Social Attention for Autonomous Decision-Making in Dense Traffic
This addresses autonomous decision-making in dense traffic for self-driving cars, representing an incremental improvement over existing methods.
The paper tackles the problem of designing learning architectures for behavioral planning in dense traffic, which must handle varying numbers of vehicles and be invariant to ordering, and proposes an attention-based architecture that leads to significant performance gains.
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/.