Posts with «open source» label

XGO Duck: the open source robot duck that walks with neural policies

XGO Duck is an open source, 3D-printable robot duck that Luwu Dynamics built starting from Pollen Robotics’ Microduck. From the original project it keeps the body, the layout of the 15 servos and the joint order, but replaces all of the electronics. In place of the Pollen Robotics board there is an Arduino UNO Q, which runs neural policies for walking, getting up from the ground and picking. So there is no need to wait for a commercial robot: anyone with a 3D printer can build one.

The heart of the system is the Arduino UNO Q itself, which hosts two computers on a single board. On one side there is a host with a Qualcomm processor running Linux, on the other an STM32U585 MCU running Zephyr. This division of tasks is the most interesting architectural choice in the project. The host handles the neural policies, the MCU handles real-time motor control. On top of that, the link between the two is a 2 Mbps Bridge, so the two worlds stay synchronised without Linux ever having to wait on the servo bus.

Two computers, two loops: 50 Hz for the policies and 100 Hz for the bus

The host runs the ONNX policies at 50 Hz on a dedicated thread, with the web UI listening on port 9527. The MCU, on the other hand, runs a 100 Hz bus loop and does not wait for Linux. It publishes a 240-byte duck_state snapshot at 100 Hz; the host filters every snapshot on arrival and the 50 Hz thread reads the latest available one, skipping late cycles. That way the robot does not stall if the host is busy.

The servo bus always addresses all 15 servos in the order ID 10-14, 20-24, 30-34. The order in action 14-D of the policy is instead 10-14, 30-33, 20-24. The servo bus is on Serial1 at 1 Mbps, while the QMI8658 IMU is on Wire at 400 kHz, with I2C address 0x6A then 0x6B. Servo positions are saturated to the encoder range 0-4095, with a raw centre position of 2047.

  • 15 FeeTech 1910 servos on a serial bus
  • Arduino UNO Q with Qualcomm host and STM32U585 MCU
  • QMI8658 IMU on the Wire bus at 400 kHz
  • Bridge host-MCU link at 2 Mbps
  • servo bus on Serial1 at 1 Mbps

The neural policies: observation [1, 61], action [1, 14] and automatic get-up

The policies expect an observation [1, 61] and output an action [1, 14]. There are three: xgoduck_walk.onnx for walking, xgoduck_getup.onnx for getting up from the ground and xgoduck_pick.onnx for the pick, which lasts 4 s. A tilt above 55° for 0.15 s triggers the get-up model, then the action is forced to 0 for 1 s. When the tilt drops below 15° for 1 s, the robot goes back to walking.

The home pose has hip and ankle at ±24°, knee at 0°, hip roll at ±5°, neck and head pitch at 20°, mouth at 0°. The action_scale is 1. The walking commands are vx ±0.4, vy ±0.3 and ωz ±1.0, with a joystick dead zone of 0.1. The four head channels sit within ±1 radian. The mouth is driven from the web UI from 0° to 30°, and in the pick cycle it opens to 30° and closes when φ ≥ 0.4.

Action smoothing uses α = 0.45 on the slices [0:5], [5:10] and [10:14], yaw smoothing uses α = 0.5 and joint speed smoothing uses α = 0.4. The gravity complementary filter uses τ = 0.3 s, with accelerometer correction dropping when the norm deviates from 1 g by more than about 20%. Position control stops if commands are missing for 250 ms or if the IMU is missing for 100 ms; a host feedback older than 150 ms disarms it.

The Zephyr firmware, servo calibration and the web UI on port 9527

The firmware is a CLI app built with Arduino Zephyr core 1.0.0, on top of RouterBridge 0.4.3, RPClite 0.3.1 and MsgPack 0.4.2. A patch to RouterBridge 0.4.3 raises the RPC thread stack from 500 to 4096 bytes, and the serial router is set to 2 Mbps. Calibration and servo setup use a 2 s heartbeat. The temporary gains for the centring movement are KP = 6 and KD = 20, with a temporary KP = 10 for the servo with ID 34. During calibration the gains become KP = 3 and KD = 0, and every servo is commanded to 2047.

