A Hybrid Autoencoder for Robust Heightmap Generation from Fused Lidar and Depth Data for Humanoid Robot Locomotion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bank, Dennis, Cordes, Joost, Seel, Thomas, Ehlers, Simon F. G.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912881763680256
author Bank, Dennis
Cordes, Joost
Seel, Thomas
Ehlers, Simon F. G.
author_facet Bank, Dennis
Cordes, Joost
Seel, Thomas
Ehlers, Simon F. G.
contents Reliable terrain perception is a critical prerequisite for the deployment of humanoid robots in unstructured, human-centric environments. While traditional systems often rely on manually engineered, single-sensor pipelines, this paper presents a learning-based framework that uses an intermediate, robot-centric heightmap representation. A hybrid Encoder-Decoder Structure (EDS) is introduced, utilizing a Convolutional Neural Network (CNN) for spatial feature extraction fused with a Gated Recurrent Unit (GRU) core for temporal consistency. The architecture integrates multimodal data from an Intel RealSense depth camera, a LIVOX MID-360 LiDAR processed via efficient spherical projection, and an onboard IMU. Quantitative results demonstrate that multimodal fusion improves reconstruction accuracy by 7.2% over depth-only and 9.9% over LiDAR-only configurations. Furthermore, the integration of a 3.2 s temporal context reduces mapping drift.
format Preprint
id arxiv_https___arxiv_org_abs_2602_05855
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Hybrid Autoencoder for Robust Heightmap Generation from Fused Lidar and Depth Data for Humanoid Robot Locomotion
Bank, Dennis
Cordes, Joost
Seel, Thomas
Ehlers, Simon F. G.
Robotics
Machine Learning
Reliable terrain perception is a critical prerequisite for the deployment of humanoid robots in unstructured, human-centric environments. While traditional systems often rely on manually engineered, single-sensor pipelines, this paper presents a learning-based framework that uses an intermediate, robot-centric heightmap representation. A hybrid Encoder-Decoder Structure (EDS) is introduced, utilizing a Convolutional Neural Network (CNN) for spatial feature extraction fused with a Gated Recurrent Unit (GRU) core for temporal consistency. The architecture integrates multimodal data from an Intel RealSense depth camera, a LIVOX MID-360 LiDAR processed via efficient spherical projection, and an onboard IMU. Quantitative results demonstrate that multimodal fusion improves reconstruction accuracy by 7.2% over depth-only and 9.9% over LiDAR-only configurations. Furthermore, the integration of a 3.2 s temporal context reduces mapping drift.
title A Hybrid Autoencoder for Robust Heightmap Generation from Fused Lidar and Depth Data for Humanoid Robot Locomotion
topic Robotics
Machine Learning
url https://arxiv.org/abs/2602.05855