Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Hibikino-Musashi@Home 2024 Team Description Paper

Kosei Isomoto, Akinobu Mizutani, Fumiya Matsuzaki, Hikaru Sato, Ikuya Matsumoto, Kosei Yamao, Takuya Kawabata, Tomoya Shiba, Yuga Yano, Atsuki Yokota, Daiju Kanaoka, Hiromasa Yamaguchi, Kazuya Murai, Kim Minje, Lu Shen, Mayo Suzuka, Moeno Anraku, Naoki Yamaguchi, Satsuki Fujimatsu, Shoshi Tokuno, Tadataka Mizo, Tomoaki Fujino, Yuuki Nakadera, Yuka Shishido, Yusuke Nakaoka, Yuichiro Tanaka, Takashi Morie, Hakaru Tamukoh

TL;DR

This paper provides an overview of the techniques employed by Hibikino-Musashi@Home, which intends to participate in the domestic standard platform league and continuously attends competitions to evaluate and improve the developed system.

Abstract

This paper provides an overview of the techniques employed by Hibikino-Musashi@Home, which intends to participate in the domestic standard platform league. The team has developed a dataset generator for training a robot vision system and an open-source development environment running on a Human Support Robot simulator. The large language model powered task planner selects appropriate primitive skills to perform the task requested by users. The team aims to design a home service robot that can assist humans in their homes and continuously attends competitions to evaluate and improve the developed system.

Hibikino-Musashi@Home 2024 Team Description Paper

TL;DR

This paper provides an overview of the techniques employed by Hibikino-Musashi@Home, which intends to participate in the domestic standard platform league and continuously attends competitions to evaluate and improve the developed system.

Abstract

This paper provides an overview of the techniques employed by Hibikino-Musashi@Home, which intends to participate in the domestic standard platform league. The team has developed a dataset generator for training a robot vision system and an open-source development environment running on a Human Support Robot simulator. The large language model powered task planner selects appropriate primitive skills to perform the task requested by users. The team aims to design a home service robot that can assist humans in their homes and continuously attends competitions to evaluate and improve the developed system.
Paper Structure (13 sections, 7 figures, 1 table)

This paper contains 13 sections, 7 figures, 1 table.

Table of Contents

  1. Introduction
  2. System Overview
  3. Perception
  4. Object Recognition
  5. YOLO
  6. Language Segment-Anything
  7. Speech Recognition
  8. Human Detection
  9. Human Tracking
  10. Semantic Map
  11. Task Planning
  12. Reusability
  13. Conclusions

Figures (7)

  • Figure 1: Block diagram providing an overview of the HSR system. [HSR, Human Support Robot; ROS, robot operating system]
  • Figure 2: Placing scanned objects on a 3D simulator.
  • Figure 3: Example of the prompts for Language Segment-Anything.
  • Figure 4: Placing scanned objects on a 3D simulator.
  • Figure 5: Example of a semantic map
  • ...and 2 more figures