Autonomous Vehicles Research Articles

3D coherent single shot lidar imaging beyond coherence length

Advancements in remote sensing and autonomous vehicle technologies made lidars equally important for unmanned objects alongside cameras. Therefore, precise 3D lidar imaging and point cloud generation have become important subjects. Although existing coherent lidar technologies provide precise imaging results, the spectral linewidth of the laser sources becomes a key limitation over long distances as it defines the maximum detection range. Here, we present long-distance 3D lidar imaging which removes the coherence length limitations and therefore the necessity of high-coherence laser sources. Mainly, we generate optical sidebands, by modulating a continuous wave (CW) laser source with multiple radio-frequency (RF) tones. Then, using our own post-processing and triangulation methods, we use the relative phase changes between the sidebands which are free from laser phase noise to determine the target distance. We prove that the multi-tone coherent Lidar technique can perform precise 3D imaging and point cloud generation of various targets at sub-10pW optical power reception and distances up to ∼12× beyond the coherence length of the CW laser employed in the lidar architecture. Overall, it is demonstrated that coherence length restriction is removed by the suggested method, which makes precise long-distance 3D lidar imaging possible, particularly for applications such as spacecraft and aerial coherent lidars.

Real-time localization with probabilistic maps and unscented kalman filtering: a dynamic sensor fusion approach

This paper presents a robust position estimation technique for autonomous vehicles navigating urban and highway environments. It employs a probabilistic framework, integrating Monte Carlo simulation and Bayesian filtering via particle filters to represent position estimates beyond Gaussian distributions. To improve accuracy, Unscented Kalman Filtering (UKF) is used to fuse radar and lidar data, facilitating the detection of static, pole-like objects. These objects are matched with landmarks from a detailed reference map generated through 3D lidar scans. The proposed method addresses both lateral and longitudinal localisation challenges, ensuring precise vehicle positioning. Comprehensive simulation tests validate the system's effectiveness, demonstrating reliable performance across various driving conditions.

Advancing Vehicle Trajectory Prediction: A Probabilistic Approach Using Combined Sequential Models

Abstract This paper addresses the critical need to quantify vehicle trajectory uncertainty in autonomous driving under environmental variability. We focus on predicting the posterior distribution of vehicle trajectories over a fixed horizon, given an initial state and a sequence of actions. We propose and compare three approaches: a probabilistic seq2seq model based on stochastic variational Gaussian processes, sequential Monte Carlo simulation with a single-step Gaussian process model, and a hybrid model that leverages the strengths of both methods. Each approach incorporates a baseline vehicle kinematics model to enhance stability and convergence. We evaluate these methods using a dataset generated from the CARLA simulator, assessing both point error metrics and probabilistic prediction metrics. This research introduces novel approaches to quantifying vehicle trajectory uncertainty through various uncertainty quantification techniques, with the goal of improving the safety and reliability of autonomous vehicle control systems.

Steer-by-wire Actuator with Direct Drive for Autonomous Vehicles

Steer-by-wire Actuator with Direct Drive for Autonomous Vehicles

Blockchain-based fast handover authentication protocol for Internet of Vehicles in small industrial parks

Autonomous vehicles safeguard the security and efficiency of Internet of Vehicles systems in small industrial parks by authenticating and exchanging real-time information with transportation infrastructure. Deploying a multi-server framework reduces the risk of message blocking and privacy information leakage from centralized services. However, in traditional handover authentication protocols, there are still potential security risks such as high-overhead performance issues and single point of failure attacks. Therefore, it is considered challenging to realize efficient authentication while protecting the privacy of vehicles. In this paper, we propose a secure and efficient handover authentication protocol for autonomous vehicles in a small industrial park to address the challenges. The protocol is based on blockchain and Pedersen verifiable secret sharing scheme, which not only ensures lightweight real-time interactions between autonomous vehicles and edge servers in multi-server environments, but also strictly protects the security and privacy of both vehicles and edge servers. We prove the semantic security of the protocol under the Real-Or-Random model and perform a informal analysis of its security attributes to show that it can withstand a wide range of malicious attacks. Performance evaluation shows that the proposed protocol satisfies more security requirements and has better computational efficiency and communication cost than other related protocols.

