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.

翻译：随着机器人技术的持续进步，对具备适应性和持续学习能力的具身智能体的需求日益增长，尤其在辅助机器人领域。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典型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对此鲜有探讨。本研究实证调查了在具身环境中持续训练的神经网络中灾难性遗忘的影响以及知识迁移的有效性。我们聚焦于视觉里程计任务，该任务对于实现具身智能体的自定位至关重要。我们在离散室内场景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。在此机制下，我们观察到初始阶段具有令人满意的性能及环境间的高度可迁移性，随后进入专业化阶段，模型优先获取当前环境特定知识而牺牲了泛化能力。传统的正则化策略和增加模型容量被证明无法有效缓解此现象。回放策略虽略有裨益，但需付出巨大的内存代价。引入具身环境中常用的动作信息可加速收敛，但会加剧专业化倾向，使模型过度依赖其运动预期而降低正确解读视觉线索的能力。这些发现凸显了终身机器人学中平衡适应性与记忆保留的开放性挑战，并为终身学习范式在具身智能体中的应用提供了宝贵见解。