基于课程学习的鲁棒单目视觉里程计
Robust Monocular Visual Odometry using Curriculum Learning
AI总结：
本研究将多种课程学习策略整合进DPVO框架，提出CL-DPVO以提升单目视觉里程计的鲁棒性，在多个基准上超越现有最优方法，验证了课程学习在该领域的有效性。
摘要：
课程学习（CL，Curriculum Learning）受人类与动物的自然学习模式启发，在模型开发过程中采用系统化策略逐步引入复杂度递增的训练数据。本研究将创新的CL方法应用于解决单目视觉里程计（VO，Visual Odometry）估计这一具有挑战性的几何问题，该技术对受限环境下的机器人导航至关重要。本研究的核心目标是通过探究多种课程学习策略，突破当前单目VO领域的最优（SOTA，state-of-the-art）基准性能上限。我们通过整合新型CL方法对端到端Deep-Patch-Visual Odometry（DPVO，深度块视觉里程计）框架进行增强，旨在开发更具鲁棒性的模型，使其能够在挑战性环境与复杂运动场景下保持高性能。本研究涵盖了多种独具特色的CL策略：我们提出了基于轨迹运动特征评估样本难度的方法，通过自步加权损失机制实现了精细的自适应调度，并利用强化学习智能体动态调整训练侧重点。在多样化的合成数据集TartanAir以及EuRoC、TUM-RGBD等复杂真实世界基准上的综合评估显示，我们的基于课程学习的深度块视觉里程计（CL-DPVO）性能优于现有SOTA方法，包括基于特征和基于学习的VO方法。研究结果验证了将课程学习原理融入视觉里程计系统的有效性。
英文摘要：
Curriculum Learning (CL), drawing inspiration from natural learning patterns observed in humans and animals, employs a systematic approach of gradually introducing increasingly complex training data during model development. Our work applies innovative CL methodologies to address the challenging geometric problem of monocular Visual Odometry (VO) estimation, which is essential for robot navigation in constrained environments. The primary objective of our research is to push the boundaries of current state-of-the-art (SOTA) benchmarks in monocular VO by investigating various curriculum learning strategies. We enhance the end-to-end Deep-Patch-Visual Odometry (DPVO) framework through the integration of novel CL approaches, with the goal of developing more resilient models capable of maintaining high performance across challenging environments and complex motion scenarios. Our research encompasses several distinctive CL strategies. We develop methods to evaluate sample difficulty based on trajectory motion characteristics, implement sophisticated adaptive scheduling through self-paced weighted loss mechanisms, and utilize reinforcement learning agents for dynamic adjustment of training emphasis. Through comprehensive evaluation on the diverse synthetic TartanAir dataset and complex real-world benchmarks such as EuRoC and TUM-RGBD, our Curriculum Learning-based Deep-Patch-Visual Odometry (CL-DPVO) demonstrates superior performance compared to existing SOTA methods, including both feature-based and learning-based VO approaches. The results validate the effectiveness of integrating curriculum learning principles into visual odometry systems.
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。
