NewsWorld
PredictionsDigestsScorecardTimelinesArticles
NewsWorld
HomePredictionsDigestsScorecardTimelinesArticlesWorldTechnologyPoliticsBusiness
AI-powered predictive news aggregation© 2026 NewsWorld. All rights reserved.
Trending
MilitaryCrisisStrikesIranFebruaryNewsArrestedDiplomaticOscarTrumpDigestTimelineAmbassadorEpsteinWinFundingInfrastructureAdditionalFormerUnitedKingdomPeterMandelsonProbe
MilitaryCrisisStrikesIranFebruaryNewsArrestedDiplomaticOscarTrumpDigestTimelineAmbassadorEpsteinWinFundingInfrastructureAdditionalFormerUnitedKingdomPeterMandelsonProbe
All Articles
Show HN: Sowbot – open-hardware agricultural robot (ROS2, RTK GPS)
Hacker News
Published about 6 hours ago

Show HN: Sowbot – open-hardware agricultural robot (ROS2, RTK GPS)

Hacker News · Feb 23, 2026 · Collected from RSS

Summary

Sowbot is an open-hardware agricultural robot designed to close the "prototype gap" that kills most agri-robotics startups and research projects — the 18+ months spent on drivers, networking, safety watchdogs, and UI before you can even start on the thing you actually care about. The hardware is built around a stackable 10×10cm compute module with two ARM Cortex-A55 SBCs — one for ROS 2 navigation/EKF localisation, one dedicated to vision/YOLO inference — connected via a single ethernet cable. Centimetre-level positioning via dual RTK GNSS, CAN bus for field comms, and real-time motor control via ESP32 running Lizard firmware. Everything — schematics, PCB layouts, firmware — is under open licences. The software stack runs on RoSys/Field Friend (for teams who want fast iteration) or DevKit ROS (for teams already in the ROS ecosystem). The idea is that a lab in one country can reproduce another lab's experiment by sharing a Docker image. Current status: the Open Core brain is largely fabricated, the full-size Sowbot body has a detailed BOM but isn't yet assembled, and we have two smaller dev platforms (Mini and Pico) in various stages of testing. We're a small volunteer team and we're looking for contributors — hardware, ROS, firmware, docs, whatever you can offer. The best place to start is our Discord: https://discord.gg/SvztEBr4KZ — we have a weekly call if you'd prefer to just show up and chat. GitHub: https://github.com/Agroecology-Lab/feldfreund_devkit_ros/tre... Comments URL: https://news.ycombinator.com/item?id=47123894 Points: 20 # Comments: 0

Full Article

About Our mission is to bridge the gap between sustainability and scale by providing researchers and farmers with reproducible, lightweight robotics that reduce labour and environmental impact without proprietary dependencies. The Sowbot Open AgBot ecosystem is designed to bridge the “prototype gap” in agricultural robotics. It provides a Reference Hardware Design that is accessible to startups and is developing a Production-Ready Software Stack that satisfies the rigorous requirements of research. For startups, this eliminates ~18 months of R&D on the “plumbing” (drivers, networking, UI), allowing them to focus on their unique value (e.g., a proprietary seeding algorithm). For researchers, it provides a stable, repeatable environment where experiments can be shared across labs by simply sharing a Docker image. Check the Roadmap on Github Open Core: The robot ‘brain’ Status: Largely fabricated/ constructed, ESP32 carrier needs some work A fully open-hardware robot compute unit built around a stackable 10 cm × 10 cm module standard with two Avaota A1 SIngle Board Computers (SBC) connected via a single ethernet cable. Board A: Control & Safety Board A is the primary controller responsible for the robot’s physical integrity and movement. Core Tasks: ROS 2 navigation stack, topological mapping, and EKF localization. Hardware: Direct serial link to the ESP32 (Lizard firmware) for motor control and safety watchdogs, for deterministic real-time control. Priority: Executes real-time path planning and emergency stop logic. Board B: Perception & AI Board B acts as a dedicated vision processor for compute-heavy tasks. Core Tasks: Camera drivers, image pre-processing, and neural network inference (e.g., YOLO). Output: Processes raw video into lightweight detection coordinates or semantic labels. Priority: High-bandwidth data handling without impacting SBC A’s CPU stability. Native CAN bus support enables robust field-level communication. Dual GNSS RTK receivers provide centimetre-scale positioning for navigation and task execution. All schematics, PCB layouts, and firmware are released under open licences. The system is housed in a rugged, waterproof aluminium enclosure with M12 connectors, designed for long-term outdoor deployment. Photo Component Description Qty Yuzuki Avaota-A1 SBC Octa-core 64‑bit ARM Cortex‑A55 (up to 1.8 GHz), 4 GB RAM, integrated AI accelerator. Open‑hardware platform. 2 ESP32‑S3 Microcontroller Real-time Lizard control node and general‑purpose peripheral I/O on custom open hardware PCB. 1 BNO055 IMU Adafruit 9-DOF Absolute Orientation IMU Fusion Breakout – BNO055 1 CAN Bus Breakout CAN interface breakout for deterministic, vehicle‑grade communication. 1 SparkFun GNSS RTK or alternate Septentrio Mosaic High‑precision GNSS positioning with RTK support. 2 36V → 12V & 5V Power Conversion & Isolation from motor noise Custom‑fabricated power regulation and electrical isolation board. 1 Waterproof Aluminum Enclosure Sealed aluminum enclosure with M12 connectors for rugged deployments. 1 Sowbot: The body Status: Detailed BOM & concept but not yet assembled The Open core module above powers the Open AgBot reference platform. This integrates high-performance motors, precise control, long-lasting batteries suitable for Low temp <0C charging and rugged suspension into a fully modular, open-hardware agricultural robot. Modular chassis and standardised connections enable rapid expansion and reconfiguration, providing full control over electronics, software, and mechanics for a versatile, field-ready system. Photo Component Description Qty Odrive CAN Bus Drivers with (Open hardware version, in development) Later migration to SimpleFOC hardware possible High-performance motor control with real-time CAN communication for precise torque and speed regulation. 2 800W Hub motor 14.5″ Geared hub motors 100N.m with 4096*10 encoder delivering good acceleration and traction. 4 12V 80Ah Sodium-Ion Battery Packs High-capacity energy modules providing long-duration power for fully autonomous operation. 6 5″ Fatbike Suspension Forks Shock-absorbing suspension for smooth navigation across rough terrain and dynamic environments. 4 Modular Chassis Structure Lightweight aluminium tube sections forming a flexible backbone for sensors, processors, and actuators Many Chassis Connectors Aluminium 90° crossover and modular pipe fittings used to join tubing at right angles for structural frames. Many Sowbot Mini (dev platform) Status: Needs assembly and testing A 1/4 scale development platform for testing and validation Dev platform Components Description Quantity Driver Odrive 2 Electric wheel 6.5″ hub with encoder 4 Chassis structure 1515 extrusion many Chassis connections 1515 corner Many Sowbot Pico (dev platform) Status: Requires some Lizard firmware work, but physical platform tested with alternate software Track issue here Software Software stack(s) Lizard The Sowbot Platform leverages Lizard developed by Zauberzeug for real-time robot orchestration, using its framework to manage sensor input, motor control, and navigation. Lizard enables seamless communication between the processor, microcontrollers, and peripherals, coordinating autonomous operations while remaining fully open and customisable. Lizard supports a range of motor drivers RoSys On top of Lizard, developers can use RoSys, an asyncio-based Python framework, to simplify control loops, messaging, and UI, arguably the fastest route to a working robot. The agricultural implementation, Field Friend, built by Zauberzeug on RoSys to coordinate autonomous navigation and field operations. DevKit ROS Our primary development is on DevKit ROS, a full ROS‑based development kit tailored to the Sowbot Platform, based on work by Zauberzeug. DevKit ROS provides standard ROS tooling, sensor drivers, simulation support and community interoperability, making it ideal for teams already invested in the ROS ecosystem or requiring mature libraries for perception and planning. Software Roadmap Check the Roadmap on Github Contributing We welcome contributions! If you’d like to chat join this channel in the Personal robotics Discord Get in touch


