Search Results (4,611)

Object detection and classification in autonomous vehicles are crucial for ensuring safe and efficient navigation through complex environments. This paper addresses the need for robust detection and classification algorithms tailored specifically for Indian roads, which present unique challenges such as diverse traffic patterns, erratic driving behaviors, and varied weather conditions. Despite significant progress in object detection and classification for autonomous vehicles, existing methods often struggle to generalize effectively to the conditions encountered on Indian roads. This paper proposes a novel approach utilizing the YOLOv8 deep learning model, designed to be lightweight, scalable, and efficient for real-time implementation using onboard cameras. Experimental evaluations were conducted using real-life scenarios encompassing diverse weather and traffic conditions. Videos captured in various environments were utilized to assess the model’s performance, with particular emphasis on its accuracy and precision across 35 distinct object classes. The experiments demonstrate a precision of 0.65 for the detection of multiple classes, indicating the model’s efficacy in handling a wide range of objects. Moreover, real-time testing revealed an average accuracy exceeding 70% across all scenarios, with a peak accuracy of 95% achieved in optimal conditions. The parameters considered in the evaluation process encompassed not only traditional metrics but also factors pertinent to Indian road conditions, such as low lighting, occlusions, and unpredictable traffic patterns. The proposed method exhibits superiority over existing approaches by offering a balanced trade-off between model complexity and performance. By leveraging the YOLOv8 architecture, this solution achieved high accuracy while minimizing computational resources, making it well suited for deployment in autonomous vehicles operating on Indian roads. Full article

In recent years, the simplified computation of position and velocity changes in nonlinear systems using Lie groups and Lie algebra has been widely used in the study of robot localization systems. The unscented Kalman filter (UKF) can effectively deal with nonlinear systems through the unscented transformation, and in order to more accurately describe the robot localization system, the UKF method based on Lie groups has been studied successively. The computational complexity of the UKF on Lie groups is high, and in order to simplify its computation, the Lie groups are applied to the manifold, which efficiently handles the state and uncertainty and ensures that the system maintains the geometric constraints and computational simplicity during the updating process. In this paper, a multi-sensor fusion localization method based on an unscented Kalman filter on manifolds (UKF-M) is investigated. Firstly, a system model and a multi-sensor model are established based on an Autonomous Underwater Vehicle (AUV), and a corresponding UKF-M is designed for the system. Secondly, the multi-sensor fusion method is designed, and the fusion method is applied to the UKF-M. Finally, the proposed method is validated using an underwater cave dataset. The experiments demonstrate that the proposed method is suitable for underwater environments and can significantly correct the cumulative error in the trajectory estimation to achieve accurate underwater localization. Full article

The allocation of tasks among multiple Autonomous Underwater Vehicles (AUVs) with energy constraints in underwater environments presents an NP-complete problem with far-reaching consequences for marine exploration, environmental monitoring, and underwater construction. This paper critically examines the contemporary methodologies and technologies in the task allocation for multiple AUVs, with a particular focus on strategies that optimize navigation time with energy consumption constraints. By conceptualizing the multiple AUVs task allocation issue as a Capacitated Vehicle Routing Problem (CVRP) and addressing it using the SCIP solver, this study seeks to identify effective task allocation strategies that enhance the operational efficiency and minimize the mission duration in energy-restricted underwater settings. The findings of this research provide valuable insights into efficient task allocation under energy constraints, providing useful theoretical implications and practical guidance for optimizing task planning and energy management in multiple AUVs systems. These contributions are demonstrated through the improved solution quality and computational efficiency. Full article

