- AI-Driven and ROS-Compatible: JetArm Pro is a high-performance robotic arm powered by Jetson modules, fully compatible with ROS1/ROS2 and ideal for advanced AI and Python-based development.
- Powerful 3D Vision and Hardware: Features six high-torque smart servos, a 3D depth camera, a 7-inch touchscreen, and a microphone array for precise grasping, tracking, sorting, and voice control.
- Natural Human-Robot Interaction: Combines 3D vision with ChatGPT-driven AI for intuitive, multimodal interaction and embodied intelligence.
- Versatile Multimodal Expansion: Easily integrates with Mecanum wheels, sliding rails, and conveyors for building intelligent transport systems and complex AI automation workflows.
- Cutting-Edge Tech with Full Learning Support: Covers ROS, vision, deep learning, and simulation with comprehensive tutorials, empowering users to master AI-driven robotics step by step.
Product Description
JetArm Pro is an AI-powered multimodal robot designed for ROS-based education. Upgraded from the JetArm robotic arm, it supports modular add-ons like mecanum/tank chassis, sliding rail, and conveyor belt—enabling applications such as intelligent transport, vision line following, and even automated AI sorting systems. With built-in support for multimodal large model and integration with platforms like ChatGPT, JetArm Pro can perceive, plan, and execute complex embodied AI tasks. Hiwonder provides open-source code, learning resources, and hands-on experiments to help users easily build and explore their own AI projects.
1) Depth Vision, 3D Scene Flexible Grabbing
The end of the JetArm Pro robot arm is equipped with a high-performance 3D depth camera, which can realize target recognition, tracking and grabbing. Through RGB+D fusion detection, JetArm Pro can also realize flexible grabbing in 3D scene.
2) All-metal Structure, Bearing Base
The body of the robot arm adopts an all-metal structure, and the surface is anodized, making it exquisite and beautiful. The base uses industrial-grade bearings to meet high-demand grabbing projects.
3) Wrapped Structure Design, Beautiful Wiring
JetArm Pro adopts a wrapped structure design, and the wiring of the servo can be hidden inside the fuselage, making the outside of the fuselage clean and tidy.
4) Circular Microphone Array
JetArm Pro comes with a circular 6-microphone array that delivers excellent noise reduction and clear audio capture. It supports advanced features such as sound source localization, speech recognition, voice announcements, and voice control.
1. Dual-Controller Design for Efficient Collaboration
1) Host Controller
● ROS Controller (JETSON Orin Nano)
● Depth Image Processing
● Human-Machine Voice Interaction
● Advanced Al Algorithms
● Deep Neural Networks
● Al Visual Image Processing
2) Sub Controller
● STM32 Robot Controlier
● Servo Control and Feedback
● Power Status Monitorin
2. Multimodal Expansion
JetArmPro is built on a modular architecture that supports a variety of multimodal extensions, including Mecanum wheel chassis, tank chassis, sliding rail, and conveyor belt. These enhancements enable a wide range of creative applications such as mobile transport, intelligent handling and line following. Additionally, it provides a solid foundation for developing advanced Al scenarios like automated sorting systems.(Compatible with ROS2 only)
1) Mecanum Wheel Chassis Add-on
The Mecanum wheel chassis adopts a pendulum suspension design, ensuring that all four wheels remain in contact with the ground, even on uneven surfaces.This enables JetArm Pro to perform 360-degree omnidirectional movement and in-place rotation, providing flexible and stable mobility across various operating environments.
2) Tank Chassis Add-on
The tracked chassis features high-quality anti-slip tracks, precision encoder motors, and a multi-wheel drive system, allowingJetArm Pro to achieve precise movement and turning in any direction.
3) Sliding Rail Add-on
Driven by a stepper motor, the sliding rail provides up to 500mm of effective travel, greatly expanding the robotic arm's movement range on the desktop. This allows for a broader range of advanced Al-powered creative applications.
