Visual navigation requires a whole range of capabilities. A crucial one of these is the ability of an agent to determine its own location and heading in an environment. Prior works commonly assume this information as given, or use methods which lack a suitable inductive bias and accumulate error over time. In this work, we show how the method of slow feature analysis (SFA), inspired by neuroscience research, overcomes both limitations by generating interpretable representations of visual data that encode location and heading of an agent. We employ SFA in a modern reinforcement learning context, analyse and compare representations and illustrate where hierarchical SFA can outperform other feature extractors on navigation tasks.

翻译：视觉导航需要一系列能力，其中关键之一是智能体在环境中确定自身位置和朝向的能力。以往的工作通常假设这些信息已知，或使用缺乏合适归纳偏置且随时间累积误差的方法。在本工作中，我们展示了受神经科学启发的慢特征分析（SFA）方法如何通过生成编码智能体位置和朝向的可解释视觉数据表示，来克服上述两种局限性。我们将SFA应用于现代强化学习场景中，分析和比较其表示能力，并阐明分层SFA如何在导航任务上优于其他特征提取器。