Photo credits: HIWONDER

EDU+ PupPi quadruped robot running Python ROS2 on a Raspberry Pi 5 (8GB RAM), with voice and image recognition, color and QR code scanning. Features 8 powerful servomotors, stainless steel metal gears, a 2D HD camera, AI mapping module, LiDAR, robotic arm, and gripper.


SKU: PUP-WIH-PI5
Options

1 029,00€ - 1 465,00€ VAT Incl.

PupPi is an AI-powered quadruped robot dog based on the Raspberry Pi 5. It is equipped with 8 high-performance coreless servos and features a linkage structure design in its legs, allowing for flexible and dynamic movement.



Select a variation to see the stock
Delivery: 2 to 3 days
Categories: EDU+ range
PAYMENT & SECURITY

DESCRIPTION

YouTube video - 3ab-o7AZ4wE

 

PupPi is an AI-powered quadruped robot dog based on the Raspberry Pi 5. It features eight high-performance coreless servos and a linkage structure design in its legs, enabling flexible and dynamic movement. Running on ROS1 and ROS2 operating systems, PupPi supports Python programming and integrates AI vision capabilities, such as target tracking and face detection, to support a variety of creative AI applications. With its multimodal AI model, camera, and AI voice interaction module, PupPi can understand its environment and perform tasks with agility, enabling advanced embedded AI applications.

 

 

Dual controller design for efficient collaboration

 

AI vision, unlimited creativity

The PupPi robot dog is equipped with a wide-angle HD camera on its head, enabling real-time image acquisition and processing using the OpenCV vision library. It can detect and extract parameters such as the color and position of target objects within its field of view. The system supports a range of vision-based functions, including video streaming, color recognition, label identification, and visual line tracking. By applying a PID control algorithm, Hiwonder PupPi achieves real-time target locking, allowing for advanced AI applications such as target tracking and autonomous kicking.

 

Object tracking

Powered by the OpenCV vision library, the PupPi Raspberry Pi dog can detect and locate objects of a specific color in real time. Using PID control, its head can actively track moving targets with precision.

 

Going up and down the stairs

Hiwonder PupPi leverages the OpenCV vision library to accurately detect the spatial position and geometric contours of stairs in its view. Through autonomous decision-making, it can climb stairs efficiently and smoothly on its own.

 

Beacon recognition

Using OpenCV algorithms, the PupPi AI robotic dog can recognize and interpret tag codes within its field of vision. It can also calculate the position and orientation of each tag, allowing users to program custom interactive movements.

 

Face detection

Hiwonder PupPi features a built-in MediaPipe deep learning algorithm that works with a high-definition camera to accurately detect and lock onto the human face. Users can program PupPi to perform reactive actions based on facial detection.

 

Autonomous obstacles

Using the OpenCV vision library, the PupPi quadruped robot dog can detect obstacles in real time while following a path, capture their coordinates, and dynamically adjust its posture. It then autonomously makes decisions to navigate smoothly and overcome obstacles.

 

Next Line

Thanks to AI vision and PID motion control, Hiwonder PupPi can identify colored lines in its view and autonomously adjust its gait to follow the path smoothly and stably.

 

AI applications embedded in large models

The PupPi Raspberry Pi robot is equipped with a high-performance AI voice interaction module. Unlike conventional AI systems that operate on unidirectional command-response mechanisms, the PupPi AI robot dog leverages ChatGPT to enable a cognitive transition from semantic understanding to physical execution, significantly improving the fluidity and naturalness of human-machine interaction. Combined with computer vision, Hiwonder PupPi exhibits advanced capabilities in perception, reasoning, and autonomous action, paving the way for more sophisticated embodied AI applications.
 
 

Voice command

Powered by ChatGPT, the PuppyPi quad robot is capable of semantically understanding and executing corresponding actions, enabling smooth and natural voice control.
 

Scene comprehension

By leveraging OpenAI's ChatGPT model, Hiwonder PuppyPi is able to understand user commands and perform semantic analysis of visual scenes within its field of vision. It can interpret image content and features, providing contextual feedback through text and speech.

 

Tracking and firing the ball

With semantic understanding powered by a large language model, the robot dog PuppyPi can lock onto a target based on commands, adjust its posture in real time, and accurately execute tracking and ball-kicking actions.
 

 

Autonomous patrol

By using the semantic understanding of a large language model, PuppyPi can accurately detect and track lines of different colors in real time while autonomously navigating around obstacles, ensuring a smooth and efficient patrol.
 

 

Transport of objects

Powered by a vision language model, Hiwonder PuppyPi can recognize target objects in its view and intelligently respond to commands by adjusting its posture in real time to pick up and place objects accurately.
 

 

Post-detection

The robotic dog PuppyPi continuously reads data from the IMU sensor, allowing the large AI model to analyze its posture in real time and make intelligent adjustments based on commands.
 

 

Smart Home Assistant

By leveraging the multimodal model deployed on its body, Hiwonder PuppyPi is able to recognize and analyze objects within its field of vision. Combined with ChatGPT, it can understand user commands and execute corresponding actions and responses.
 

 

Temperature report

Equipped with a temperature and humidity sensor, the PuppyPi robot can continuously monitor environmental conditions, collect real-time data, and use semantic understanding powered by a large language model to report current temperature and humidity.