4) Conveyor Belt Add-on
Designed for smooth and reliable transport of various objects, the conveyor belt features adjustable speed and direction, making it a perfect fit for creating Al-driven automated handling and logistics solutions.
3. Mobile Chassis Function
JetArm Pro supports both mecanum wheel and tank chassis add-ons, enabling intelligent transport, mobility, and line following capabilities. Its detachable design allows for easy switching between a desktop robotic arm and a mobile robot, adapting seamlessly to different use cases and environments.
1) App Control
The app allows you to receive the FPV live camera feed from JetArm Pro's camera and remotely control the robot's movements.
2) Wireless Controller Control
Using a wireless controller, you can remotely control JetArm Pro's movements. Through programming, it can perform a variety of actions.
3) Target Tracking
JetArm Pro can identify targets within its field of view and continuously lock onto and track their movements in real time.
4) Vision Line Following
JetArm Pro supports custom color selection, and the robot can identify color lines and follow them.
4. Sliding Rail Function
JetArm Pro supports sliding rail expansion. The controller communicates via I2C to directly control the stepper motor on the sliding rail, extending its reach for grasping and handling tasks. It can precisely calculate the rail's movement distance, enabling acurate transport, sorting, and stacking operations.
1) Wireless Controller Control
Using a wireless controller, you can precisely and instantly control JetArm Pro's movement along the sliding rail, enabling efficient and accurate grasping and sorting tasks.
2) Color Sorting
Leveraging OpenCV algorithms, JetArm Pro can precisely identify and track targets within its field of view. Combined with advanced inverse kinematics, it performs sorting tasks with agility and accuracy.
3) Waste Sorting
Powered by YOLOv8 model training, JetArm Pro rapidly detects various types of "waste" and uses inverse kinematics to precisely sort and place them into designated categories.
4) Tag Sorting
JetArm Pro accurately detects various AprilTag markers and autonomously determines their coordinates. It then picks up and sorts the tagged objects into specified locations.
5. Motorized Conveyor Belt Function
By combining the motorized conveyor belt with a vision system, JetArm Pro can accurately track and pick objects moving on the conveyor in real time, sorting them into specified zones. This enables simulation of a closed-loop industrial production line, making it an ideal choice for Al-driven automated sorting scenarios.
1) Wireless Controller Control
The wireless controller allows real-time control of the conveyor belt's direction, working seamlessly with JetArm Pro to enable efficient and intelligent sorting scenarios.
2) Speed Control
The conveyor belt offers adjustable speed control, reaching up to 50mm/s, and supports a maximum load of around 3kg-perfect for a range of handling and sorting tasks.
3) Direction Control
Easily program the conveyor belt to move in either direction.
4) Color Sorting
JetArm Pro can automatically identify objects on the conveyor belt and, through programmable control, pick and sort them into specified areas with precision.
6. Large AI Model–Driven Embodied AI Applications
JetArm Pro Ultimate Kit is equipped with a circular 6-microphone array. Going beyond the one-way command-response pattern of traditional AI models, JetArm Pro—powered by ChatGPT—enables a cognitive leap from semantic understanding to physical execution, significantly enhancing the naturalness and fluidity of human-machine interaction. Combined with advanced machine vision, JetArm Pro delivers outstanding capabilities in perception, reasoning, and action, making it ideal for developing sophisticated embodied AI applications.
1) Voice Control
With ChatGPT integration, JetArm Pro can comprehend spoken commands and carry out corresponding actions, enabling intuitive and seamless voice-controlled interaction.
2) Color Sorting
With the support of ChatGPT, JetArm Pro can understand user commands and, when combined with AI vision, accurately identify and sort objects based on their colors within its field of view.
3) Waste Sorting
JetArm Pro leverages the YOLOv8 deep learning model built into its system to recognize different types of objects in the scene. With the power of ChatGPT, it can interpret user commands and perform corresponding actions, such as waste sorting.
4) 3D Object Sorting
Equipped with a 3D depth camera, JetArm Pro can detect objects of various shapes within its field of view. When combined with ChatGPT, it understands user instructions and carries out the required actions.