The servo setup page starts with default values KP = 5 and KD = 20. Writing the ID unlocks register 0x37 and then writes 0x05; writing KP/KD unlocks 0x37 and stores both bytes at 0x15. The duck_command sent by the host is 80 bytes. Closing the page or leaving it in the background for more than 1 s disables position control, so the web UI is not just a convenience panel.

The Luwu Dynamics repository collects the project code: sketch, configurations, ONNX models and support scripts. Among the tools are tools/prepare-bridge.py, tools/router-2m.sh, tools/reuse-toolchain.py, tools/verify-elf.py and tools/measure.py, which measures for 60 seconds. There are also python/rl_core.py, python/requirements.txt, sketch/sketch.yaml, app.yaml, data/zero_pos.json and sketch/duck_config.h. Anyone who wants to rebuild it will find everything needed to get started there.

The host needs a Linux environment with ONNX Runtime and Python, while the MCU runs on Zephyr. The UNO Q loader error in case of a tail-call is ENOEXEC (−8), a detail familiar to anyone who compiles firmware. The default rate of Bridge.begin() in another app is 115200, so it has to be raised to 2 Mbps to run the bus as needed. If you want to start with the right hardware, an Arduino UNO Q with a complete accessory kit covers the host and MCU side on a single board.

Source: https://github.com/LuwuDynamics/xgoduck_runtime_arduino

Related products

The post XGO Duck: the open source robot duck that walks with neural policies appeared first on Open Electronics.

From open source to real world solutions: How Linux and Arduino bring big ideas to life

Linux mascot Tux the penguin was created by Larry Ewing using GIMP

The idea that changed how we build technology

Happy Linux Day, Arduino Fans!

Since 1991, Linux has helped popularize open-source software. And then Arduino, inspired by that, extended that open source concept to hardware with its own launch in 2005. The open-source movement did not stop at the screen; it also influenced the development of physical computing. As we celebrate Linux Day, we honor the collaborative ethos that helped shape the internet and the Arduino movement. Just as Linux democratized software by opening the kernel, Arduino liberated hardware from corporate labs, proving that when we freely share our blueprints from C++ to circuit schematics, we empower a global community to build the future together.

Linux meets the physical world

Imagine building an autonomous robot where the engineering challenge isn’t just running computer vision, but seamlessly bridging that user-space intelligence with bare-metal physical execution. The Arduino® UNO Q board solves this by unifying a Qualcomm Dragonwing QRB2210 microprocessor running a full Debian Linux environment with an STM32U585 microcontroller for real-time, deterministic hardware control. This dual architecture gives developers the established capabilities of Debian’s package ecosystem and networking stack for AI workloads, while the bare-metal microcontroller supports real-time control of motors, sensors, and actuators, including sub-millisecond operations where supported by the applicable configuration and workload.

This integrated architecture is designed to reduce the friction associated with bridging separate computing and control hardware.By unifying real-time control with Debian’s robust software ecosystem, the UNO Q can help developers focus on building applications across robotics, computer vision, and industrial automation.The platform illustrates how advanced computing and bare-metal execution can be combined in an open, collaborative development environment.

From ideas to real world builds

The real power of open source comes to life in what people can create with it. Across the Arduino community, makers and developers can explore a broad range of possibilities, from desktop companion robots to autonomous systems that tackle everyday problems, and beyond. Whether they’re experimenting with the UNO Q or Arduino® VENTUNO Q board, sharing their ingenuity through competitions and hackathons, or inspiring others with creative builds, these projects turn bold ideas into working solutions. Here are a few builds that caught our attention, built by community members using Arduino hardware and Linux-based capabilities.

