Abstract Building “always-on” robots to be deployed over extended periods of time in real human environments is challenging for several reasons. Some fundamental questions that arise in the process include: 1) How can the robot reconcile unexpected differences between its observations and its map of the world? 2) How can we scalably test robots for longterm autonomy? 3) Can a robot learn to predict its own failures, and their corresponding causes? 4) When the robot fails and is unable to recover autonomously, can it utilize partially specifified human corrections to overcome its failures? This paper summarizes our research towards addressing all of these questions. We present 1) Episodic nonMarkov Localization to maintain the belief of the robot’s location while explicitly reasoning about unmapped observations; 2) a 1, 000km Challenge to test for long-term autonomy; 3) feature-based and learning-based approaches to predicting failures; and 4) human-in-the-loop SLAM to overcome robot mapping errors, and SMT-based robot transition repair to overcome state machine failures