Interpretable End-to-End Driving Model for Implicit Scene Understanding

TL;DR

This paper introduces an interpretable end-to-end driving model that extracts implicit scene features aligned with planning, achieving state-of-the-art results and providing richer scene understanding for autonomous driving.

Contribution

The proposed II-DSU model uniquely extracts implicit scene features guided by planning, improving interpretability and downstream planning performance in autonomous driving.

Findings

Achieves state-of-the-art performance on CARLA benchmarks.

Extracts richer scene features relevant to driving tasks.

Enables better interpretability of scene understanding results.

Abstract

Driving scene understanding is to obtain comprehensive scene information through the sensor data and provide a basis for downstream tasks, which is indispensable for the safety of self-driving vehicles. Specific perception tasks, such as object detection and scene graph generation, are commonly used. However, the results of these tasks are only equivalent to the characterization of sampling from high-dimensional scene features, which are not sufficient to represent the scenario. In addition, the goal of perception tasks is inconsistent with human driving that just focuses on what may affect the ego-trajectory. Therefore, we propose an end-to-end Interpretable Implicit Driving Scene Understanding (II-DSU) model to extract implicit high-dimensional scene features as scene understanding results guided by a planning module and to validate the plausibility of scene understanding using auxiliary perception tasks for visualization. Experimental results on CARLA benchmarks show that our approach achieves the new state-of-the-art and is able to obtain scene features that embody richer scene information relevant to driving, enabling superior performance of the downstream planning.