top of page

Cube petit

"Cube petit" is an autonomous robot that can be integrated into people's lives. It is being developed as a low-cost, compact robot kit to be used worldwide.
The hardware combines off-the-shelf products, allowing the installation of preferred sensors and motors.
The software is compatible with the open-source "ROS" and can be customized for research applications.

Simulation with SLAM (mapping and self-positioning), autonomous movement, and automatic charging is currently available on GitHub.

Component Composition


Basic function: SLAM & Navigation

Cube petit uses 2D LiDAR to estimate its position and create a map. It also uses a Depth Camera to move and patrol to a specified position while avoiding people and obstacles. ROS package (gmapping, navigation).






Simulator Environment and Map Creation

Specifications (Ver2.0 ClearBlue)

  • PC : Intel NUC (BLKNUC7I7DNHE / Intel Corei7-8650U)

  • Sensor : 2DLiDAR (PACECAT LDS-50C), barometer + 9-axis IMU (Witmotion WT901B)

  • Camera : RGB/Depth camera (Intel RealSense SR305), infrared camera (ELP USBFHD01M-KRL156)

  • Dimensions : width 220 x height 275 x depth 220 [mm]

  • Mass : 7.5 [kg]

  • Battery : LifePo4 / 4 cells / 12 [V] 3 hours operation with 3 hours charge

  • Movement speed : 0.5 [m/s]

  • Other modules : MPPT, DCDC converter, Wifi router

*RaspberryPy4+2D LiDAR (Ver1.0 Ivory) is also available.

Applied function: Automatic charging

  • Detects when the battery is low and moves to the charging dock

  • Automatically recharges while watching AR markers

  • Uses ROS package (ar_track_alvar)


Simulator environment


Automatic charging

Applied function: Conversation

  • Offline Japanese and English speech synthesis and recognition

  • Uses OpenJTalk for Japanese speech synthesis and Julius for recognition, enabling speech with various speeds and emotions

bottom of page