MentorPi is a ROS2-compatible, Raspberry Pi 5-based robot car with Mecanum or Ackermann chassis

MentorPi is a ROS2-compatible robot car powered by the Raspberry Pi 5, designed for AI-driven robotics and Python programming. It offers two chassis options: MentorPi-M1, which features a Mecanum-wheel chassis, and MentorPi-A1, equipped with an Ackermann chassis. Both variants come with high-performance components such as closed-loop encoder motors, STL-19P TOF lidar, 3D depth cameras, and high-torque servos. These enable precise navigation, SLAM mapping, path planning, and dynamic obstacle avoidance, making MentorPi an ideal platform for robotics tasks.

The system utilizes a dual-controller architecture to optimize performance. The Raspberry Pi 5 handles AI vision processing and strategic functions, while Hiwonder’s RRC Lite expansion board manages motion control and sensor data processing. This task distribution enhances efficiency in machine vision, AI-powered navigation, and robotic control, allowing MentorPi to tackle complex AI and vision-based applications with ease.

MentorPi also supports advanced features like 3D visual mapping and YOLOv5-based object detection for recognizing road signs and traffic lights, enabling autonomous driving functions. Users can rely on detailed ROS2 tutorials and resources provided by Hiwonder, ensuring a smooth setup and learning process for AI robotics development. The system is designed to provide a comprehensive platform for AI-driven applications, with capabilities in autonomous navigation and vision recognition.

Hiwonder MentorPi A1 and MentorPi M1 robot car

MentorPi robot car specifications:

  • Controller
    • Host controller – Raspberry Pi 5 for
      • AI vision image processing
      • Deep neural network
      • Human-machine voice interaction
      • Simultaneous Localization and mapping (SLAM)
    • Sub-controller – RRC Lite Controller board for motion control and sensor data
      • SoC – STMicro STM32F407VET6 Cortex-M4 MCU @ 168 MHz with 512KB flash, 192KB SRAM
      • SA8870C overcurrent protection motor drive chip
      • Servo port – 4-channel PWM servo port and 2-channel serial bus servo port
      • IMU sensor – 3-axis acceleration and 3-axis gravity acceleration
      • USB – 2x Type-C port for serial and power input
      • Misc
        • 1x buzzer
        • I2C port and 4-channel encoder motor port
        • 3x LED indicator, 2x RGB light
        • 1x reset button and 3x user buttons
  • Storage – 64GB microSD card
  • Camera module
    • 2DOF Monocular Camera – 170° focal field HS-256-650 camera with 640 x 480 resolution, and 2.0 aperture; or
    • 3D Depth Camera – Infrared camera, RGB camera, laser dot projector, and depth processing chip with 73.8° FOV, 1920×1080 color image output, and 0.2 to 4m depth range.
  • Lidar – 360° scanning angle STL-19P D500 TOF development kit supports indoor and outdoor environment
  • Motor and servo
    • MentorPi M1 – 4x AB phase incremental hall encoder geared motor
    • MentorPi A1
      • 1x LD-1501MG High-precision Servo for steering control
      • 2x AB phase incremental hall encoder geared motor
  • Wheel
    • MentorPi M1 – 4x Mecanum wheel
    • MentorPi A1 – 4x 64mm anti-slip rubber wheel
  • Connectivity – Gigabit Ethernet, WiFi 5, and Bluetooth 5 on Raspberry Pi 5 SBC
  • Misc – Comes with a Raspberry Pi heatsink with a cooling fan
  • Battery – 7.4V 2200mAh 20C high-quality 18650 cells LiPo Battery with over 300 charge cycles; 2.5 female plug and SM-2P male jack
  • Power – 8.4V/2A charger
  • Dimension and weight
    • MentorPi M1 – 212 x 171 x 147 mm | 1.2 KG
    • MentorPi A1 – 213 x 159 x 157 mm | 1.2 KG

RRC Lite controller specifications

MentorPi A1 and MentorPi M1 Raspberry Pi 5 robot car specifications
MentorPi A1 and MentorPi M1 robot car specifications

MentorPi’s 3D depth camera, integrated with OpenCV, enables advanced vision functions such as color recognition and tracking, allowing the robot to follow objects based on selected colors. It also supports target tracking through vision positioning and QR code recognition for decoding custom information. With vision line tracking, the robot can follow predefined color lines. Using the RTAB-VSLAM algorithm, MentorPi combines Lidar and camera data to generate 3D maps for navigation and obstacle avoidance. The system provides API access to depth maps, color images, and point clouds for further processing and applications.

3D maps and depth maps
RTAB-VSLAM 3D Vision Mapping and Depth Map Data

MentorPi integrates MediaPipe for advanced 3D detection, enabling fingertip, body, and face recognition. It supports open-source Python programming with detailed annotations and offers wireless control via Bluetooth. The WonderPi app, available for Android and iOS, provides multiple AI game modes. MentorPi operates on Raspberry Pi OS, Ubuntu 22.04 LTS, and ROS2 Humble (Docker), with support for Python, C, C++, and JavaScript programming languages. Additionally, ROS (Robot Operating System) offers a comprehensive robotic communication framework, providing hardware abstraction, low-level device control, and tools for code reuse in robotics development. For more information on the user guide, setup, software, and video tutorials, visit the Hiwonder download page, which links to a shared Google Drive.

MediaPipe development framework
MediaPipe development framework

Previously, we covered the Waveshare UGV AI Rover, which features a 2mm thick aluminum body, six 80mm shock-absorbing tires, and a four-wheel drive system controlled by an ESP32 sub-controller, with Raspberry Pi 4B or Raspberry Pi 5 as the primary controller. We also reviewed the SunFounder PiCar-X 2.0, an AI-powered self-driving robot car using Raspberry Pi 3/4 as its main processing unit, as well as the SunFounder Zeus robot car with mecanum wheels but lower processing capabilities combining an Arduino UNO with an ESP32 board.

The key difference between the MentorPi A1 and MentorPi M1 lies in the aluminum alloy chassis and the wheel steering system, as detailed in the specifications section. Currently, only the MentorPi M1 robot car is listed on AliExpress for $599.78 with free shipping, and on Amazon, prices start at $439.99 without the Raspberry Pi 5 and $579.99 with the Raspberry Pi 5 (8GB version). Both the MentorPi A1 and MentorPi M1 models are available on Hiwonder’s official store. Check out the announcement for more details.

Share this:

Support CNX Software! Donate via cryptocurrencies, become a Patron on Patreon, or purchase goods on Amazon or Aliexpress

ROCK 5 ITX RK3588 mini-ITX motherboard
Subscribe
Notify of
guest
The comment form collects your name, email and content to allow us keep track of the comments placed on the website. Please read and accept our website Terms and Privacy Policy to post a comment.
0 Comments
oldest
newest
Boardcon Rockchip RK3588S SBC with 8K, WiFI 6, 4G LTE, NVME SSD, HDMI 2.1...