Trajectory Prediction for Autonomous Driving with Topometric Map
- URL: http://arxiv.org/abs/2105.03869v1
- Date: Sun, 9 May 2021 08:16:16 GMT
- Title: Trajectory Prediction for Autonomous Driving with Topometric Map
- Authors: Jiaolong Xu, Liang Xiao, Dawei Zhao, Yiming Nie, Bin Dai
- Abstract summary: State-of-the-art autonomous driving systems rely on high definition (HD) maps for localization and navigation.
We propose an end-to-end transformer networks based approach for map-less autonomous driving.
- Score: 10.831436392239585
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: State-of-the-art autonomous driving systems rely on high definition (HD) maps
for localization and navigation. However, building and maintaining HD maps is
time-consuming and expensive. Furthermore, the HD maps assume structured
environment such as the existence of major road and lanes, which are not
present in rural areas. In this work, we propose an end-to-end transformer
networks based approach for map-less autonomous driving. The proposed model
takes raw LiDAR data and noisy topometric map as input and produces precise
local trajectory for navigation. We demonstrate the effectiveness of our method
in real-world driving data, including both urban and rural areas. The
experimental results show that the proposed method outperforms state-of-the-art
multimodal methods and is robust to the perturbations of the topometric map.
The code of the proposed method is publicly available at
\url{https://github.com/Jiaolong/trajectory-prediction}.
Related papers
- MapLocNet: Coarse-to-Fine Feature Registration for Visual Re-Localization in Navigation Maps [8.373285397029884]
Traditional localization approaches rely on high-definition (HD) maps, which consist of precisely annotated landmarks.
We propose a novel transformer-based neural re-localization method, inspired by image registration.
Our method significantly outperforms the current state-of-the-art OrienterNet on both the nuScenes and Argoverse datasets.
arXiv Detail & Related papers (2024-07-11T14:51:18Z) - Augmenting Lane Perception and Topology Understanding with Standard
Definition Navigation Maps [51.24861159115138]
Standard Definition (SD) maps are more affordable and have worldwide coverage, offering a scalable alternative.
We propose a novel framework to integrate SD maps into online map prediction and propose a Transformer-based encoder, SD Map Representations from transFormers.
This enhancement consistently and significantly boosts (by up to 60%) lane detection and topology prediction on current state-of-the-art online map prediction methods.
arXiv Detail & Related papers (2023-11-07T15:42:22Z) - Prior Based Online Lane Graph Extraction from Single Onboard Camera
Image [133.68032636906133]
We tackle online estimation of the lane graph from a single onboard camera image.
The prior is extracted from the dataset through a transformer based Wasserstein Autoencoder.
The autoencoder is then used to enhance the initial lane graph estimates.
arXiv Detail & Related papers (2023-07-25T08:58:26Z) - Online Map Vectorization for Autonomous Driving: A Rasterization
Perspective [58.71769343511168]
We introduce a newization-based evaluation metric, which has superior sensitivity and is better suited to real-world autonomous driving scenarios.
We also propose MapVR (Map Vectorization via Rasterization), a novel framework that applies differentiableization to preciseized outputs and then performs geometry-aware supervision on HD maps.
arXiv Detail & Related papers (2023-06-18T08:51:14Z) - Exploring Navigation Maps for Learning-Based Motion Prediction [9.919575841909962]
We describe an approach to integrate navigation maps into learning-based motion prediction models.
Our approach shows a significant improvement over not using a map at all.
Our publicly available navigation map API for Argoverse enables researchers to develop and evaluate their own approaches using navigation maps.
arXiv Detail & Related papers (2023-02-13T09:06:27Z) - Coarse-to-fine Semantic Localization with HD Map for Autonomous Driving
in Structural Scenes [1.1024591739346292]
We propose a cost-effective vehicle localization system with HD map for autonomous driving using cameras as primary sensors.
We formulate vision-based localization as a data association problem that maps visual semantics to landmarks in HD map.
We evaluate our method on two datasets and demonstrate that the proposed approach yields promising localization results in different driving scenarios.
arXiv Detail & Related papers (2021-07-06T11:58:55Z) - MP3: A Unified Model to Map, Perceive, Predict and Plan [84.07678019017644]
MP3 is an end-to-end approach to mapless driving where the input is raw sensor data and a high-level command.
We show that our approach is significantly safer, more comfortable, and can follow commands better than the baselines in challenging long-term closed-loop simulations.
arXiv Detail & Related papers (2021-01-18T00:09:30Z) - DAGMapper: Learning to Map by Discovering Lane Topology [84.12949740822117]
We focus on drawing the lane boundaries of complex highways with many lanes that contain topology changes due to forks and merges.
We formulate the problem as inference in a directed acyclic graphical model (DAG), where the nodes of the graph encode geometric and topological properties of the local regions of the lane boundaries.
We show the effectiveness of our approach on two major North American Highways in two different states and show high precision and recall as well as 89% correct topology.
arXiv Detail & Related papers (2020-12-22T21:58:57Z) - Radar-based Dynamic Occupancy Grid Mapping and Object Detection [55.74894405714851]
In recent years, the classical occupancy grid map approach has been extended to dynamic occupancy grid maps.
This paper presents the further development of a previous approach.
The data of multiple radar sensors are fused, and a grid-based object tracking and mapping method is applied.
arXiv Detail & Related papers (2020-08-09T09:26:30Z) - Automatic Building and Labeling of HD Maps with Deep Learning [18.9340830352492]
We propose a novel method capable of generating labelled HD maps from raw sensor data.
The results show that the pro-posed deep learning based method can produce highly accurate HD maps.
arXiv Detail & Related papers (2020-06-01T00:02:45Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.