Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Real-Time Polygonal Semantic Mapping for Humanoid Robot Stair Climbing

Teng Bin, Jianming Yao, Tin Lun Lam, Tianwei Zhang

TL;DR

A novel algorithm for real-time planar semantic mapping tailored for humanoid robots navigating complex terrains such as staircases and leveraging GPU-accelerated processes for planar extraction, enabling the rapid generation of globally consistent semantic maps.

Abstract

We present a novel algorithm for real-time planar semantic mapping tailored for humanoid robots navigating complex terrains such as staircases. Our method is adaptable to any odometry input and leverages GPU-accelerated processes for planar extraction, enabling the rapid generation of globally consistent semantic maps. We utilize an anisotropic diffusion filter on depth images to effectively minimize noise from gradient jumps while preserving essential edge details, enhancing normal vector images' accuracy and smoothness. Both the anisotropic diffusion and the RANSAC-based plane extraction processes are optimized for parallel processing on GPUs, significantly enhancing computational efficiency. Our approach achieves real-time performance, processing single frames at rates exceeding $30~Hz$, which facilitates detailed plane extraction and map management swiftly and efficiently. Extensive testing underscores the algorithm's capabilities in real-time scenarios and demonstrates its practical application in humanoid robot gait planning, significantly improving its ability to navigate dynamic environments.

Real-Time Polygonal Semantic Mapping for Humanoid Robot Stair Climbing

TL;DR

A novel algorithm for real-time planar semantic mapping tailored for humanoid robots navigating complex terrains such as staircases and leveraging GPU-accelerated processes for planar extraction, enabling the rapid generation of globally consistent semantic maps.

Abstract

We present a novel algorithm for real-time planar semantic mapping tailored for humanoid robots navigating complex terrains such as staircases. Our method is adaptable to any odometry input and leverages GPU-accelerated processes for planar extraction, enabling the rapid generation of globally consistent semantic maps. We utilize an anisotropic diffusion filter on depth images to effectively minimize noise from gradient jumps while preserving essential edge details, enhancing normal vector images' accuracy and smoothness. Both the anisotropic diffusion and the RANSAC-based plane extraction processes are optimized for parallel processing on GPUs, significantly enhancing computational efficiency. Our approach achieves real-time performance, processing single frames at rates exceeding , which facilitates detailed plane extraction and map management swiftly and efficiently. Extensive testing underscores the algorithm's capabilities in real-time scenarios and demonstrates its practical application in humanoid robot gait planning, significantly improving its ability to navigate dynamic environments.

Paper Structure

This paper contains 14 sections, 10 equations, 26 figures, 3 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Works
  3. System Framework And Methods
  4. Overview
  5. System Sensory Equipment
  6. Anisotropic Diffusion and Normal Vector Calculation
  7. Plane Segmentation
  8. Polygons Integration and Drift Compensation
  9. Experiments Results and Evaluations
  10. Single-Frame Mapping Accuracy
  11. Performance Evaluation of Algorithmic Components
  12. Comparative Analysis with Elevation Mapping
  13. Motion Planning Simulation
  14. Conclusions

Figures (26)

  • Figure 1: Planar polygon semantic mapping results of spiral and straight stairs
  • Figure 2: Overview of the Planar Polygonal Semantic Mapping System Framework. The system inputs are depth images and robot pose estimates, which are processed to generate a terrain's polygonal planar semantic map. This map can be directly utilized to plan humanoid robot gaits.
  • Figure 3: Overview of processing.
  • Figure 4: Multi-sensory setup installed at the waist of the Leju humanoid robot leju-robot.
  • Figure 5: raw image
  • ...and 21 more figures