Collaboration among road agents, such as connected autonomous vehicles and roadside units, enhances driving performance by enabling the exchange of valuable information. However, existing collaboration methods predominantly focus on perception tasks and rely on single-frame static information sharing, which limits the effective exchange of temporal data and hinders broader applications of collaboration. To address this challenge, we propose CoPnP, a novel collaborative joint perception and prediction system, whose core innovation is to realize multi-frame spatial–temporal information sharing. To achieve effective and communication-efficient information sharing, two novel designs are proposed: (1) a task-oriented spatial–temporal information-refinement model, which filters redundant and noisy multi-frame features into concise representations; (2) a spatial–temporal importance-aware feature-fusion model, which comprehensively fuses features from various agents. The proposed CoPnP expands the benefits of collaboration among road agents to the joint perception and prediction task. The experimental results demonstrate that CoPnP outperforms existing state-of-the-art collaboration methods, achieving a significant performance-communication trade-off and yielding up to 11.51%/10.34% Intersection over union and 12.31%/10.96% video panoptic quality gains over single-agent PnP on the OPV2V/V2XSet datasets. Full article

With the rapid advancement of autonomous driving technology, the accurate prediction of vehicle trajectories has become a research hotspot. In order to accurately predict vehicles’ trajectory, this study comprehensively explores the impact of driving style and intention on trajectory prediction, proposing a novel prediction method. Firstly, the dataset AD4CHE was selected as the research data, from which the required trajectory data of vehicles were extracted, including 1202 lane-changing and 1137 car-following driving trajectories. Secondly, a long short-term memory (LSTM) network based on the Keras framework was constructed by using the TensorFlow deep-learning platform. The LSTM network integrates driving intention, driving style, and historical trajectory data as inputs to establish a vehicle-trajectory prediction model. Finally, the mean absolute error (MAE) and root-mean-square error (RMSE) were selected as the evaluation indicators for the models, and the prediction results of the models were compared under two conditions: not considering driving style and considering driving style. The results demonstrate that models incorporating driving style significantly outperformed those that did not, highlighting the critical influence of driving style on vehicle trajectories. Moreover, compared to traditional kinematic models, the LSTM-based approach exhibits notable advantages in long-term trajectory prediction. The prediction method that accounts for both driving intention and style effectively reduces RMSE, significantly enhancing prediction accuracy. The findings of this research provide valuable insights for vehicle-driving risk assessment and contribute positively to the advancement of autonomous driving technology and the sustainable development of road traffic. Full article

The paper presents an approach to solving the problem of unknown motion parameters Bayesian identification for the stochastic dynamic system model with randomly delayed observations. The system identification and the object tracking tasks obtain solutions in the form of recurrent Bayesian relations for a posteriori probability density. These relations are not practically applicable due to the computational challenges they present. For practical implementation, we propose a conditionally minimax nonlinear filter that implements the concept of conditionally optimal estimation. The random delays model source is the area of autonomous underwater vehicle control. The paper discusses in detail a computational experiment based on a model that is closely aligned with this practical need. The discussion includes both a description of the filter synthesis features based on the geometric interpretation of the simulated measurements and an impact analysis of the effectiveness of model special factors, such as time delays and model unknown parameters. Furthermore, the paper puts forth a novel approach to the identification problem statement, positing a random jumping change in the motion parameters values. Full article

Crowdsensing has gained popularity across various domains such as urban transportation, environmental monitoring, and public safety. Unmanned aerial vehicle (UAV) crowdsensing is a novel approach that collects extensive data from targeted environments using UAVs equipped with built-in sensors. Unlike conventional methods that rely on fixed sensor networks or the mobility of humans, UAV crowdsensing offers high flexibility and scalability. With the rapid advancement of artificial intelligence techniques, UAV crowdsensing is becoming increasingly intelligent and autonomous. Previous studies on UAV crowdsensing have predominantly focused on algorithmic sensing strategies without considering the impact of different sensing environments. Thus, there is a research gap regarding the influence of environmental factors and sensing strategies in this field. To this end, we designed a $4\times 3$ empirical study, classifying sensing environments into four major categories: open, urban, natural, and indoor. We conducted experiments to understand how these environments influence three typical crowdsensing strategies: opportunistic, algorithmic, and collaborative. The statistical results reveal significant differences in both environments and sensing strategies. We found that an algorithmic strategy (machine-only) is suitable for open and natural environments, while a collaborative strategy (human and machine) is ideal for urban and indoor environments. This study has crucial implications for adopting appropriate sensing strategies for different environments of UAV crowdsensing tasks. Full article

