Evaluating Temporal Observation-Based Causal Discovery Techniques Applied to Road Driver Behaviour

TL;DR

This paper benchmarks 10 observational temporal causal discovery methods in autonomous driving, highlighting their limitations in real-world scenarios and suggesting directions for future improvements.

Contribution

It provides a comprehensive evaluation of current causal discovery techniques in autonomous driving, emphasizing their challenges and proposing future research directions.

Findings

Current methods struggle with causal sparsity and non-stationarity.

Benchmark reveals gaps in real-world applicability.

Discussion of future research directions.

Abstract

Autonomous robots are required to reason about the behaviour of dynamic agents in their environment. The creation of models to describe these relationships is typically accomplished through the application of causal discovery techniques. However, as it stands observational causal discovery techniques struggle to adequately cope with conditions such as causal sparsity and non-stationarity typically seen during online usage in autonomous agent domains. Meanwhile, interventional techniques are not always feasible due to domain restrictions. In order to better explore the issues facing observational techniques and promote further discussion of these topics we carry out a benchmark across 10 contemporary observational temporal causal discovery methods in the domain of autonomous driving. By evaluating these methods upon causal scenes drawn from real world datasets in addition to those generated synthetically we highlight where improvements need to be made in order to facilitate the application of causal discovery techniques to the aforementioned use-cases. Finally, we discuss potential directions for future work that could help better tackle the difficulties currently experienced by state of the art techniques.