Curie: An AI companion for ADHD and cognitive focus grounding

Curie is an open-source desk companion built on UNO Q, intended to interact through audio and vision features to help users begin tasks and maintain focus. Learn more.

Autonomous pantry assistant

An autonomous edge AI assistant that identifies pantry products and reads their labels aloud for people with low vision. Learn more.

A robot arm that sees you

Imagine a robot arm designed to detect configured users and deliver selected objects. The arm runs on Feetech digital servo motors with a Waveshare control board, and a camera on the head handles the recognition. Learn more.

Depth multitool on the VENTUNO Q

One ordinary webcam, a depth model on the VENTUNO Q NPU, and four visualization modes for estimating the distance of objects within the camera’s field of view. Learn more.

Building on open foundations

Many community projects build on open-source software and hardware. Arduino continues to strengthen that foundation with new hardware, software, and tools that give developers more ways to experiment, create, and solve difficult problems. The 2026 Arduino Open Source Report highlights this motion and key contributions from our vibrant, passionate community. Here are just a few of the highlights, reported by Arduino as part of its open-source ecosystem:

  • 6 new open source hardware boards
  • 11 new official libraries
  • Arduino® App Lab for UNO Q

The community led with:

  • 1,218 new libraries, bringing the total to 8,754
  • 6,602 new versions of libraries
  • 420 new open source projects

The next chapter

As AI descends from the cloud to power the next generation of autonomous robots and edge devices, open-source development continues to play an important role in this area. The convergence of Linux, Arduino, and edge intelligence is helping enable new physical-computing applications, and it is the global community that will define what is possible. That is the true spirit of Linux Day: a brilliant, decentralized future we are building together.


Qualcomm branded products are products of Qualcomm Technologies, Inc. and/or its subsidiaries. Arduino, UNO, and VENTUNO are trademarks or registered trademarks of Arduino S.r.l.

The post From open source to real world solutions: How Linux and Arduino bring big ideas to life appeared first on Arduino Blog.

Arduino Blog 23 Oct 20:12

Arduino Zephyr core 1.0.0: the move away from MbedOS is complete

The Arduino core for Zephyr RTOS has reached version 1.0.0. This release marks the completion of the transition away from the old MbedOS-based core. The new core provides a modern and flexible foundation for current and future Arduino boards. It also lets you use Zephyr RTOS features and APIs directly from the Arduino IDE, Arduino CLI and Arduino App Lab tools.

The project is built on a two-component architecture. The core generates a standalone elf file that is loaded dynamically by a precompiled Zephyr firmware called the loader. The loader handles the interaction between sketches and the underlying Zephyr system. After the initial bootloader installation, the loader automates the sketch loading process. Version 0.90.0 made the Zephyr loader installation procedure fully automatic.

The loader and its operating modes

The loader’s behaviour is set through the IDE’s Mode menu. In Standard mode, the loader loads the sketch automatically. In Debug mode, on the other hand, it requires you to type ‘sketch’ in the Zephyr shell. This flexibility makes debugging much easier. The loader design is generic: board-specific changes are made in the DTS overlay or fixup files.

The core is validated with version v0.16.8 of the Zephyr SDK. Development uses the standard tools of the Zephyr ecosystem, such as west and sync-zephyr-artifacts. The core also relies on components such as llext, the dynamic extension mechanism, and zephyr-sketch-tool for compiling sketches. Everything rests on ArduinoCore-API to maintain compatibility with the Arduino ecosystem.

What you need to get started

To try the Zephyr core you need a supported board and an up-to-date development environment. Here are the main steps:

  • Install Arduino IDE 2.x.x or Arduino CLI
  • Add board support through the Board Manager
  • Install the Zephyr core from version 1.0.0
  • Configure the loader mode from the IDE’s Mode menu

Version 1.0.0 of the Zephyr core is a milestone release. The move from MbedOS to Zephyr is complete. The new core offers a more solid foundation for the future of Arduino boards. Among the new features, support for the project’s code repository includes all the loader and core sources. In addition, the new Arduino UNO Q board is among the first devices to benefit from this architecture.

