Social Attention for Autonomous Decision-Making in Dense Traffic

TL;DR

This paper introduces an attention-based learning architecture for behavioral planning in dense traffic, which handles variable numbers of vehicles, is invariant to their order, and improves decision-making accuracy.

Contribution

The paper proposes a novel attention mechanism architecture that effectively models interactions in dense traffic scenarios, outperforming existing representations.

Findings

Significant performance improvements over previous methods

Ability to visualize and interpret interaction patterns

Robust handling of varying numbers of traffic participants

Abstract

We study the design of learning architectures for behavioural planning in a dense traffic setting. Such architectures should deal with a varying number of nearby vehicles, be invariant to the ordering chosen to describe them, while staying accurate and compact. We observe that the two most popular representations in the literature do not fit these criteria, and perform badly on an complex negotiation task. We propose an attention-based architecture that satisfies all these properties and explicitly accounts for the existing interactions between the traffic participants. We show that this architecture leads to significant performance gains, and is able to capture interactions patterns that can be visualised and qualitatively interpreted. Videos and code are available at https://eleurent.github.io/social-attention/.