arXiv 2503.044412025-03cs.ROcs.CV

EvidMTL：用于从单目RGB图像进行不确定性感知语义表面建图的证据多任务学习

EvidMTL: Evidential Multi-Task Learning for Uncertainty-Aware Semantic Surface Mapping from Monocular RGB Images

Humanoid Robots Lab and the Center for Robotics, University of Bonn（人形机器人实验室和机器人中心，波恩大学）；Lamarr Institute, Bonn, Germany（拉马尔研究所，德国波恩）

Rohit Menon, Nils Dengler, Sicong Pan, Gokul Krishna Chenchani, Maren Bennewitz

备注：: Submitted to IROS 2025 Conference

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出证据多任务框架EvidMTL及语义表面建图系统EvidKimera，通过联合证据深度与分割损失提升单目RGB预测的不确定性校准和三维建图一致性。

摘要：

对于非结构化环境中的场景理解，需要精确且具备不确定性感知的度量-语义建图，以使自主系统能够做出明智的行动选择。现有建图方法往往受到过度自信的语义预测以及稀疏、含噪深度感知的困扰，从而导致不一致的地图表示。为此，本文提出EvidMTL，这是一个多任务学习框架，采用证据头进行深度估计和语义分割，从而能够从单目RGB图像进行不确定性感知推理。为实现经过不确定性校准的证据多任务学习，我们提出一种新颖的证据深度损失函数，将深度预测的信念强度与证据分割损失联合优化。在此基础上，我们提出EvidKimera，这是一个不确定性感知的语义表面建图框架，利用证据深度和语义预测来改善三维度量-语义一致性。我们在NYUDepthV2上训练并评估EvidMTL，并在ScanNetV2上评估其零样本性能，结果表明其相比传统方法具有更优的不确定性估计，同时保持相当的深度估计和语义分割水平。在ScanNetV2的零样本建图测试中，EvidKimera在语义表面建图精度和一致性方面优于Kimera，凸显了不确定性感知建图的优势，并强调了其在真实机器人应用中的潜力。

英文摘要：

For scene understanding in unstructured environments, an accurate and uncertainty-aware metric-semantic mapping is required to enable informed action selection by autonomous systems. Existing mapping methods often suffer from overconfident semantic predictions, and sparse and noisy depth sensing, leading to inconsistent map representations. In this paper, we therefore introduce EvidMTL, a multi-task learning framework that uses evidential heads for depth estimation and semantic segmentation, enabling uncertainty-aware inference from monocular RGB images. To enable uncertainty-calibrated evidential multi-task learning, we propose a novel evidential depth loss function that jointly optimizes the belief strength of the depth prediction in conjunction with evidential segmentation loss. Building on this, we present EvidKimera, an uncertainty-aware semantic surface mapping framework, which uses evidential depth and semantics prediction for improved 3D metric-semantic consistency. We train and evaluate EvidMTL on the NYUDepthV2 and assess its zero-shot performance on ScanNetV2, demonstrating superior uncertainty estimation compared to conventional approaches while maintaining comparable depth estimation and semantic segmentation. In zero-shot mapping tests on ScanNetV2, EvidKimera outperforms Kimera in semantic surface mapping accuracy and consistency, highlighting the benefits of uncertainty-aware mapping and underscoring its potential for real-world robotic applications.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。