Powered by Raspberry Pi 5, compatible with ROS2, and programmed in Python, making it an ideal platform for AI robot development
Supports both Mecanum-wheel and Ackermann chassis, allowing flexibility for various applications and meeting diverse user needs
Equipped with closed-loop encoder motors, TOF lidar, 3D depth camera, high-torque servos, and other advanced components to ensure optimal performance
performance Supports SLAM mapping, path planning, multi-robot coordination, vision recognition, target tracking, and more
Utilizes YOLOv5 model training to enable road sign and traffic light recognition, along with other autonomous driving features, helping users develop autonomous driving technologies

Product Description

MentorPi is a smart robot car powered by Raspberry Pi 5 and supports ROS2. It offers two chassis options: Mecanum-wheel and Ackermann-wheel. Equipped with high-speed closed-loop encoder motors, Lidar, a 3D depth camera, and large-torque servos,it delivers high-performance capabilities. These include SLAM mapping, path planning, vision recognition, and autonomous driving. With YOLOv5 model training, MentorPi can detect road signs and traffic lights. Hiwonder also provides detailed ROS2 tutorials and videos to help users get started quickly.MentorPi is an excellent choice for advanced AI robotics.

① 3D Depth Camera

The 3D depth camera not only enables AI visual functions but also supports advanced features like depth image data processing and 3D visual mapping and navigation.

② Raspberry Pi 5 Controller

MentorPi is powered by Raspberry Pi 5 controller allowing you to embark on motion control, machine vision, and OpenCV projects.

③ STL-19P TOF Lidar

MentorPi is equipped with lidar, which can realize SLAM mapping and navigation, and supports path planning, fixed-point navigation and dynamic obstacle avoidance.

④ High Performance Encoder Motor

It offers robust force, has a high-precision encoder,and includes a protective end shell to ensure an extended service life.

1) Dual-Controller Design for Efficient Collaboration

① Host Controller

- ROS Controller (JETSON, Raspberry Pi, etc.）

- AI Visual image processing

- Deep neural network

- Human-Machine Voice Interaction

- Advanced Al algorithms

- Simultaneous localization and mapping (SLAM）

② Sub Controller

- ROS expansion board

- High-Frequency PID Control

- Motor Closed-Loop Control

- Servo Control and Feedback

- IMU Data Acquisition

- Power Status Monitoring

2) Lidar Function

Mentor Pi is equipped with lidar, which supports path planning, fixed point navgation, navigation and obstacle avoidance, multiple algorithm mapping, and realizes lidar guard and lidar tracking functions.

① Lidar Mapping and Navigation

MentorPi can realize advanced SLAM functins by lidar, including localization, mapping and navigation, path planning, dynamic obstacle avoidance, Lidar tracking and guarding, etc.

② 2D Lidar Mapping Method

TOF Lidar utilizes the SLAM Toolbox for mapping algorithms and supports fixed-point navigation multi-point navigation, as well as TEB path planning.

③ Multi-Point Navigation

MentorPi is equipped with a high-accuracy Lidar that provides real-time environmental detection. It supports both fixed-point navigation and multi-point navigation, making it suitable for complex navigation scenarios.

④ Multi-Robot Cooperation Mapping&Navigation

By leveraging multi-root communicotion and navigation technolcgy, several robots can colaborate to simultaneously map their surroundings. This enables multi-robot navigation, path planning.

⑤ Dynamic Obstacle Avoidance

Using TOF Lidar, MentorPi can detect obstacles during navigation and intelligently plan its path to effectively avoid them.

⑥ Lidar Tracking and Guarding

MentorPi can work with Lidar to scan and subsequently track a moving target ahead. MentorPi utilizes TOF Lidar toscan the secured area. Upon detecting an intruder, it will automatically turn toward the intruder and activate an alarm.

3) 3D Depth Camera Function

Equipped with a Angstrong depth camera, Mentor Pi can effectively perceive envronmental changes, allowing for intelligent Al interaction with humans.

① Color Recognition and Tracking

Working with OpenCV, MentorPi can track specific color. After you select the color on the APP, it emits light of corresponding color and moves with the object of that color.

② Target Tracking

Through vision positioning of the target object, the target object can be better targeted and tracked.

③ QR Code Recognition

MentorPi can recognize the content of custom QR codes and display the decoded information.

④ Vision Line Tracking

MentorPi supports custom color selection, and the robot can identify color lines and track them.

⑤ RTAB-VSLAM 3D Vision Mapping & Navigation

By utilizing the RTAB SLAM algorithm and fusing vision and Lidar data to create 3D colored map, MentorPi can navigate and avoid cbstacles within this 3D environment. t also supports global relocalizotion.

⑥ Depth Map Data，Point Cloud

Through the corresponding API, MentorPi can get a depth map, color image and point cloud of the camera.

4) Deep Learning,Autonomous Driving

In the ROS system, MentorPi has deployed the deep learning framework PyTorch, the open source image processing library OpenCV and the target detection algorithm YOLOV5 to help users who want to explore the field of autonomous driving image technology easily enjoy Al autonomous driving.

① Road Sign Detection

Through training the deep learning model library, MentorPi can realize the autonomous driving function with Al vision.

② Lane Keeping

MentorPi is capable of recognizing the lanes on both sides to maintain safe distance between it and the lanes.

③ Autonomous Parking

Combined with deep learning algorithms to simulate realscenarios, side parking and warehousing can be achieved.

④ Turning Decision Making

According to the lanes, road signs and traffic lights, MentorPi will estimate the traffic and decide whether to turn.

⑤ YOLO Object Recognition

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

⑥ MediaPipe Development, Upgraded Al Interaction

MentorPi utilizes MediaPipe development framework to accomplish various functions, such as fingertip recognition, humanbody recognition, 3D detection, and 3D face detection.

5) Open Source Python Programming

MentorPi supports python programming. All AI intelligent Python code is open source, with detailed annotations for easy self-study.

6) Wireless Handle Control

MentorPi supports wireless handle control and can connect to the robot via Bluetooth to control the robot in real time.

7) App Control

WonderPi app supports Android and iOS. Switch game modes easily and quickly to experience various AI games.

1* M1 (Mecanum) Chassis

1* Controller top cover

1* Front cover

1* Rear cover

1* Raspberry Pi 5 8GB Board

1* 64GB SD card

1* Cooling fan

1* Raspberry Pi power supply cable

1* RRC data cable

1* RRC Lite controller

1* Battery cable

1* Lidar

1* Lidar data cable

1* 8.4V 2A charger (DC5.5*2.5 male connector)]

1* 3D Depth camera

1* Depth data cable

1* Wireless handle & Handle receiver

1* EVA ball

1* Card reader

1* Accessory bag

1* User manual

Model: Mecanum-wheel chassis version

Weight: 1.2kg

Size: 212*171*147mm

Chassis type: Mecanum wheel chassis

Motor: 310 metal gear geared motor

Encoder: AB-phase high-accuracy quadrature encoder

Material: Full metal aluminum alloy chassis, anodizing process

ROS controller: RRC Lite controller + Raspberry Pi 5 controller

Control method: App, wireless handle and PC control

Camera: Angstrong binocluar 3D depth camera

Lidar: ldrobot STL-19P

Battery: 7.4V 2200mAh 20C LiPo battery

OS: Raspberry Pi OS + Ubuntu 22.04 LTS + ROS2 Humble (Docker)

Software: iOS/ Android app

Communication method: WiFi/ Ethernet

Programming language: Python/ C/ C++/ JavaScript

Storage: 64GB TF card

Package size: 41*22*18cm

Package weight: About 2.1kg