Arduino’s Zephyr core, designed to replace the MbedOS version, has reached release 1.0.0 and now supports the VENTUNO Q.

The Zephyr core represents a paradigm shift for Arduino. It is not just an update: it is an infrastructure built to last. The separation between loader and sketch makes the system safer and easier to update. What’s more, using Zephyr RTOS opens the door to advanced features such as support for numerous protocols and optimised power management. For anyone developing IoT applications, this is a solid foundation to build on.

The transition from MbedOS to Zephyr was not only technical, but also strategic. Zephyr is an open source RTOS with an active community and a regular release cycle. This guarantees long-term support for Arduino boards. In addition, version 1.0.0 of the core is validated with the Zephyr SDK v0.16.8, ensuring stability and compatibility. The future of Arduino boards goes through here.

Source: https://github.com/arduino/ArduinoCore-zephyr

Related products

The post Arduino Zephyr core 1.0.0: the move away from MbedOS is complete appeared first on Open Electronics.

Face-Following Robot Built on Arduino UNO Q and Edge Impulse

A new open-source project demonstrates how to combine computer vision and robotics on a single board. The robot, about the size of a desk, detects a human face through locally executed machine learning and turns toward it in real time, working at roughly 10–15 frames per second. Everything runs on the new Arduino UNO Q, without relying on the cloud.

Dual-processor architecture

The operation leverages the hybrid architecture of the UNO Q, which integrates two distinct units. The Qualcomm MPU microprocessor, running Linux, executes the AI model and the control logic written in Python. The STM32 MCU microcontroller, running Zephyr RTOS, drives the PWM signal of the servomotors with real-time precision.

The two processors communicate via Bridge RPC, a protocol based on MessagePack over an internal serial link, with a round-trip latency of about 8 milliseconds. This way, heavy inference stays separate from the real-time path, keeping motor control deterministic.

Vision, control, and web interface

The face-following robot built on the Arduino UNO Q.

A USB webcam captures video, while a lightweight face-detection model locates the face in the frame. A proportional controller then converts the horizontal position of the face into differential commands for the wheels. The project uses two ready-made App Lab “bricks”: one for camera-based object detection, the other for the web interface.

In particular, the browser-accessible dashboard lets you monitor detections and adjust steering parameters in real time, without recompiling the code. Every change to the sliders takes effect immediately via Socket.IO, making the tuning phase quick.

Technical details and motion safety

The robot uses differential drive with two continuous-rotation servos: a 1500-microsecond pulse corresponds to stop, while lower or higher values determine rotation in either direction. Additionally, the system limits Bridge calls to a maximum of 20 Hz, because sending commands too quickly would block the serial link.

The project therefore includes several protections: a “coasting” mechanism that maintains the last known position when the face disappears for a moment, a watchdog that stops the robot if detections are interrupted, and an emergency stop that ignores rate limiting to halt the motors immediately. Classified as an intermediate-level project, it is fully documented and released under an open-source license.

The post Face-Following Robot Built on Arduino UNO Q and Edge Impulse appeared first on Open Electronics.

Boards Guide 2024: Boards Are Back

From Make: Vol. 87: New evolutions in dev boards make this a metamorphic period for Makers.

The post Boards Guide 2024: Boards Are Back appeared first on Make: DIY Projects and Ideas for Makers.

Boards Guide 2024: Boards Are Back

From Make: Vol. 87: New evolutions in dev boards make this a metamorphic period for Makers.

An Open-Source Ebike Motor Controller

DIY e-bikes are often easy to spot. If they’re not built out of something insane like an old washing machine motor, the more subtle kits that are generally used still stand out when compared to a non-assisted bike. The motors tend to be hub- or mid-drive systems with visible wires leading to a bulky battery, all of which stand out when you know what to look for. To get a stealthy ebike that looks basically the same as a standard bicycle is only possible with proprietary name-brand solutions that don’t lend themselves to owner repair or modification, but this one has at least been adapted for use with an open source motor controller.

