融合激光雷达与深度相机数据，用神经网络生成更精准的地形高度图。
A Hybrid Autoencoder for Robust Heightmap Generation from Fused Lidar and Depth Data for Humanoid Robot Locomotion
- 用CNN+GRU混合结构提取空间与时间特征，提升地形感知鲁棒性。
- 多模态融合使重建精度比纯深度或纯激光雷达提升7.2%和9.9%。
- 引入3.2秒时序信息，有效减少地图漂移，适合复杂环境行走机器人。
在非结构化、以人为主的环境中部署类人机器人，可靠地形感知是关键前提。传统系统常依赖人工设计的单传感器流程，本文提出一种基于学习的框架，采用机器人中心的高度图表示。引入混合编码器-解码器结构（EDS），结合卷积神经网络（CNN）进行空间特征提取，以及门控循环单元（GRU）保持时间一致性。该架构融合了Intel RealSense深度相机、经高效球面投影处理的LIVOX MID-360激光雷达，以及机载惯性测量单元（IMU）的多模态数据。定量结果显示，多模态融合相较仅深度数据提升重建精度7.2%，相较仅激光雷达提升9.9%。此外，引入3.2秒的时序上下文可显著降低地图漂移。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。