Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Socially Aware Motion Planning for Service Robots Using LiDAR and RGB-D Camera

Duc Phu Nguyen, Thanh Long Nguyen, Minh Dang Tu, Cong Hoang Quach, Xuan Tung Truong, Manh Duong Phung

TL;DR

A motion planning system that includes human states such as positions and velocities and their personal space for social-aware navigation and is able to navigate alongside humans in a dynamic environment while respecting their physical and psychological comfort is introduced.

Abstract

Service robots that work alongside humans in a shared environment need a navigation system that takes into account not only physical safety but also social norms for mutual cooperation. In this paper, we introduce a motion planning system that includes human states such as positions and velocities and their personal space for social-aware navigation. The system first extracts human positions from the LiDAR and the RGB-D camera. It then uses the Kalman filter to fuse that information for human state estimation. An asymmetric Gaussian function is then employed to model human personal space based on their states. This model is used as the input to the dynamic window approach algorithm to generate trajectories for the robot. Experiments show that the robot is able to navigate alongside humans in a dynamic environment while respecting their physical and psychological comfort.

Socially Aware Motion Planning for Service Robots Using LiDAR and RGB-D Camera

TL;DR

A motion planning system that includes human states such as positions and velocities and their personal space for social-aware navigation and is able to navigate alongside humans in a dynamic environment while respecting their physical and psychological comfort is introduced.

Abstract

Service robots that work alongside humans in a shared environment need a navigation system that takes into account not only physical safety but also social norms for mutual cooperation. In this paper, we introduce a motion planning system that includes human states such as positions and velocities and their personal space for social-aware navigation. The system first extracts human positions from the LiDAR and the RGB-D camera. It then uses the Kalman filter to fuse that information for human state estimation. An asymmetric Gaussian function is then employed to model human personal space based on their states. This model is used as the input to the dynamic window approach algorithm to generate trajectories for the robot. Experiments show that the robot is able to navigate alongside humans in a dynamic environment while respecting their physical and psychological comfort.

Paper Structure

This paper contains 17 sections, 17 equations, 10 figures.

Table of Contents

  1. Introduction
  2. Human model and robot sensor system
  3. Human model
  4. Robot sensor system
  5. LiDAR and Camera calibration
  6. Human state estimation
  7. Human detection using LiDAR
  8. Human detection using the RGB-D camera
  9. Pose estimator with MoveNet
  10. Human's position in the LiDAR frame
  11. Fusion algorithm for human state estimation
  12. Socially aware motion planning
  13. Results and discussion
  14. Human state estimation evaluation
  15. Fusion algorithm evaluation
  16. ...and 2 more sections

Figures (10)

  • Figure 1: Personal space: (a) static person; (b) moving person
  • Figure 2: The robot platform with LiDAR and RGB-D camera
  • Figure 3: Human state estimation by LiDAR: (a) correct detection of a person standing in front of the robot; (b) wrong detection of two persons due to reflection noise
  • Figure 4: Mean and variance of human state estimated based on the RGB-D camera
  • Figure 5: Experiment setup for the fusion algorithm where a static camera viewing two ArUco markers placed at the robot and the person
  • ...and 5 more figures