The bike in use here is a model called the Curt from Estonian ebike builder Ampler, which is notable in that it looks indistinguishable from a regular bicycle with the exception of the small 36-volt, 350-watt hub motor somewhat hidden in the rear wheel. [BB8] decided based on no reason in particular to replace the proprietary motor controller with one based on VESC, an open-source electric motor controller for all kinds of motors even beyond ebikes. Installed on a tiny Arduino, it fits inside the bike’s downtube to keep the stealthy look and can get the bike comfortably up to around 35 kph. It’s also been programmed to turn on the bike’s lights if the pedals are spun backwards, and this method is also used to change the pedal assist level, meaning less buttons and other user-interface devices on the handlebars.

[BB8] has been working on this for a while, and although the bulk of a working ebike controller is there, it still doesn’t support the torque sensing pedals included with this bike. We’re presuming that this is still a work-in-progress as the Arduino and associated code easily interfaces with all the other sensors available on this bike. Hopefully this open-source motor controller finds its way into other proprietary systems as well, since a lot of these ebikes can turn into massive paperweights if the companies who originally built them go out of business or simply decide to stop supporting older models. Of course, you can avoid this issue entirely by building your own ebike from spare parts.

Thanks to [Arnoud] for the tip!

Robotic Platform Is Open Sourced And User Friendly

Having a 3D printer or a CNC machine available for projects is almost like magic. Designing parts in software and having them appear on the workbench is definitely a luxury. But for a lot of us, these tools aren’t easily available and projects that use them can be out-of-reach. That’s why one of the major design goals of this robotics platform was to use as many off-the-shelf components as possible.

The robot is called the OpenScout and, as its name implies, intends to be a fully open-source robotics platform for a wide range of use cases. It uses readily-available aluminum extrusion as a frame, which bolts together without any other specialized tools like welders. The body of the robot is articulating, helping it navigate uneven terrain outdoors. The specifications also call for using an Arduino to drive the robot, although there is plenty of space in the robot body to house any robotics platform you happen to have on hand.

For anyone looking to get right into the useful work of what robots can do, rather than spending time building up a platform from scratch, this is an excellent project. It’s straightforward and easy to build without many specialized tools. The unique articulating body design should make it effective in plenty of environments. If you do have a 3D printer, though, that opens up a lot of options for robotics platforms.

Open-Source Robotic Arm for All Purposes

A set of helping hands is a nice tool to have around the shop, especially if soldering or gluing small components is a common task. What we all really want, though, is a robotic arm. Sure, it could help us set up glue or solder but it can do virtually any other task it is assigned as well. A general-purpose tool like this might be out of reach of most of us, unless we have a 3D printer to make this open-source robotic arm at home.

The KAUDA Robotic Arm from [Giovanni Lerda] is a five-axis arm with a gripping tool and has a completely open-source set of schematics so it can be printed on any 3D printer. The robot arm uses three stepper motors and two servo motors, and is based on the Arduino MEGA 2560 for control. The electrical schematics are also open-source, so getting this one up and running is just an issue of printing, wiring, and implementing some software. To that end there are software examples available, and they can easily be modified to fit one’s robotic needs.

A project like this could be helpful for any number of other projects, or also just as a lesson in robotics for yourself or even in a classroom, since many schools now have their own 3D printers. With everything being open-source, this is a much simpler endeavor now than other projects we’ve seen that attempted to get robotic arms running again.

December 2019 Certified Open Source Hardware

The Open Source Hardware Association (OSHWA) runs a free program that allows creators to certify that their hardware complies with the community definition of open source hardware.  Whenever you see the certification logo, you know that the certified hardware meets this standard. The certification site includes a full list of […]

Read more on MAKE

The post December 2019 Certified Open Source Hardware appeared first on Make: DIY Projects and Ideas for Makers.