5) Real-Time Detection
JetArm Pro, powered by OpenAI's ChatGPT, can understand user commands and intelligently analyze scenes. It provides real-time feedback on image content and object features through both text and voice.
6) Vision Tracking
By integrating ChatGPT with OpenRouter’s visual large model, JetArm Pro can accurately interpret user commands to identify and locate objects within its field of view. Paired with inverse kinematics algorithms, it enables precise and responsive target tracking.
7) Intelligent Transport
Utilizing the OpenRouter Vision large model, JetArm Pro can identify target objects, retrieve their positional data, and, with the help of ChatGPT, analyze user commands to move objects to specified locations.
8) Smart Home Assistant
Thanks to its integrated multimodal large model, JetArm Pro is capable of recognizing and analyzing objects within its view. Paired with ChatGPT, it comprehends user commands and delivers appropriate verbal and physical responses.
7. Multimodal Models Deployment
JetArm integrates a Multimodal Large AI Model and supports online deployment via OpenAI's API, enabling real-time access to advanced AI capabilities. It also allows seamless switching to alternative models, such as those available through OpenRouter, to support Vision Language Model applications. At its core, JetArm is designed as an all-in-one interaction hub built around ChatGPT, enabling sophisticated embodied AI use cases and creating a smooth, intuitive human-machine interaction experience!
1) Large Language Model
With the integration of the ChatGPT Large Model, JetArm operates like a 'superbrain” - capable of comprehending
diverse user commands and responding intelligently and contextually.
2) Large Speech Model
Empowered by a 6-microphone array, JetArm now has "ears" and a "voice",enabling it to hear your voice and respond in real time. Powered by advanced end-to-end streaming speech-language modeling and natural language processing, it offers smooth and natural voice inter-action.
3) Vision Language Model
JetArm integrates with OpenRouter's Vision Large Model, enabling advanced image understanding and analysis. It
can accurately identify and locate objects within complex visual scenes, while also delivering detailed descriptions that cover object names, characteristics, and other relevant attributes.
8. 3D Depth Vision Al Upgraded Interaction
Equipped with a Gemini plus 3D depth camera, JetArm can effectively perceive environmental changes, allowing for intelligent Al interaction with humans.
1) 3D Depth Point Cloud Recognition
Through the corresponding APl of the depth camera, JetArm can obtain the depth map, color map and point cloud map of the detection environment, and then obtain the RGB data, position coordinates, and depth information of the target item to achieve shape recognition, color sorting, height measurrement, material detection, etc.
2) Depth Camera Distance Ranging
By capturing depth point cloud data of an object, the depth camera can determine the distance betweenthe object and the camera. This enables accurate object localization, sorting, and tracking.
3) Regional Target Height Measurement
By obtaining the depth point cloud data of the object, the height of the object can beidentified, thereby realizing the gameplay of removing highly abnormal objects.
4) Regional Target Volume Measurement
By capturing depth point cloud data, the depth camera can measure the volume of an object after recognizing its shape and height.
9. Al Vision Recognition Target Tracking
JetArm's 3D depth camera is equipped with an RGB lens. The robot arm uses OpencV as the image processing library, supports Al intelligent image recognition, and can realize a varietyof intelligent vision gamep such as color recognition and tag recognition.
1) Color Sorting
JetArm can recognize and sort color blocks of different colors.In addition to standard colors, JetArm can also recognize a variety of custom colors.
2) Tag Recognition, Intelligent Stacking
JetArm can recognize different AprilTags and determine the position of the tag block to achieve intelligent stacking.
3) Target Tracking
JetArm can locate and track targets, cnd we can also use machine learning to let JetArm track more trained target items.
10. RGB+D Integration for 3D Spatial Random Grasping
JetArm's 3D depth camera combines RGB and depth data to capture both the object's color and depth point cloud information, enhancing the spatial representation. Using the inverse kinematics algorithm, JetArm can perform advanced Al tasks such as 3D spatial random object grasping, sorting, and transport,enabling more complex and dynamic projects.