Transferability of real-time EVT safety models: an investigation using autonomous vehicles data

Recent research has shown that data from autonomous vehicles (AVs) enables proactive, real-time road safety management. However, with low AV market penetration, it's crucial to assess the transferability of AV-based safety models to other locations. This study transfers real-time safety models from a data-rich to a data-scarce environment using vehicular conflict data collected by AVs. Multi-site Bayesian hierarchical Extreme Value Theory models are developed in two cities, with model transfer evaluated using informative priors and parameter recalibration. Both approaches produce reliable results, though the transferability index favors the informed prior method, while predictive deviance shows similar performance for both. Model sensitivity to temporal data limitations is assessed, revealing that the recalibration approach is more sensitive to block size, whereas the informed prior method remains stable. A novel method mimicking data limitations shows transferred models perform well with data utilizations above 20%, promoting transferability to mitigate data inadequacy.

Deep learning-based improved transformer model on android malware detection and classification in internet of vehicles

With the growing popularity of autonomous vehicles (AVs), confirming their safety has become a significant concern. Vehicle manufacturers have combined the Android operating system into AVs to improve consumer comfort. However, the diversity and weaknesses of the Android operating system pose substantial safety risks to AVs, as these factors can expose them to threats, namely Android malware. The advanced behaviour of multi-data source fusion in autonomous driving models has mitigated recognition accuracy and effectualness for Android malware. To efficiently counter new malware variants, novel techniques distinct from conventional methods must be utilized. Machine learning (ML) techniques cannot detect every new and complex malware variant. The deep learning (DL) model is an efficient tool for detecting various malware variants. This manuscript proposes a Deep Learning-Based Improved Transformer Model on Android Malware Detection (DLBITM-AMD) technique for Internet vehicles (IoVs). The main aim of the presented DLBITM-AMD approach is to detect Android malware effectually and accurately. The DLBITM-AMD method performs a Z-score normalization process to convert the raw data into a standard form. Then, the DLBITM-AMD approach utilizes the binary grey wolf optimization (BGWO) model to select optimum feature subsets. An improved transformer is integrated with the RNN model and softmax to enhance classification for Android malware recognition. Finally, the snake optimizer algorithm (SOA) method is employed to select the optimum parameter for the classification method. An extensive experiment of the DLBITM-AMD method is accomplished on a benchmark dataset. The performance validation of the DLBITM-AMD technique portrayed a superior accuracy value of 99.26% over existing Android malware recognition models.

Improved lane detection for autonomous vehicles using deep learning, semantic segmentation, edge detection and multi-sensor data fusion

Automated driving has gained significant attention because it can eliminate severe driving risks in real time. While autonomous vehicles rely heavily on sensors for lane detection, obstacle identification, and environmental awareness, accurate lane recognition remains a persistent challenge due to factors such as noise from shadows, poor lane markings, and obstructed views. Despite advances in computer vision, this problem is yet to be fully resolved, presenting a gap in the current literature. The primary objective of this research is to address these challenges by developing an enhanced lane-detection system. To achieve this, the study integrates advanced techniques, including semantic segmentation, edge detection, and deep learning, coupled with multi-sensor data fusion from cameras, LIDAR, and radar. By employing this methodology, the research examines various lane-detection methods and benchmarks the proposed model against existing systems in terms of accuracy, specificity and processing speed. Initial findings demonstrate that the combination of semantic segmentation and multi-sensor fusion improves lane detection in real-time scenarios. The proposed model achieved a lane detection accuracy of 97.8%, a specificity of 99.28%, and an average processing time of 0.0047 seconds per epoch. This study not only addresses the limitations of existing lane detection systems but also offers insights into improving road safety for autonomous vehicles.

