Hiwonder

【Embodied AI ROS 2 Robotic Arm】ROS 2-powered & Jetson/Raspberry Pi 5 compatible. Packed with a 3D depth camera, AI voice box, and 65 kg·cm magnetic encoder servos to effortlessly deliver motion-sensing interaction, voice control, and intelligent grasping.

【Large AI Models & OpenClaw Agent】Supports online/local multimodal AI model deployment. Deep OpenClaw Agent integration enables remote voice/text interaction, autonomous task decomposition, intelligent decision-making, and complex task execution.

【Integrated Algorithm Framework】Integrates YOLO26, OpenCV, MediaPipe, Gmapping, inverse kinematics, and other algorithms and tools, providing a highly configurable and extensible development environment.

【Visual PC Software】Features professional PC software supporting one-click scene switching and dual-stream real-time video feedback. Easily customize scenes and hardware parameters for smooth, efficient operation.

【Out-of-the-Box Ready & Full-Scale Curriculum】Pre-loaded with Ubuntu 22.04 alongside a complete dev stack of Python, TensorFlow, PyTorch, and ROS for instant deployment. Includes an end-to-end curriculum spanning computer vision, deep learning, NLP, inverse kinematics, large AI models, and VLA imitation learning.

【Embodied AI ROS 2 Robotic Arm】ROS 2-powered & Jetson/Raspberry Pi 5 compatible. Packed with a 3D depth camera, AI voice box, and 65 kg·cm magnetic encoder servos to effortlessly deliver motion-sensing interaction, voice control, and intelligent grasping.

【Sandbox Setup & Flexible Expansion】Compatible with electric sliding rails, conveyors, and mobile chassis, the NexArm ROS simulates smart warehousing, logistics sorting, and automated production lines—delivering a real-world validation environment for embodied AI algorithms.

【Large AI Models & OpenClaw Agent】Supports online/local multimodal AI model deployment. Deep OpenClaw Agent integration enables remote voice/text interaction, autonomous task decomposition, intelligent decision-making, and complex task execution.

【3D Vision & Spatial Grasping】Featuring a 3D depth camera and an all-metal frame, NexArm ROS enables advanced AI applications like tracking, grasping, sorting, and transporting anywhere within 3D space.

【Out-of-the-Box Ready & Full-Scale Curriculum】Pre-loaded with Ubuntu 22.04 alongside a complete dev stack of Python, TensorFlow, PyTorch, and ROS for instant deployment. Includes an end-to-end curriculum spanning computer vision, deep learning, NLP, inverse kinematics, large AI models, and VLA imitation learning.

【Next-Gen Embodied AI Robotic Arm】Built on an ESP32 + AT32 dual-chip architecture, with an industrial-grade all-metal body and advanced inverse kinematics algorithms, NexArm delivers a full-stack solution from low-level hardware to end-to-end large-model validation.

【Compatibility with LeRobot Ecosystem & End-to-End VLA Models】NexArm robotic arm is fully integrated with the LeRobot framework to access community models, datasets, and simulations. Developers can easily train and deploy end-to-end imitation learning algorithms and multimodal models like ACT & VLA.

【65 kg·cm High-Torque Magnetic Encoder Bus Servos】Industrial-grade high-precision magnetic encoder bus servos, combined with trapezoidal acceleration/deceleration and curve-smoothing algorithms, reduce start-stop jitter, enable smooth motion, and deliver ±2 mm repeatability.

【6 TOPS K230 Vision Module & Al Voice Interaction】NexArm robot arm equipped with the K230 Al vision module, with 30+built-in Al vision features including color/objects/gesture recognition and sorting, personalized face recognition, and more. Supports voice control, Al vision & voice interaction, and hand-eye coordinated grasping.

【Open-Source and Multi-Mode Control】Open-source code and schematics, plus PC software, app control, secondary development examples, and structured tutorials, significantly lower the barrier to embodied AI development.

【Modular Dual-Arm Production Line Setup】Simulates automated production lines for comprehensive hands-on training. Fully supports 3D perception, dual-arm coordination, visual interface control, and pick-and-place operations.

【Dual-Arm Collaboration & 3D Vision Perception】Combines a 3D vision dual-arm system with an electric conveyor to seamlessly fuse 3D point cloud recognition, inverse kinematics, and YOLO deep learning. Enables precise 3D spatial positioning, real-time tracking, adaptive grasping, and smart sorting.

