Neural Map Prior for Autonomous Driving
- URL: http://arxiv.org/abs/2304.08481v2
- Date: Wed, 14 Jun 2023 17:10:00 GMT
- Title: Neural Map Prior for Autonomous Driving
- Authors: Xuan Xiong, Yicheng Liu, Tianyuan Yuan, Yue Wang, Yilun Wang, Hang
Zhao
- Abstract summary: High-definition (HD) semantic maps are crucial in enabling autonomous vehicles to navigate urban environments.
Traditional method of creating offline HD maps involves labor-intensive manual annotation processes.
Recent studies have proposed an alternative approach that generates local maps using online sensor observations.
In this study, we propose Neural Map Prior (NMP), a neural representation of global maps.
- Score: 17.198729798817094
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: High-definition (HD) semantic maps are crucial in enabling autonomous
vehicles to navigate urban environments. The traditional method of creating
offline HD maps involves labor-intensive manual annotation processes, which are
not only costly but also insufficient for timely updates. Recent studies have
proposed an alternative approach that generates local maps using online sensor
observations. However, this approach is limited by the sensor's perception
range and its susceptibility to occlusions. In this study, we propose Neural
Map Prior (NMP), a neural representation of global maps. This representation
automatically updates itself and improves the performance of local map
inference. Specifically, we utilize two approaches to achieve this. Firstly, to
integrate a strong map prior into local map inference, we apply
cross-attention, a mechanism that dynamically identifies correlations between
current and prior features. Secondly, to update the global neural map prior, we
utilize a learning-based fusion module that guides the network in fusing
features from previous traversals. Our experimental results, based on the
nuScenes dataset, demonstrate that our framework is highly compatible with
various map segmentation and detection architectures. It significantly improves
map prediction performance, even in challenging weather conditions and
situations with a longer perception range. To the best of our knowledge, this
is the first learning-based system for creating a global map prior.
Related papers
- Map-aided annotation for pole base detection [0.0]
In this paper, a 2D HD map is used to automatically annotate pole-like features in images.
In the absence of height information, the map features are represented as pole bases at the ground level.
We show how an object detector can be trained to detect a pole base.
arXiv Detail & Related papers (2024-03-04T09:23:11Z) - 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) - NeMO: Neural Map Growing System for Spatiotemporal Fusion in
Bird's-Eye-View and BDD-Map Benchmark [9.430779563669908]
Vision-centric Bird's-Eye View representation is essential for autonomous driving systems.
This work outlines a new paradigm, named NeMO, for generating local maps through the utilization of a readable and writable big map.
With an assumption that the feature distribution of all BEV grids follows an identical pattern, we adopt a shared-weight neural network for all grids to update the big map.
arXiv Detail & Related papers (2023-06-07T15:46:15Z) - Long-term Visual Map Sparsification with Heterogeneous GNN [47.12309045366042]
In this paper, we aim to overcome the environmental changes and reduce the map size at the same time by selecting points that are valuable to future localization.
Inspired by the recent progress in Graph Neural Network(GNN), we propose the first work that models SfM maps as heterogeneous graphs and predicts 3D point importance scores with a GNN.
Two novel supervisions are proposed: 1) a data-fitting term for selecting valuable points to future localization based on training queries; 2) a K-Cover term for selecting sparse points with full map coverage.
arXiv Detail & Related papers (2022-03-29T01:46:12Z) - HDMapNet: An Online HD Map Construction and Evaluation Framework [23.19001503634617]
HD map construction is a crucial problem for autonomous driving.
Traditional HD maps are coupled with centimeter-level accurate localization which is unreliable in many scenarios.
Online map learning is a more scalable way to provide semantic and geometry priors to self-driving vehicles.
arXiv Detail & Related papers (2021-07-13T18:06:46Z) - CAMERAS: Enhanced Resolution And Sanity preserving Class Activation
Mapping for image saliency [61.40511574314069]
Backpropagation image saliency aims at explaining model predictions by estimating model-centric importance of individual pixels in the input.
We propose CAMERAS, a technique to compute high-fidelity backpropagation saliency maps without requiring any external priors.
arXiv Detail & Related papers (2021-06-20T08:20:56Z) - 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) - Gaussian Process Gradient Maps for Loop-Closure Detection in
Unstructured Planetary Environments [17.276441789710574]
The ability to recognize previously mapped locations is an essential feature for autonomous systems.
Unstructured planetary-like environments pose a major challenge to these systems due to the similarity of the terrain.
This paper presents a method to solve the loop closure problem using only spatial information.
arXiv Detail & Related papers (2020-09-01T04:41:40Z) - 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) - Rethinking Localization Map: Towards Accurate Object Perception with
Self-Enhancement Maps [78.2581910688094]
This work introduces a novel self-enhancement method to harvest accurate object localization maps and object boundaries with only category labels as supervision.
In particular, the proposed Self-Enhancement Maps achieve the state-of-the-art localization accuracy of 54.88% on ILSVRC.
arXiv Detail & Related papers (2020-06-09T12:35:55Z)
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.