Assessing energy consumption in scalable semi-autonomous destination-based E-platoons: A multiplayer approach

Recent developments in connected and automated vehicle technologies have opened up new possibilities but also posed enduring challenges. One of the primary challenges is the efficient coordination of vehicles in urban environments, specifically through scalable and destination-based platooning. While considerable research has focused on platooning with a limited number of vehicles demonstrating seamless connectivity and coordination on highways, there remains a significant gap in understanding and implementing scalable platoons in more dynamic urban settings. This paper bridges these gaps by developing a novel extension to the 3DCoAutosim simulation platform. Our model introduces ’Scalable Semi-autonomous Destination-based Multiplayer E-Platoons’, accommodating different automation levels and simulation characteristics of vehicles in five distinct platoons. We employed seven electric vehicles to create these platoons, each consisting of an autonomous lead vehicle, followers that are either autonomous or semi-autonomous (accompanied by drivers), customised according to the specific requirements of each platoon. Utilising Time Series Analysis, Multiple Linear Regression and a comprehensive, comparative scenario-based analysis, we assessed and validated our developed model’s impact on battery energy consumption under varying road slopes and car-following models. Our assessment employs real-world trip data from Upper Austria, with results indicating a potential reduction in total battery energy consumption when operating in platoon mode.

Use of Remote Focus Groups to Improve Inclusive Design Practice

This study examines the use of remote focus groups to obtain wheeled mobility device user’s ideas regarding Shared Autonomous Vehicles (SAVs). Given the global increase in the aging population and disabled people, inclusive design is essential for accessible transportation. Using remote focus groups, this research collected statements from nine wheeled mobility device users about their design preferences, needs, and challenges with SAVs. Participants attended four virtual sessions featured with presentations and videos of SAVs. Discussions were video recorded in Zoom, with transcripts reviewed for accuracy. Data analysis included cleaning, coding, and assessing interrater reliability using the ICC. The findings not reported here highlighted the diverse needs and preferences of participants, emphasizing the importance of collecting information from this group early in the design process. This study shows well-planned remote focus groups can be an effective tool to gather human factors system design information from user populations that face transportation barriers.

MFE-SSNet: Multi-Modal Fusion-Based End-to-End Steering Angle and Vehicle Speed Prediction Network

AbstractIn the field of autonomous vehicles, accurately predicting steering angle and speed is a pivotal task. This task affects the accuracy of the final decision of the autonomous vehicle and is the basis for ensuring the safe and efficient operation of the autonomous vehicle. Previous studies have often relied on data from only one or two modalities to make predictions for steering angle and vehicle speed, which were often inadequate. In this paper, the authors propose a Multi-Modal Fusion-Based End-to-End Steering Angle and Vehicle Speed Prediction Network (MFE-SSNet). The network innovatively extends the one-stream and two-stream structure to a three-stream structure and cleverly extracts features of images, steering angles, and vehicle speeds using HRNet and LSTM layers. In addition, in order to fully fuse the feature information of different modal data, this paper also proposes a local attention-based feature fusion module. This module improves the fusion of different modal feature vectors by capturing the interdependencies in the local channels. Experimental results demonstrate that MFE-SSNet outperforms the current state-of-the-art model on the publicly available Udacity dataset.

Fostering User Acceptance in Shared Autonomous Vehicles: A Framework for HMI Design

Fostering User Acceptance in Shared Autonomous Vehicles: A Framework for HMI Design

