SCOUT: Socially-COnsistent and UndersTandable Graph Attention Network for Trajectory Prediction of Vehicles and VRUs

TL;DR

SCOUT is a novel graph attention network that models interactions among agents in dynamic environments, accurately predicting trajectories of vehicles and VRUs across diverse traffic scenarios, enhancing autonomous navigation safety.

Contribution

Introduces SCOUT, a flexible graph neural network with multiple attention mechanisms for socially-consistent trajectory prediction in mixed traffic conditions.

Findings

Outperforms state-of-the-art on InD and ApolloScape benchmarks.

Demonstrates transferability to new scenarios on RounD dataset.

Provides interpretability of interaction influences via attention visualization.

Abstract

Autonomous vehicles navigate in dynamically changing environments under a wide variety of conditions, being continuously influenced by surrounding objects. Modelling interactions among agents is essential for accurately forecasting other agents' behaviour and achieving safe and comfortable motion planning. In this work, we propose SCOUT, a novel Attention-based Graph Neural Network that uses a flexible and generic representation of the scene as a graph for modelling interactions, and predicts socially-consistent trajectories of vehicles and Vulnerable Road Users (VRUs) under mixed traffic conditions. We explore three different attention mechanisms and test our scheme with both bird-eye-view and on-vehicle urban data, achieving superior performance than existing state-of-the-art approaches on InD and ApolloScape Trajectory benchmarks. Additionally, we evaluate our model's flexibility and transferability by testing it under completely new scenarios on RounD dataset. The importance and influence of each interaction in the final prediction is explored by means of Integrated Gradients technique and the visualization of the attention learned.