- Driven by Raspberry Pi 4B/5 and ROS, with 8 coreless servos for high-precision, fast rotation, and strong torque. Real-time posture detection and self-balancing with IMU sensor
- 100W-pixel HD wide-angle camera with OpenCV for target recognition, line following, obstacle avoidance, face detection ball shooting, color tracking, and tag recognition
- Control via WonderPi app (Android/iOS), PC software, or wireless PS2 handle. PuppyPi Pro offers live camera feed to the app
- Incorporate inverse kinematics algorithm offering precise control over the touch time, lift time, and lifted height of each leg.
- Mini TOF lidar for 360-degree scanning, enabling advanced functions like localization, mapping, navigation, path planning, obstacle avoidance, and SLAM.
Product Description
PuppyPi is an AI vision quadruped robot driven by Raspberry Pi and built on the Robot Operating System (ROS). It is equipped with 8 stainless steel coreless servos, delivering high-precision performance, rapid rotation speed, and a robust torque of 8KG.cm. With an IMU sensor, PuppyPi can detect its posture in real-time, enabling self-balancing capabilities.
1) Linkage Mechanism, Efficient Movement
PuppyPi's legs employ a linkage mechanism to increase the angular velocity of its lower legs. The independent movement of different parts of the leg contributes to a greater rotation range.
2) Gait Planning, Free Adjustment
Walk, Amble and Trot gaits can be realized through adjusting touchdown time, lift time and lifted height of each leg as well as the speed of switching front legs and hind legs.
3) Equipped with Coreless Servos
Equipped with stainless steel coreless servos which features high accuracy, fast rotation speed and strong torque.
4) FPV Image Feedback, APP Control
PuppyPi supports Android and iOS dual-system APP control, which not only allows body remote control, but also allows you to see the first visual image of the robot dog.
5) Al Vision Recognition Target Tracking
PuppyPi has a built-in high-definition wide-angle camera on its head, which can identify and locate different targets, thereby enabling creative Al gamep such as visual line following, autonomous climbing, face detection, autonomous kicking, target tracking, and tag recognition.
① Color Tracking
Recognize the position of the ball and continuously adjust its posture to track it.
② Line Following
PuppyPi is able to recognize black and red line, and then calculate the location of the line so as to adjust the walking gait and realize line following.
③ Ball Shooting
Locate the ball via OpenCV, track it in real-time with PID algorithm, and then switch the gait to shoot the ball.
④ Tag Recognition
Recognize Apriltag and give different reactions according to different tags
⑤ Face Tracking
PuppyPi utilizes OpenCV to load the trained models of face detection. When recognizing human face, it will interact with you.
6) PC Software Control
Through PC software PuppyPi's its height and inclination can also be adjusted to make it turn as walking.
7) Support APP Control
Android and iOS mobile APP are available. Via the APP, you can remotely control the robot and view what the robot sees.
8) Python Programming
All intelligent Python code is open source, with detailed annotations for easy self-study.
9) Intelligent Self-balancing
The built-in IMU sensor can monitor PuppyPi's posture in real-time to adjust its joints to balance the body.
10) Inverse Kinematics, Support Gazebo Simulation
This Lidar sensor enables PuppyPi to perform a 360-degree laser scanning of itsenvironment and execute various advanced functions such as synchronous localization, autonomous mapping, multi-point navigation, TEB path planning, dynamic obstacle avoidance, and advanced SLAM capabilities.
① Inverse Kinematics
Through inputting the coordinate of the end of the leg into thevisual PC software, the servo angle can be calculated by its inner processor so as to design cool actions.
② Support Gazebo Simulation
PuppyPi supports Gazebo smulation, which allows you to contol and verify algorithms in a simulated environment, reducing experimental requirements and proving effclency.
7) Support APP Control, FPV Image Feedback
Android and iOS mobile applications are available for remotely controlling the robot and viewing what the robot sees.
8) Carry Lidar for SLAM Mapping and Navigation
The PuppyPi can carry a TOF Lidar on its back to scan the surroundings 360 degrees to realize advanced SLAM functions, including localization, mapping and navigation, path planning and dynamic obstacle avoidance. The combination of the Lidar and the PuppyPi can bring more interesting AI games, such as Lidar tracking and Lidar guarding.
1) Lidar Mapping and Navigation
The Lidar adopts Gmapping, Hector and Karto algorithms to map, and can implement single point navigation, multi point navigation and TEB path planning.
2) Multi point Navigation
The TOF Lidar is able to detect the surroundings in real time, allowing it to plan the path in real time and enabling the PuppyPi to avoid obstacles when executing multi point navigation.
3) Lidar Guarding
The PuppyPi employs the TOF Lidar to scan the protected area. If it detects someone trespassing, it will turn to the intruder and sound the alarm.
4) Lidar Tracking
The PuppyPi can work with the Lidar to scan the moving target ahead and follow it.
9) Support Sensor Expansion, Create More Functions
The PuppyPi is compatible with MP3 modules, touch sensors, dot matrix displays, ultrasonic sensors and other modules, making it possible to build more creative AI projects.
10) ROS Robot Operating System
ROS is an open source meta operating system for robots. It provides basic services, such as hardware abstraction, low level device control, implementation of commonly used functionality, message passing between processes and package management. It also offers the tools and library functions needed to obtain, compile, write and run code across computers and aims to provide code reuse support for robotics research and development.
11) Support Gazebo Simulation
The PuppyPi adopts the ROS framework and supports Gazebo simulation. Gazebo provides a fresh approach for controlling the PuppyPi and verifying algorithms in a simulated environment, which reduces experimental requirements and improves efficiency.
12) TOF Lidar
The LiDAR LD19 TOF Lidar ranges by the means of Time of Flight (TOF). Its ranging radius reaches 12m and the ranging frequency is 4500Hz. The Lidar together with ROS can achieve indoor mapping and navigation with ease.