Trajectory Planning for Autonomous Vehicle with Numerical Optimization Method

Trajectory Planning for Autonomous Vehicle with Numerical Optimization Method

AEFF-SSC: an attention-enhanced feature fusion for 3D semantic scene completion

Abstract Three-dimensional (3D) occupancy perception technology aims to enable autonomous vehicles to observe and understand dense 3D environments. Estimating the complete geometry and semantics of a scene solely from visual images is challenging. However, humans can easily conceive the complete form of objects based on partial key information and their own experience. This ability is crucial for recognizing and interpreting the surrounding environment. To equip 3D occupancy perception systems with a similar capability, a 3D semantic scene completion method called AEFF-SSC is proposed. This method deeply explores boundary and multi-scale information in voxels, aiming to reconstruct 3D geometry more accurately. We have specifically designed an attention-enhanced feature fusion module that effectively fuses image feature information from different scales and focuses on feature boundary information, thereby more efficiently extracting voxel features. Additionally, we introduce a semantic segmentation module driven by a 3D attention-UNet network. This module combines a 3D U-Net network with a 3D attention mechanism. Through feature fusion and feature weighting, it aids in restoring 3D spatial information and significantly improves the accuracy of segmentation results. Experimental verification on the SemanticKITTI dataset demonstrates that AEFF-SSC significantly outperforms other existing methods in terms of both geometry and semantics. Specifically, within a 12.8 m × 12.8 m area ahead, our geometric occupancy accuracy has achieved a significant improvement of 71.58%, and at the same time, the semantic segmentation accuracy has also increased remarkably by 54.20%.

A Design Method for Road Vehicles with Autonomous Driving Control

The past three decades have witnessed extensive studies on motion-planning and tracking-control for autonomous vehicles (AVs). There is, however, a lack of studies on effective design methods for AVs, which consist of the subsystems of the mechanical vehicle, tracking-control, motion-planning, etc. To tackle this problem, this paper proposes a design approach for AVs. The proposed method features a design framework with two layers: at the upper layer, a particle swarm optimization (PSO) algorithm serves as a solver to a multi-objective optimization problem for desired AV trajectory-tracking performance; at the lower layer, a coupled dynamic analysis is conducted among the three subsystems, i.e., a nonlinear model for the mechanical vehicle, a motion-planning module, and a controller based on nonlinear model predictive control (NLMPC) for direction control. The simulation results demonstrate that the proposed method can effectively determine the desired design variables for the NLMPC controller and the mechanical vehicle to achieve optimal trajectory-tracking performance. The research findings from this work provide guidelines for designing AVs.

Branch-and-Price for the Capacitated Autonomous Vehicle Assisted Delivery Problem

In recent years, the exponential growth of package volumes has posed significant challenges for logistics networks, particularly in the realm of last-mile delivery. To mitigate costs while upholding service and delivery commitments, companies are increasingly investigating autonomous assisted delivery as a viable solution. In this paper, we study the Capacitated Autonomous Vehicle Assisted Delivery Problem, where an autonomous vehicle works in conjunction with a delivery person. The autonomous vehicle drops off the delivery person at designated locations, and the delivery person completes the deliveries (with a capacity constraint) on foot to the final addresses. Once the deliveries are completed, the vehicle picks up the delivery person and travels to the next reloading point. The goal is to decide on a route to serve all customers while minimizing the route completion time. We introduce an integer programming formulation with exponentially many variables and develop a branch-and-price approach. For generating promising columns, we present a tailored pulse algorithm to solve the pricing problem. Furthermore, by leveraging the structural properties of optimal solutions, we carefully design algorithmic enhancements, valid inequalities, and preprocessing steps to improve computational tractability. By conducting computational experiments based on instances derived from real-world data, we demonstrate the positive impact of these components. More importantly, we provide optimal certificates for 426 out of the 450 instances documented in the literature. Among the 100 instances in which driving could be slower than walking, we report solutions for the 40 largest instances for the first time. History: Accepted by David Alderson, Area Editor for Network Optimization. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.0177 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2023.0177 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

Federated learning system on autonomous vehicles for lane segmentation

Autonomous Vehicles (AV) is one of the most evolving industries in the last decade. However, one of the bottlenecks of this evolution is providing data that contains different scenarios and scenes to improve the models without exposing the privacy and security of the edge vehicles. The authors of this research propose a secure and efficient novel solution for lane segmentation in AVs through the use of Federated Learning (FL). FedLane involves initial training of U-Net, ResUNet, and ResUNet++ models, followed by real-time inference in edge devices and the application of FL to update the server model using clients’ data. The study found that FL has enhanced the performance of lane segmentation significantly over baseline, enabling decentralized privacy-preserving collaborative optimization with increased dice coef from 0.9429 to 0.9794 for U-Net, from 0.9291 to 0.9854 for ResUNet and from 0.9079 to 0.9675 for ResUNet++. Additionally, the models show increased stability over the training iterations, highlighting the potential of FL to play a significant role in the future of automation in the AV industry.