【Embodied AI ROS 2 Robotic Arm】Utilizes the 3D vision dual-arm and conveyor setup to execute complex transferring, transporting, and sorting tasks. Replicates industrial multi-robot collaboration as an ideal platform for embodied AI education and automation simulation.

【Large AI Models & OpenClaw Agent】Supports cloud and local deployment of multimodal AI models like Gemini and ChatGPT via the integrated OpenClaw agent. Use natural language or voice commands to automatically decompose tasks and direct collaborative dual-arm execution.

【Out-of-the-Box Ready & Full-Scale Curriculum】Pre-loaded with Ubuntu 22.04, Python, TensorFlow, PyTorch, and ROS for instant deployment. Includes a comprehensive curriculum covering computer vision, deep learning, NLP, inverse kinematics, large AI models, and VLA imitation learning.

【Embodied AI ROS 2 Robotic Arm】ROS 2-powered & Jetson/Raspberry Pi 5 compatible. Packed with a 3D depth camera, AI voice box, and 65 kg·cm magnetic encoder servos to effortlessly deliver motion-sensing interaction, voice control, and intelligent grasping.

【Sandbox Setups & Flexible Expansion】The NexArm ROS robotic arm is compatible with peripherals like electric sliding rails, conveyor belts, and mobile chassis. It simulates smart warehousing, logistics sorting, and automated production lines, providing a real-world validation environment for embodied AI algorithms.

【Large AI Models & OpenClaw Agent】Supports online/local multimodal AI model deployment. Deep OpenClaw Agent integration enables remote voice/text interaction, autonomous task decomposition, intelligent decision-making, and complex task execution.

【3D Vision & Spatial Grasping】Equipped with a 3D depth camera and an all-metal robotic arm, it executes advanced AI tasks like 3D spatial tracking, picking, sorting, and transporting.

【Out-of-the-Box Ready & Full-Scale Curriculum】Pre-loaded with Ubuntu 22.04 alongside a complete dev stack of Python, TensorFlow, PyTorch, and ROS for instant deployment. Includes an end-to-end curriculum spanning computer vision, deep learning, NLP, inverse kinematics, large AI models, and VLA imitation learning.

【Embodied AI ROS 2 Robotic Arm】ROS 2-powered & Jetson/Raspberry Pi 5 compatible. Packed with a 3D depth camera, AI voice box, and 65 kg·cm magnetic encoder servos to effortlessly deliver motion-sensing interaction, voice control, and intelligent grasping.

【All-Terrain Mobile Chassis】Supports Mecanum and tank chassis to effortlessly navigate complex terrains. The trusted platform for robotics competitions, R&D, and scenario testing.

【Large AI Models & OpenClaw Agent】Supports online/local multimodal AI model deployment. Deep OpenClaw Agent integration enables remote voice/text interaction, autonomous task decomposition, intelligent decision-making, and complex task execution.

【3D Vision & Spatial Grasping】Equipped with a 3D depth camera and an all-metal robotic arm, it executes advanced AI tasks like 3D spatial tracking, picking, sorting, and transporting.

【Out-of-the-Box Ready & Full-Scale Curriculum】Pre-loaded with Ubuntu 22.04 alongside a complete dev stack of Python, TensorFlow, PyTorch, and ROS for instant deployment. Includes an end-to-end curriculum spanning computer vision, deep learning, NLP, inverse kinematics, large AI models, and VLA imitation learning.

【Raspberry Pi & ROS1/ROS2 Compatible】 PuppyPi is an AI vision robot dog built for education and development. Powered by a Raspberry Pi 5 and fully compatible with ROS1 and ROS2, it enables efficient AI computing and versatile robotics projects through Python. Complete source code and documentation included to help you build and customize your own intelligent robot dog.

【Multimodal AI & Enhanced Human Robot Interaction】 PuppyPi integrates a multimodal model, featuring ChatGPT at its core for advanced human-robot interaction. Enhanced with AI vision, it delivers improved perception, reasoning, and action, creating a more natural and flexible interaction experience!

【High-Torque Smart Servos & Inverse Kinematics】 PuppyPi is equipped with 8 high-torque stainless steel gear servos, offering faster response times and stable output. The robot's legs use a link structure design combined with inverse kinematics algorithms to enable coordinated multi-joint movement and precise motion control.

【AI Vision Recognition & Tracking】 PuppyPi features a high-definition camera that enables a variety of AI vision capabilities, including color recognition, target tracking, face detection, ball kicking, line following, and MediaPipe gesture control.

