Improving Autonomous Driving Safety with POP: A Framework for Accurate Partially Observed Trajectory Predictions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Sheng, Chen, Yingbing, Cheng, Jie, Mei, Xiaodong, Xin, Ren, Song, Yongkang, Liu, Ming
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929303523950592
author Wang, Sheng
Chen, Yingbing
Cheng, Jie
Mei, Xiaodong
Xin, Ren
Song, Yongkang
Liu, Ming
author_facet Wang, Sheng
Chen, Yingbing
Cheng, Jie
Mei, Xiaodong
Xin, Ren
Song, Yongkang
Liu, Ming
contents Accurate trajectory prediction is crucial for safe and efficient autonomous driving, but handling partial observations presents significant challenges. To address this, we propose a novel trajectory prediction framework called Partial Observations Prediction (POP) for congested urban road scenarios. The framework consists of two key stages: self-supervised learning (SSL) and feature distillation. POP first employs SLL to help the model learn to reconstruct history representations, and then utilizes feature distillation as the fine-tuning task to transfer knowledge from the teacher model, which has been pre-trained with complete observations, to the student model, which has only few observations. POP achieves comparable results to top-performing methods in open-loop experiments and outperforms the baseline method in closed-loop simulations, including safety metrics. Qualitative results illustrate the superiority of POP in providing reasonable and safe trajectory predictions.
format Preprint
id arxiv_https___arxiv_org_abs_2309_15685
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Improving Autonomous Driving Safety with POP: A Framework for Accurate Partially Observed Trajectory Predictions
Wang, Sheng
Chen, Yingbing
Cheng, Jie
Mei, Xiaodong
Xin, Ren
Song, Yongkang
Liu, Ming
Robotics
Accurate trajectory prediction is crucial for safe and efficient autonomous driving, but handling partial observations presents significant challenges. To address this, we propose a novel trajectory prediction framework called Partial Observations Prediction (POP) for congested urban road scenarios. The framework consists of two key stages: self-supervised learning (SSL) and feature distillation. POP first employs SLL to help the model learn to reconstruct history representations, and then utilizes feature distillation as the fine-tuning task to transfer knowledge from the teacher model, which has been pre-trained with complete observations, to the student model, which has only few observations. POP achieves comparable results to top-performing methods in open-loop experiments and outperforms the baseline method in closed-loop simulations, including safety metrics. Qualitative results illustrate the superiority of POP in providing reasonable and safe trajectory predictions.
title Improving Autonomous Driving Safety with POP: A Framework for Accurate Partially Observed Trajectory Predictions
topic Robotics
url https://arxiv.org/abs/2309.15685