Learn from Experience: Probabilistic Prediction of Perception Performance to Avoid Failure
Abstract –Despite the significant advances in machine learning and perception over the past few decades, perception algorithms can still be unreliable when deployed in challenging, time-varying environments. When these systems are used for autonomous decision-making, such as in self-driving vehicles, the impact of their mistakes can be catastrophic. As such, it is important to characterise the performance of the system and predict when and where it may fail in order to take appropriate action. This is related to the paradigm of introspection, in which a model must assign a measure of confidence or trust to its predictions. This paper explores the idea of predicting the likely performance of a robot’s perception system based on past experience in the same workspace. In particular, we propose two models that probabilistically predict perception performance from observations gathered over time. While both approaches are place-specific, the second approach additionally considers appearance similarity when considering past observations. We evaluate our method in a classical decision making scenario in which the robot must choose when and where to drive autonomously in 60km of driving data from an urban environment. Results demonstrate that both approaches lead to fewer false decisions (in terms of incorrectly offering or denying autonomy) for two different detector models, and show that leveraging visual appearance within a state-of-the-art navigation framework increases the accuracy of our performance predictions.