RedMotion: Motion Prediction via Redundancy Reduction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wagner, Royden, Tas, Omer Sahin, Klemp, Marvin, Fernandez, Carlos, Stiller, Christoph
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916668635086848
author Wagner, Royden
Tas, Omer Sahin
Klemp, Marvin
Fernandez, Carlos
Stiller, Christoph
author_facet Wagner, Royden
Tas, Omer Sahin
Klemp, Marvin
Fernandez, Carlos
Stiller, Christoph
contents We introduce RedMotion, a transformer model for motion prediction in self-driving vehicles that learns environment representations via redundancy reduction. Our first type of redundancy reduction is induced by an internal transformer decoder and reduces a variable-sized set of local road environment tokens, representing road graphs and agent data, to a fixed-sized global embedding. The second type of redundancy reduction is obtained by self-supervised learning and applies the redundancy reduction principle to embeddings generated from augmented views of road environments. Our experiments reveal that our representation learning approach outperforms PreTraM, Traj-MAE, and GraphDINO in a semi-supervised setting. Moreover, RedMotion achieves competitive results compared to HPTR or MTR++ in the Waymo Motion Prediction Challenge. Our open-source implementation is available at: https://github.com/kit-mrt/future-motion
format Preprint
id arxiv_https___arxiv_org_abs_2306_10840
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle RedMotion: Motion Prediction via Redundancy Reduction
Wagner, Royden
Tas, Omer Sahin
Klemp, Marvin
Fernandez, Carlos
Stiller, Christoph
Computer Vision and Pattern Recognition
Robotics
We introduce RedMotion, a transformer model for motion prediction in self-driving vehicles that learns environment representations via redundancy reduction. Our first type of redundancy reduction is induced by an internal transformer decoder and reduces a variable-sized set of local road environment tokens, representing road graphs and agent data, to a fixed-sized global embedding. The second type of redundancy reduction is obtained by self-supervised learning and applies the redundancy reduction principle to embeddings generated from augmented views of road environments. Our experiments reveal that our representation learning approach outperforms PreTraM, Traj-MAE, and GraphDINO in a semi-supervised setting. Moreover, RedMotion achieves competitive results compared to HPTR or MTR++ in the Waymo Motion Prediction Challenge. Our open-source implementation is available at: https://github.com/kit-mrt/future-motion
title RedMotion: Motion Prediction via Redundancy Reduction
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2306.10840