ParallelNet: Multi-mode Trajectory Prediction by Multi-mode Trajectory Fusion

TL;DR

ParallelNet introduces a multi-mode trajectory prediction architecture for autonomous vehicles by parallelizing CNN backbones and fusing features, aiding in safe path planning.

Contribution

It proposes a novel multi-mode trajectory prediction network that parallelizes CNNs and fuses features, advancing autonomous vehicle motion prediction.

Findings

Ranked 15th in 2020 ICRA Nuscene Prediction challenge

Demonstrates effectiveness of multi-mode trajectory fusion

Shows potential for improved autonomous driving safety

Abstract

Level 5 Autonomous Driving, a technology that a fully automated vehicle (AV) requires no human intervention, has raised serious concerns on safety and stability before widespread use. The capability of understanding and predicting future motion trajectory of road objects can help AV plan a path that is safe and easy to control. In this paper, we propose a network architecture that parallelizes multiple convolutional neural network backbones and fuses features to make multi-mode trajectory prediction. In the 2020 ICRA Nuscene Prediction challenge, our model ranks 15th on the leaderboard across all teams.