【Lidar & Robotic Arm Expansion】 PuppyPi quadruped robot supports TOF Lidar and robotic arm expansion. It can perform 360° environmental scanning, SLAM navigation, and dynamic obstacle avoidance. Additionally, Hiwonder PuppyPi can precisely grasp objects, opening up opportunities for advanced AI applications.

【Raspberry Pi 5 & ROS2 Robot Car】 MentorPi M1 robot, powered by a RPi 5 and compatible with ROS2, is programmed in Python, making it an excellent platform for developing AI robots.

【Built for Performance】 With closed-loop encoder motors, a TOF lidar, a 2DOF camera, and high-torque servos, the MentorPi car ensures optimal performance and efficiency for all your robotics projects.

【Unlock Advanced AI】 Explore a wide range of AI applications with features that include SLAM mapping, path planning, multi-robot coordination, vision recognition, and target tracking.

【Learn Autonomous Driving】 Utilize the YOLOv11 model for training the robot to recognize road signs and traffic lights, helping you explore and develop cutting-edge autonomous driving technologies.

【ROS2 & High-Performance Hardware】 Built on ROS2, ROSOrin Pro is compatible with Jetson and Raspberry Pi 5. Featuring an AI voice interaction module, a 6DOF robotic arm, and other high-performance hardware, it supports motion interaction, voice control, intelligent grasping, and more creative applications.

【AI Large Models and OpenClaw Agent】 Supports multimodal AI large model deployment, including online access and local offline deployment. Deep integration with the OpenClaw agent enables remote voice and text commands, autonomous task breakdown, intelligent decision-making, and complex task execution.

【Mapping, Navigation, and 3D Vision】 Equipped with a TOF LiDAR and a 3D depth camera, ROSOrin Pro supports SLAM mapping, path planning, and dynamic obstacle avoidance, while enabling 3D object recognition, grasping, sorting, transport, and other advanced human-robot collaboration tasks.

【Integrated Algorithm Framework】 Integrates YOLO26, OpenCV, MediaPipe, Gmapping, inverse kinematics, and other algorithms and tools, providing a highly configurable and extensible development environment.

【Comprehensive Development Resources】 Comes with extensive tutorials and development manuals, covering the full learning path from beginner to advanced levels for faster robot development.

【ROS2 & High-Performance Hardware】 ROSOrin runs on ROS2, compatible with Jetson and Raspberry Pi. It features LiDAR, a 3D camera, and a six-microphone array for tasks like mapping and navigation, 3D recognition, and voice interaction.

【Multimodal Large AI Model & OpenClaw】 Multimodal large AI model deployment and deep OpenClaw agent integration unlock advanced embodied intelligence. This enables cross-platform collaboration, proactive responsiveness, and spatial vector memory for advanced robotic applications.

【Versatile Chassis Expansion】 Switches between Mecanum, Ackermann, and differential drive chassis, paired with a swing arm suspension system for stable movement and precise control on complex terrains.

【AI Vision Algorithms】 Equipped with YOLO26, OpenCV, MediaPipe, and KCF algorithms, ROSOrin delivers powerful visual perception for advanced applications like autonomous driving, face recognition, and target tracking.

【Learning Resources】 Includes comprehensive tutorials, source code, and AI project examples from beginner to advanced, everything needed to move from first build to advanced ROS robot applications.

【Driven by Jetson Nano and high-voltage intelligent serial bus servos】 ROSPug is a smart quadruped robot dogdruped robot driven by Jetson Nano and built on the Robot Operating System (ROS). It is equipped with 12 high-voltage strong-magnetic intelligent serial bus servos, delivering high-precision performance, rapid rotation speed, and robust torque.

【AI Vision, Unlimited Creativity】 Hiwonder ROSPug is equipped with an HD wide-angle camera. It utilizes OpenCV library for efficient image processing, enabling a diverse range of AI applications, including target recognition, localization, line following, obstacle avoidance, face detection, ball shooting, color tracking and tag recognition.

【Various Control Methods and Live Camera Feed】 You can conveniently control ROSPug through WonderROS app available for Android and iOS devices, PC software, or a wireless PS2 handle. Additionally, ROSPug provides a FPV experience by transmitting the live camera feed to the app.

【Gait Planning, Free Adjustment】 ROSPug incorporates inverse kinematics algorithm offering precise control over the touch time, lift time, and lifted height of each leg. You can easily adjust these parameters to achieve different gaits, including ripple and trot. Additionally, ROSPug provides detailed analysis of inverse kinematics, along with the source code for the inverse kinematics function.