Traffic Scenario Clustering by Iterative Optimisation of Self-Supervised Networks Using a Random Forest Activation Pattern Similarity

TL;DR

This paper introduces a novel clustering method for traffic scenarios that combines self-supervised CNNs, iterative optimization, and a new RFAP similarity measure, improving scenario categorization for autonomous driving.

Contribution

It presents a new adaptive similarity measure and an iterative clustering approach that leverages both labeled and unlabeled data to enhance traffic scenario categorization.

Findings

Outperforms baseline clustering methods on highD dataset.

Effective integration of RFAP similarity improves clustering accuracy.

Iterative optimization refines feature representations for better clustering.

Abstract

Traffic scenario categorisation is an essential component of automated driving, for e.\,g., in motion planning algorithms and their validation. Finding new relevant scenarios without handcrafted steps reduce the required resources for the development of autonomous driving dramatically. In this work, a method is proposed to address this challenge by introducing a clustering technique based on a novel data-adaptive similarity measure, called Random Forest Activation Pattern (RFAP) similarity. The RFAP similarity is generated using a tree encoding scheme in a Random Forest algorithm. The clustering method proposed in this work takes into account that there are labelled scenarios available and the information from the labelled scenarios can help to guide the clustering of unlabelled scenarios. It consists of three steps. First, a self-supervised Convolutional Neural Network~(CNN) is trained on all available traffic scenarios using a defined self-supervised objective. Second, the CNN is fine-tuned for classification of the labelled scenarios. Third, using the labelled and unlabelled scenarios an iterative optimisation procedure is performed for clustering. In the third step at each epoch of the iterative optimisation, the CNN is used as a feature generator for an unsupervised Random Forest. The trained forest, in turn, provides the RFAP similarity to adapt iteratively the feature generation process implemented by the CNN. Extensive experiments and ablation studies have been done on the highD dataset. The proposed method shows superior performance compared to baseline clustering techniques.