1) RGB+D 3D Spatial Random Grasping
2) Voice-Controlled 3D Spatial Grasping and Sorting
11. Upgraded Inverse Kinematics Algorithm
JetArm has a high-level inverse kinematics algorithm, which can move to any coordinate in 3D scene, and the path planning of the robot arm can also be realized by Python programming.
1) Target Detection, Joint Adaptive Adjustment
JetArm can detect target items within the recognition area and calculate the position coordinates and placement angle of the target item. Combined with the inverse kinematics algorithm of the robot arm, each joint angle is adaptively adjusted to achieve free grabbing.
2) 3D Scene Motion Control
JetArm can use inverse kinematics algorithms to achieve linear motion and path planning in 3D scene.
3) Provides Source Code for DH Model and Inverse Kinematics
Provide the inverse kinematics analysis, coordinate DH model and inverse kinematics function source code of the JetArm robot arm, and input the end coordinates of the robot arm greatly shortening the project development time.
12. Deep Learning Model Training
JetArm integrates advanced neural network technologies, leveraging YOLOv8 for real-time multi-object detection. It enables customized deep learning model training for specific objects, producing lightweight models optimized for TensorRT acceleration, unlocking a wide range of AI-driven creative possibilities.
1) Waste Sorting - JetArm's kit is equipped with garbage pattern blocks. By loading the corresponding model, JetArm can quickly recognize different garbage and place it in the corresponding classification area.
2) Item Sorting - By training models of daily items and generating corresponding models, with the support of depth cameras, JetArm can quickly recognize and grab corresponding items by obtaining the depth information of the items.
13. MediaPipe Development, Upgraded Al Interaction
Leveraging the MediaPipe development framework, JetArm enables features like gesture recognition, motion control, and face tracking.
1) Gesture Recognition
JetArm can recognize various gestures, enabling interactive and engaging gesture-based controls.
2) Face Tracking
JetArm can recognize human faces and retrieve their coordinates, enabling precise face tracking by integrating inverse kinematics and PID algorithms.
3) Fingertip Trajectory Control
Based on the detection of the distance between fingertips, JetArm can perform corresponding actions.
14. Gazebo Simulation
The JetArm robotic arm is developed using the ROS framework and supports GAZEBO simulation. The robotic arm is controlled and algorithm verified in a virtual environment, which reduces the requirements for the experimental environment and improves experimental efficiency.
15. Movelt Kinematics
JetArm Pro integrates Movelt simulation, allowing you to control the robotic arm and validate algorithms in a virtual environment. This minimizes dependency on physical labs and accelerates the development process.
1) URDF Kinematics Simulation Model
A scale-accurate virtual replica of the physical robot. The Movelt tool offers a visual interface with features such as drag-and-drop operation, preset position control, and robotic arm motion obstacle avoidance.
2) Simulation Control / Motion Planning
Control the robotic arm's movements in real time through a visual simulation interface, executing actions that precisely match the model.
3) Collision Detection
Create obstacles within the simulation environment and operate the robotic arm, which will autonomously avoid collisions during movement.
4) Spatial Grasping
Customize the planning scene to drive the robotic arm in performing tasks such as grasping, placing, and sorting, with integrated collision detection for the environment.
16. Various Control Methods
1) WonderAi App
2) PC Software
3) Wireless Handle
17. JetArm Pro Configuration Selection Guide
The Jetson Nano provides essential AI inference capabilities, perfect for simple neural networks and deep learning models, making it ideal for entry-level AI applications. The Jetson Orin Nano offers 80 times the performance and computing power of the Jetson Nano, supporting more complex deep learning models and accelerated inference, making it well-suited for advanced edge AI applications. The Jetson Orin NX boosts computing power 2.5 times over the Jetson Orin Nano, offering top-tier AI inference performance for larger neural networks and real-time deep learning tasks. This performance upgrade enhances JetArm Pro, unlocking exceptional capabilities in servo control, vision tasks, and deep learning across a wide range of applications!
