持续视觉里程计中遗忘与迁移的实证影响
The Empirical Impact of Forgetting and Transfer in Continual Visual Odometry
AI总结：
本研究实证调查了具身环境下持续训练的视觉里程计神经网络中灾难性遗忘与知识迁移的影响，发现模型经历从高可迁移性到环境专门化的转变，常规正则化和增加容量无效，排练练习略有裨益但增加记忆成本，融入动作信息加速收敛却加剧专门化。
摘要：
随着机器人技术的不断进步，对自适应和持续学习的具身智能体的需求日益增加，尤其是在辅助机器人领域。快速适应能力和长期信息保留能力对于在人类日常生活的动态环境中运行至关重要。因此需要一种终身学习范式，但当前机器人学文献很少涉及这一问题。本研究实证调查了在具身环境中持续训练的神经网络的灾难性遗忘影响和知识迁移的有效性。我们聚焦于视觉里程计任务，该任务对于具身智能体实现自定位具有首要重要性。我们在室内位置间离散转换的简单持续场景中进行实验，类似于机器人在不同公寓间导航。在这种机制下，我们观察到初始性能良好，环境间具有高可迁移性，随后进入专门化阶段，模型优先考虑当前环境特定知识而牺牲泛化能力。传统正则化策略和增加模型容量在缓解这一现象方面被证明无效。排练练习反而略有裨益，但增加了大量记忆成本。融入动作信息（如具身环境中的常见做法）可加快收敛速度，但会加剧专门化，使模型过度依赖其运动预期，从而降低正确解读视觉线索的能力。这些发现强调了在终身机器人技术中平衡适应与记忆保留的开放性挑战，并为终身范式在具身智能体上的应用提供了宝贵见解。
英文摘要：
As robotics continues to advance, the need for adaptive and continuously-learning embodied agents increases, particularly in the realm of assistance robotics. Quick adaptability and long-term information retention are essential to operate in dynamic environments typical of humans' everyday lives. A lifelong learning paradigm is thus required, but it is scarcely addressed by current robotics literature. This study empirically investigates the impact of catastrophic forgetting and the effectiveness of knowledge transfer in neural networks trained continuously in an embodied setting. We focus on the task of visual odometry, which holds primary importance for embodied agents in enabling their self-localization. We experiment on the simple continual scenario of discrete transitions between indoor locations, akin to a robot navigating different apartments. In this regime, we observe initial satisfactory performance with high transferability between environments, followed by a specialization phase where the model prioritizes current environment-specific knowledge at the expense of generalization. Conventional regularization strategies and increased model capacity prove ineffective in mitigating this phenomenon. Rehearsal is instead mildly beneficial but with the addition of a substantial memory cost. Incorporating action information, as commonly done in embodied settings, facilitates quicker convergence but exacerbates specialization, making the model overly reliant on its motion expectations and less adept at correctly interpreting visual cues. These findings emphasize the open challenges of balancing adaptation and memory retention in lifelong robotics and contribute valuable insights into the application of a lifelong paradigm on embodied agents.
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。
