Autonomous Vehicle Perception: The Technology of Today and Tomorrow

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Electrical and Autonomous Vehicles".

Deadline for manuscript submissions: closed (31 January 2023) | Viewed by 2632

Special Issue Editors


E-Mail Website
Guest Editor
Virtual Vehicle Research GmbH, Inffeldgasse 21a, 8010 Graz, Austria
Interests: automated driving; ADAS development and testing; autonomous systems; control theory; vehicle dynamics, dynamics and control; active safety

E-Mail Website
Guest Editor
Virtual Vehicle Research GmbH, Inffeldgasse 21a, 8010 Graz, Austria
Interests: control system design; system identification and state estimation; environment perception approaches based on sensor fusion; fault diagnosis and sensor monitoring, real-time co-simulation

Special Issue Information

Dear colleagues,

Autonomous driving (AD) and advanced driver assistance systems (ADAS) involve a typical “sense-plan-act” cycle that was initially developed in the context of robot control. The first and perhaps the most important step of this cycle is the sensing or “perception” of the surrounding environment using on-board and/or infrastructure sensors, which provides the necessary information for the subsequent planning and control steps. The sensors often include superfluous combinations of camera, Lidar, radar, and ultrasonic sensors, which need to be fused in an efficient manner to ensure a robust and fail-operational surround perception, often utilizing AI methods. This very same goal poses the biggest challenge for ADAS/AD systems, since perception systems require extensive calibration, testing, and validation to ensure that the related ADAS/AD functions behave as expected in a multitude of traffic scenarios. Conventional automotive testing and validation methods are neither suitable nor feasible for this purpose. It is therefore in the interest of developers and OEMs to ensure that ADAS/AD systems conform to reliability, compliance, performance, and fault-tolerance requirements in a cost effective and efficient manner. One major challenge for this, among others, is to find generally accepted key scenarios and their corresponding KPIs for the evaluation of automotive perception systems and the corresponding ADAS and AD functions. Given these facts, there is an increasing interest in novel testing, verification, and validation concepts.

This Special Issue aims to bring industry and academia together to exchange ideas, experiences, and research results on perception systems for ADAS/AD applications as well as related testing, verification, validation, and certification methodologies.

Prof. Dr. Selim Solmaz
Dr. Georg Stettinger
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • novel perception system solutions for automated vehicles
  • testing, verification, and validation of perception systems
  • sensor models and simulation
  • sensors and sensor fusion methodologies for autonomous driving
  • datasets for development and verification of perception systems
  • benchmarks and comparisons of perception system solutions
  • use of perception for traffic prediction and control
  • intention monitoring of vulnerable road users
  • dependable machine learning and AI for automated driving
  • standardization and certification of perception systems

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

16 pages, 3106 KiB  
Article
AGS-SSD: Attention-Guided Sampling for 3D Single-Stage Detector
by Hanxiang Qian, Peng Wu, Bei Sun and Shaojing Su
Electronics 2022, 11(14), 2268; https://doi.org/10.3390/electronics11142268 - 20 Jul 2022
Cited by 2 | Viewed by 1755
Abstract
3D object detection based on LiDAR point cloud has always been challenging. Existing point cloud downsampling approaches often use heuristic algorithms such as farthest point sampling (FPS) to extract the features from a massive raw point cloud. However, FPS has disadvantages such as [...] Read more.
3D object detection based on LiDAR point cloud has always been challenging. Existing point cloud downsampling approaches often use heuristic algorithms such as farthest point sampling (FPS) to extract the features from a massive raw point cloud. However, FPS has disadvantages such as low operating efficiency and inability to sample key areas. This paper presents an attention-guided downsampling method for point-cloud-based 3D object detection, named AGS-SSD. The method contains two modules: PEA (point external attention) and A-FPS (attention-guided FPS). PEA explores the correlation between the data and uses the external attention mechanism to extract the semantic features in the set abstraction stage. The semantic information, including the relationship between the samples, is sent to the candidate point generation module as context points. A-FPS weighs the point cloud according to the generated attention map and samples the foreground points with rich semantic information as candidate points. The experimental results show that our method achieves significant improvements with novel architectures against the baseline and runs at 24 frames per second for inference. Full article
(This article belongs to the Special Issue Autonomous Vehicle Perception: The Technology of Today and Tomorrow)
Show Figures

Figure 1

Back to TopTop