Unmanned Ground Vehicles for Continuous Crop Monitoring in Agriculture: Assessing the Readiness of Current ICT Technology

Continuous crop monitoring enables the early detection of field emergencies such as pests, diseases, and nutritional deficits, allowing for less invasive interventions and yielding economic, environmental, and health benefits. The work organization of modern agriculture, however, is not compatible with continuous human monitoring. ICT can facilitate this process using autonomous Unmanned Ground Vehicles (UGVs) to navigate crops, detect issues, georeference them, and report to human experts in real time. This review evaluates the current state of ICT technology to determine if it supports autonomous, continuous crop monitoring. The focus is on shifting from traditional cloud-based approaches, where data are sent to remote computers for deferred processing, to a hybrid design emphasizing edge computing for real-time analysis in the field. Key aspects considered include algorithms for in-field navigation, AIoT models for detecting agricultural emergencies, and advanced edge devices that are capable of managing sensors, collecting data, performing real-time deep learning inference, ensuring precise mapping and navigation, and sending alert reports with minimal human intervention. State-of-the-art research and development in this field suggest that general, not necessarily crop-specific, prototypes of fully autonomous UGVs for continuous monitoring are now at hand. Additionally, the demand for low-power consumption and affordable solutions can be practically addressed.

Loss of pelagic fish and zooplankton density associated with subglacial upwelling in high Arctic estuaries may be mitigated by benthic habitat expansion following tidewater glacier retreat

Glacier fronts are hotspots of pelagic productivity due to upwelling of nutrient-rich water. As tidewater glaciers retreat into land, this subglacial circulation will disappear and sedimentation from terrestrial runoff will increase, leading to a decrease in pelagic productivity with a decline in the abundance of fish and zooplankton. We used Billefjorden, a high Arctic fjord with a glacier recently transitioned from sea- to land-terminating as a case study to identify spatial differences and small-scale environmental drivers of density and vertical distribution of fish and zooplankton along a gradient of glacier retreat (directly in front of the land-terminating glacier front, a river bay with terrestrial input from land-terminating glaciers further inland and a location with minimal glacial input). We developed a sustainable and efficient protocol to safely sample the glacier front and shallow coastal areas using hydroacoustics and a remote autonomous vehicle combined with oceanographic measurements and baited remote cameras. Over two years, pelagic density was lowest at the now land-terminating glacier front and highest at the site with lowest terrestrial input. Temperature, depth and turbidity explained less than 8% of the variation each.

Nanoporous Structure Fabrication on Glass Surfaces for Enhanced Glass Adhesion Using Hydrogen Fluoride Gas.

The bonding between glass and other materials plays a crucial role when glass is used in industrial products. In this study, we propose a new approach to enhance the bonding strength of glass with other materials by fabricating nanoscale porous structures on glass surfaces via a chemical reaction with hydrogen fluoride gas. Herein, we present a methodology for controlling the thickness of the porous structure, clarify the relationship between the thickness and adhesion strength, investigate the shape of the formed porous structure, and propose a method to control its shape. Our findings reveal that the fabricated porous structure greatly improves the adhesion strength of the adhesive owing to the microscopic anchoring effect induced by the penetration of the adhesive into the porous structure. This approach is expected to be applied to architectural and automobile window glasses, solar panels, sensor cover glasses of autonomous vehicles, display devices (including smartphones), and wearable devices.