Decoder Fusion RNN: Context and Interaction Aware Decoders for Trajectory Prediction

TL;DR

This paper introduces DF-RNN, a novel attention-based recurrent model that fuses map, agent interactions, and context information for improved trajectory prediction in autonomous driving, achieving state-of-the-art results.

Contribution

The paper presents a new Decoder Fusion RNN architecture that effectively combines map and agent interaction data within the decoder for enhanced motion forecasting.

Findings

Achieves state-of-the-art performance on Argoverse dataset

Effectively fuses map and interaction information within the decoder

Demonstrates the importance of explicit training for model effectiveness

Abstract

Forecasting the future behavior of all traffic agents in the vicinity is a key task to achieve safe and reliable autonomous driving systems. It is a challenging problem as agents adjust their behavior depending on their intentions, the others' actions, and the road layout. In this paper, we propose Decoder Fusion RNN (DF-RNN), a recurrent, attention-based approach for motion forecasting. Our network is composed of a recurrent behavior encoder, an inter-agent multi-headed attention module, and a context-aware decoder. We design a map encoder that embeds polyline segments, combines them to create a graph structure, and merges their relevant parts with the agents' embeddings. We fuse the encoded map information with further inter-agent interactions only inside the decoder and propose to use explicit training as a method to effectively utilize the information available. We demonstrate the efficacy of our method by testing it on the Argoverse motion forecasting dataset and show its state-of-the-art performance on the public benchmark.