An Onboard Framework for Staircases Modeling Based on Point Clouds

TL;DR

This paper introduces an onboard framework for staircase detection and modeling using point cloud data, incorporating data augmentation, a novel loss function, and pose correction to improve accuracy and generalization for legged robot navigation.

Contribution

The paper presents a new onboard method for staircase detection and modeling that includes data augmentation, a curvature suppression loss, and pose-based measurement correction.

Findings

Enhanced detection accuracy demonstrated on a new staircase dataset

Improved generalization over diverse staircase geometries

Effective boundary prediction with the proposed CSCE loss

Abstract

The detection of traversable regions on staircases and the physical modeling constitutes pivotal aspects of the mobility of legged robots. This paper presents an onboard framework tailored to the detection of traversable regions and the modeling of physical attributes of staircases by point cloud data. To mitigate the influence of illumination variations and the overfitting due to the dataset diversity, a series of data augmentations are introduced to enhance the training of the fundamental network. A curvature suppression cross-entropy(CSCE) loss is proposed to reduce the ambiguity of prediction on the boundary between traversable and non-traversable regions. Moreover, a measurement correction based on the pose estimation of stairs is introduced to calibrate the output of raw modeling that is influenced by tilted perspectives. Lastly, we collect a dataset pertaining to staircases and introduce new evaluation criteria. Through a series of rigorous experiments conducted on this dataset, we substantiate the superior accuracy and generalization capabilities of our proposed method. Codes, models, and datasets will be available at https://github.com/szturobotics/Stair-detection-and-modeling-project.