Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Fast Staircase Detection and Estimation using 3D Point Clouds with Multi-detection Merging for Heterogeneous Robots

Prasanna Sriganesh, Namya Bagree, Bhaskar Vundurthy, Matthew Travers

TL;DR

The paper tackles real-time staircase detection for heterogeneous mobile robots operating in multi-level environments. It introduces a LiDAR-based five-stage pipeline—Pre-Processing, Segmentation, Detection, Estimation, and Multi-Detection Merging—to detect diverse stairtypes and estimate geometry, with a mechanism to fuse detections from multiple viewpoints. Empirical results on two robots show detection speeds around $20.64$ ms (significantly faster than the prior state-of-the-art) while preserving or improving geometric accuracy, validating the approach for real-time autonomous traversal and cross-robot collaboration. The work enables robust, autonomous navigation in complex infrastructures and highlights practical implications for search-and-rescue and industrial robotics through fast, reliable stair perception and integration across heterogeneous platforms.

Abstract

Robotic systems need advanced mobility capabilities to operate in complex, three-dimensional environments designed for human use, e.g., multi-level buildings. Incorporating some level of autonomy enables robots to operate robustly, reliably, and efficiently in such complex environments, e.g., automatically "returning home" if communication between an operator and robot is lost during deployment. This work presents a novel method that enables mobile robots to robustly operate in multi-level environments by making it possible to autonomously locate and climb a range of different staircases. We present results wherein a wheeled robot works together with a quadrupedal system to quickly detect different staircases and reliably climb them. The performance of this novel staircase detection algorithm that is able to run on the heterogeneous platforms is compared to the current state-of-the-art detection algorithm. We show that our approach significantly increases the accuracy and speed at which detections occur.

Fast Staircase Detection and Estimation using 3D Point Clouds with Multi-detection Merging for Heterogeneous Robots

TL;DR

The paper tackles real-time staircase detection for heterogeneous mobile robots operating in multi-level environments. It introduces a LiDAR-based five-stage pipeline—Pre-Processing, Segmentation, Detection, Estimation, and Multi-Detection Merging—to detect diverse stairtypes and estimate geometry, with a mechanism to fuse detections from multiple viewpoints. Empirical results on two robots show detection speeds around ms (significantly faster than the prior state-of-the-art) while preserving or improving geometric accuracy, validating the approach for real-time autonomous traversal and cross-robot collaboration. The work enables robust, autonomous navigation in complex infrastructures and highlights practical implications for search-and-rescue and industrial robotics through fast, reliable stair perception and integration across heterogeneous platforms.

Abstract

Robotic systems need advanced mobility capabilities to operate in complex, three-dimensional environments designed for human use, e.g., multi-level buildings. Incorporating some level of autonomy enables robots to operate robustly, reliably, and efficiently in such complex environments, e.g., automatically "returning home" if communication between an operator and robot is lost during deployment. This work presents a novel method that enables mobile robots to robustly operate in multi-level environments by making it possible to autonomously locate and climb a range of different staircases. We present results wherein a wheeled robot works together with a quadrupedal system to quickly detect different staircases and reliably climb them. The performance of this novel staircase detection algorithm that is able to run on the heterogeneous platforms is compared to the current state-of-the-art detection algorithm. We show that our approach significantly increases the accuracy and speed at which detections occur.
Paper Structure (14 sections, 2 equations, 8 figures, 2 tables, 2 algorithms)

This paper contains 14 sections, 2 equations, 8 figures, 2 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Pre-Processing
  5. Segmentation
  6. Detection
  7. Estimation
  8. Multi-Detection Merging
  9. Experimentation and Results
  10. Experimentation
  11. System Overview
  12. Setup
  13. Results
  14. Conclusions and Future Work

Figures (8)

  • Figure 1: Staircase environment and detection
  • Figure 2: Different types of staircases found in an urban environment including industrial and damaged staircases
  • Figure 3: Preprocessing and segmentation overview for stair detection
  • Figure 4: Staircase model and successful detection result
  • Figure 5: Mobile robot platforms used to test our algorithm
  • ...and 3 more figures

Theorems & Definitions (2)

  • Definition 1
  • Definition 2