HTML Web Interface 1 - Open the `map.html` file directly in your PC/Mac browser. (Note for Safari users on Mac: from the top menu `Develop`, enable "Disable Local File Restrictions" to allow the local page to communicate via HTTP with the robot's IP, or use Google Chrome). 2 - In the top-left bar of the web page, paste the robot's **IP address** into the text box and click **"Connect Wi-Fi"**. Starting and Stopping Exploration * Click the light blue **` ▶ Start`** button in the top bar to command the robot to begin scanning and autonomous path exploration. * Click the red **` ⏹ STOP`** button to instantly interrupt motor movement and pause the robot. Operating Cycle Navigation and Mapping Logic The robot's operating cycle consists of 4 synchronized phases: 1 - **7-Angle Radar Scan:** While stationary, the robot rotates the SG90 servo motor across 7 angles distributed along the entire front arc (`5°`, `35°`, `65°`, `90°`, `115°`, `145°`, `175°`). At each step, it measures the distance in centimeters using the ultrasonic sensor. 2 - **Free Navigation with Ultrasonic Emergency Brake** The robot moves using short timed bursts in free space. During travel, ultra-fast monitoring continuously queries the HC-SR04: if a wall drops below 13 cm, the robot brakes instantly to avoid collisions. 3 - **Anti-Double-Scan Disengagement Maneuver:** If a close front obstacle is detected, the robot reverses by `4.5 cm` (subtracting the displacement from odometry coordinates), inspects the two extremes (`5°` far right and `175°` far left), and rotates toward the freer side. To avoid redrawing the same wall twice by overlapping lines, the software inhibits sending new scans until the robot has completed a new effective forward step. 4 - **Final Target Detection** The IR sensors passively monitor the floor. As soon as they intercept the single end-of-course black tape, the robot stops the motors, notifies completion, and transmits the target signal to the dashboard. **Automatic Trajectory Cleaning (In-browser Ray Casting):** The web dashboard tracks the robot's trail and automatically removes all impact points recorded within a 9 cm radius of the passage, ensuring a central space perfectly clear of phantom points or spurious artifacts, cleanly and continuously highlighting only the outer perimeter walls of the route. `MAP` Packet Format The web dashboard cyclically queries the HTTP endpoint `http:// /map` (equipped with CORS header `Access-Control-Allow-Origin: *`). The robot responds with a formatted string: counter#MAP:posX,posY,thetaAngle|ang1:dist1|ang2:dist2|ang3:dist3|ang4:dist4|ang5:dist5|ang6:dist6|ang7:dist7 Example: 1#MAP:0.0,15.0,90.0|5:14|35:20|65:44|90:57|115:37|145:17|175:160.0, 15.0, 90.0: The robot is located at X = 0.0 cm, Y = 15.0 cm and heading 90°.5:14... 90:57... 175:16: At various servo angles (from right to left), the sonar detected side walls at 14 cm and 16 cm and the free corridor ahead at 57 cm. The HTML interface converts each (servoAngle, distance) pair into global Cartesian coordinates using trigonometry (cos⁡cosand sin⁡sin), drawing green impact points and connecting them with cyan vector segments. CODE ON MY GITHUB 4WD-SLAM-Radar-2D-Robot-Carhttps://community.element14.com/products/arduino/f/arduino-forum/57335/what-is-your-take-on-qualcomm-arduino-becoming-persona-non-grata/238692Mon, 19 Oct 2026 13:23:00 GMT93d5dcb4-84c2-446f-b2cb-99731719e767:2fae55f8-0bab-40c1-8de7-b512b78513bacolporteurI lived through the MySQL assimilation by Oracle. The developers that made the decision to fork it after the Sun Microsystem aquistion were visionaries.https://community.element14.com/products/arduino/f/arduino-forum/57335/what-is-your-take-on-qualcomm-arduino-becoming-persona-non-grata/238684Mon, 19 Oct 2026 06:28:00 GMT93d5dcb4-84c2-446f-b2cb-99731719e767:b639b394-e25e-4645-ac71-3680977237c4WorkshopshedIt was Arduino who really got me back into electronics after a few years break. It was that combination of ease of getting started, good documentation and good enough software along with a massive library of community libraries, tutorials and examples. Having used the Arduino Portenta in its early days, certainly felt the pain of not having those. Both the Portenta and Yun had an internal "bridge" between their two systems but I never felt it worked too well. For example the Yun dumped serial logs onto the bridge during boot. I've also used some of the Qualcomm boards such as the DragonBoard, where the advantage of having a more powerful processor and a Linux O/S gives you access to software that already exists for that platform. In my case image recognition via OpenCV. That was a platform which was a bit more challenging such as having a 1.8v GPIO and 2.0mm spaced sockets. But the documentation and support were good enough for me to complete my project, using an I/O board designed for Raspberry Pi to control the servos. So I don't see a big divide between the two and with Arduino getting into the PLCs a few years back, they were already on a path to expand their user base into industry. I not too sure about the new boards having having had the challenges above. And for most of my projects the low to medium powered microcontrollers are plenty as long as they can do secure networking. So I do plan to keep using Arduino boards but likely the MKR range as I like the form factor.https://community.element14.com/products/arduino/f/arduino-forum/57335/what-is-your-take-on-qualcomm-arduino-becoming-persona-non-grata/238682Sun, 18 Oct 2026 04:53:00 GMT93d5dcb4-84c2-446f-b2cb-99731719e767:33e3c43e-ad63-4209-aa97-047c562a325bJohnsweeneyarduino wont grow much due to their direct competition with $3-8 esp 32 boards that do as much or morehttps://community.element14.com/products/arduino/f/arduino-forum/57335/what-is-your-take-on-qualcomm-arduino-becoming-persona-non-grata/238614Sat, 10 Oct 2026 00:57:00 GMT93d5dcb4-84c2-446f-b2cb-99731719e767:29c60eff-634c-4341-b83c-1b3c2ab39681WestfWMeh. I don't think that Arduino has become "Perona non grata." I'm much more interested in the "bare microcontroller replacement" Arduinos than the "runs an RTOS" or "runs Linux" boards, and the timing of the Q is a bit unforuate (what with RAM price increases and such.) I hope that the"bottom level" boards (that one could build themselves!) remain supported and in-development, but I don't see any signs that this isn't the case. A $25 board that has $5 "clones" or "assemble yourself from parts" as alternatives is more intersting (to me) than "another $80 linux board" or a $300 "supercomputer-class board. Albeit, perhaps not so profitable. :-( (OTOH, it's not Qualcom's forte, and things might go the way of Google's IoT efforts...)