3rd Place Solution for NeurIPS 2021 Shifts Challenge: Vehicle Motion Prediction

TL;DR

This paper presents a novel architecture with self-attention and a specialized loss function for vehicle motion prediction under distributional shifts, achieving third place in the NeurIPS 2021 challenge.

Contribution

The paper introduces a new backbone architecture incorporating self-attention and a tailored loss function for improved robustness in cross-domain motion prediction.

Findings

Achieved third place in NeurIPS 2021 Shifts Challenge.

Demonstrated improved robustness under real-world distributional shifts.

Proposed architecture outperforms baseline models in the challenge.

Abstract

Shifts Challenge: Robustness and Uncertainty under Real-World Distributional Shift is a competition held by NeurIPS 2021. The objective of this competition is to search for methods to solve the motion prediction problem in cross-domain. In the real world dataset, It exists variance between input data distribution and ground-true data distribution, which is called the domain shift problem. In this report, we propose a new architecture inspired by state of the art papers. The main contribution is the backbone architecture with self-attention mechanism and predominant loss function. Subsequently, we won 3rd place as shown on the leaderboard.