EDU+ programmable robot with JetOver LIDAR, Slamtec A1 3D camera, ROS1 ROS2 AI image and sound recognition, robotic arm, holonomic wheels, Ackermann or tracks

It supports 3-movement chassis: Mecanum wheel, Ackerman and Tank chassis. 

JetRover is equipped with an NVIDIA Jetson or Raspberry Pi, a high-performance magnetic encoding engine, and a 6-degree-of-freedom robotic arm. High-performance hardware configurations such as lidar, a 3D depth camera, a 7-inch LCD screen, and a far-field microphone array enable robot motion control, mapping navigation, path planning, obstacle tracking and avoidance, autonomous driving, 3D mapping, navigation and manipulation, somatosensory interaction, far-field voice interaction, group control training, and other applications. The JetRover car robot also deploys multimodal generative AI to support more advanced embedded AI applications. To help you unlock its full potential, we offer open-source code and learning resources to inspire and support your AI projects.

6DOF robot arm, intelligent bus servo

The JetRover robot is equipped with a 6DOF robot arm and a high-torque bus high-voltage servo, which greatly extends the robot's endurance.

SLAM LiDAR mapping navigation

Hiwonder JetRover is equipped with lidar, which can perform SLAM mapping and navigation. It also supports path planning, fixed-point navigation, and dynamic obstacle abundance.

FPV (first-person view) depth vision

JetRover is equipped with a 6-degree-of-freedom robotic arm, fitted with a high-performance 3D depth camera at the end, which can perform target recognition, tracking, and capture.

6CH Field Microphone Array

The 6CH far-field microphone array and speakers support sound source positioning, voice recognition control, voice navigation, and other functions.

Integration of the large AI model with SLAM mapping and navigation

The Hiwonder JetRover combines a large multimodal AI model to understand user voice commands via a large AI language model, enabling multipoint navigation. Once the JetRover arrives at the designated location, it uses a vision language model to gain a deep understanding of surrounding objects and events. This approach significantly enhances the robot's intelligence, adaptability, and overall user experience, making it better suited to meet real-world needs.

Semantic comprehension

JetRover leverages a large AI language model to accurately interpret and analyze users' voice commands, enabling a deeper understanding of natural language intent.

 

Environmental perception

Powered by an AI vision language model, the JetRover car robot can interpret objects in its environment and understand the spatial arrangement of the environment.

 

 

Intelligent navigation

Hiwonder JetRover continuously sends environmental data to an AI vision language model for in-depth, real-time analysis. It dynamically adjusts its navigation path based on the user's voice commands, enabling it to autonomously navigate to designated areas and provide intelligent, adaptive routing.

 

Scene comprehension

With the support of an AI vision language model, JetRover can deeply interpret semantic information from its environment, including surrounding objects and events in its field of view.

 

 

Embedded generative AI applications

JetRover Developer and Ultimate Kit are equipped with a circular array of six microphones. Going beyond the unidirectional command-and-response model of traditional AI models, JetRover, powered by ChatGPT, enables a cognitive leap from semantic understanding to physical execution, significantly improving the naturalness and fluidity of human-machine interaction. Combined with advanced computer vision, Hiwonder JetRover offers exceptional capabilities in perception, reasoning, and action, making it ideal for developing sophisticated embedded AI applications.

 

 

AI Vision Interaction

By integrating artificial intelligence, Hiwonder JetRover can implement KCF target tracking, AI deep learning, color/label recognition and tracking, AR augmented reality, etc.

KCF target tracking

The image-based kernelized correlation filter (KCF) algorithm enables the selection and tracking of any target in the image.

Next line of sight

JetRover supports custom color selection, and the robot can identify and follow colored lines.

 

Color recognition and tracking

The JetRover AI robot is capable of recognizing and tracking the designated color, and can recognize multiple April tags and their coordinates at the same time.

 

Augmented Reality (AR)

Select the corresponding charts via the APP and let the charts be displayed on the April Tag code using AR enhancement technology.

 

MediaPipe development, enhanced AI interaction

Using the MediaPipe development framework, JetRover can perform fingertip detection, human body recognition, 3D object recognition, face detection, and more.

 

AI Deep Learning Framework

Use the YOLO network algorithm and the deep learning model library to recognize objects.