Share this story

Read Original at Hacker News

Related Articles

Hacker Newsabout 2 hours ago
Binance Fired Employees Who Found $1.7B in Crypto Was Sent to Iran

Article URL: https://www.nytimes.com/2026/02/23/technology/binance-employees-iran-firings.html Comments URL: https://news.ycombinator.com/item?id=47127396 Points: 40 # Comments: 22

Hacker Newsabout 2 hours ago
A lithium-ion breakthrough that could boost range and lower costs

Article URL: https://www.techradar.com/vehicle-tech/hybrid-electric-vehicles/forget-solid-state-batteries-researchers-have-made-a-lithium-ion-breakthrough-that-could-boost-range-and-drastically-lower-costs Comments URL: https://news.ycombinator.com/item?id=47127133 Points: 8 # Comments: 0

Hacker Newsabout 3 hours ago
Show HN: Shibuya – A High-Performance WAF in Rust with eBPF and ML Engine

Hi HN, I’ve been working on Shibuya, a next-generation Web Application Firewall (WAF) built from the ground up in Rust. I wanted to build a WAF that didn't just rely on legacy regex signatures but could understand intent and perform at line-rate using modern kernel features. What makes Shibuya different: Multi-Layer Pipeline: It integrates a high-performance proxy (built on Pingora) with rate limiting, bot detection, and threat intelligence. eBPF Kernel Filtering: For volumetric attacks, Shibuya can drop malicious packets at the kernel level using XDP before they consume userspace resources. Dual ML Engine: It uses an ONNX-based engine for anomaly detection and a Random Forest classifier to identify specific attack classes like SQLi, XSS, and RCE. API & GraphQL Protection: Includes deep inspection for GraphQL (depth and complexity analysis) and OpenAPI schema validation. WASM Extensibility: You can write and hot-load custom security logic using WebAssembly plugins. Ashigaru Lab: The project includes a deliberately vulnerable lab environment with 6 different services and a "Red Team Bot" to test the WAF against 100+ simulated payloads. The Dashboard: The dashboard is built with SvelteKit and offers real-time monitoring (ECharts), a "Panic Mode" for instant hardening, and a visual editor for the YAML configuration. I'm looking for feedback on the architecture and the performance of the Rust-eBPF integration. Comments URL: https://news.ycombinator.com/item?id=47126656 Points: 6 # Comments: 0

Hacker Newsabout 4 hours ago
Writing code is cheap now

Article URL: https://simonwillison.net/guides/agentic-engineering-patterns/code-is-cheap/ Comments URL: https://news.ycombinator.com/item?id=47125374 Points: 33 # Comments: 15

Hacker Newsabout 4 hours ago
ASML unveils EUV light source advance that could yield 50% more chips by 2030

Article URL: https://www.reuters.com/world/china/asml-unveils-euv-light-source-advance-that-could-yield-50-more-chips-by-2030-2026-02-23/ Comments URL: https://news.ycombinator.com/item?id=47125349 Points: 66 # Comments: 12

Hacker Newsabout 4 hours ago
Half million 'Words with Spaces' missing from dictionaries

Article URL: https://www.linguabase.org/words-with-spaces.html Comments URL: https://news.ycombinator.com/item?id=47125287 Points: 18 # Comments: 5