At present Deep Neural Networks (DNN) have a dominant role in the AI-driven Autonomous driving approaches. This paper focuses on the potential safety risks of deploying DNN classifiers in Advanced Driver Assistance System (ADAS) systems. In our experience, many theoretically sound AI-driven solutions tested and deployed in ADAS have shown serious safety flaws in practice. A brief review of practice and theory of automotive safety standards and related body of knowledge is presented. It is followed by a comparative analysis between DNN classifiers and safety standards developed in the automotive industry. The output of the study provides advice and recommendations for filling the current gaps within the complex and interrelated factors pertaining to the safety of Autonomous Road Vehicles (ARV). This study may assist ARV’s safety, system, and technology providers during the design, development, and implementation life cycle. The contribution of this work is to highlight and link the learning rules enforced by risk factors when DNN classifiers are expected to provide a near real-time safer Vehicle Navigation Solution (VNS). Full article

Natural disasters like hurricanes, wildfires, and floods pose immediate hazards. Such events often necessitate prompt emergency evacuations to save lives and reduce fatalities, injuries, and property damage. This study focuses on optimizing wildfire evacuations by analyzing the influence of different transportation infrastructures and the penetration of autonomous vehicles (AVs) on a historical wildfire event. The methodology involves modeling various evacuation scenarios and incorporating different intersection traffic controls such as roundabouts and stop signs and an evacuation strategy like lane reversal with various AV penetration rates. The analysis results demonstrate that specific interventions on evacuation routes can significantly reduce travel times during evacuations. Additionally, a comparative analysis across different scenarios shows a promising improvement in travel time with a higher level of AV penetration. These findings advocate for the integration of autonomous technologies as a crucial component of future emergency response strategies, demonstrating the potential for broader applications in disaster management. Future studies can expand on these findings by examining the broader implications of integrating AVs in emergency evacuations. Full article

Photovoltaic energy (PV) is considered one of the pillars of the energy transition. However, this energy source is limited by a power density per unit surface lower than 200 W/m², depending on the latitude of the installation site. Compared to fossil fuels, such low power density opens a sustainability issue for this type of renewable energy in terms of its competition with other land uses, and forces us to consider areas suitable for the installation of photovoltaic arrays other than farmlands. In this frame, floating PV plants, installed in internal water basins or even offshore, are receiving increasing interest. On the other hand, this kind of installation might significantly affect the water ecosystem environment in various ways, such as by the effects of solar shading or of anchorage installation. As a result, monitoring of floating PV (FPV) plants, both during the ex ante site evaluation phase and during the operation of the PV plant itself, is therefore necessary to keep such effects under control. This review aims to examine the technical and academic literature on FPV plant monitoring, focusing on the measurement and discussion of key physico-chemical parameters. This paper also aims to identify the additional monitoring features required for energy assessment of a floating PV system compared to a ground-based PV system. Moreover, due to the intrinsic difficulty in the maintenance operations of PV structures not installed on land, novel approaches have introduced autonomous solutions for monitoring the environmental impacts of FPV systems. Technologies for autonomous mapping and monitoring of water bodies are reviewed and discussed. The extensive technical literature analyzed in this review highlights the current lack of a cohesive framework for monitoring these impacts. This paper concludes that there is a need to establish general guidelines and criteria for standardized water quality monitoring (WQM) and management in relation to FPV systems. Full article

Autonomous driving has long grappled with the need for precise absolute localization, making full autonomy elusive and raising the capital entry barriers for startups. This study delves into the feasibility of local trajectory planning for Level-2+ (L2+) semi-autonomous vehicles without the dependence on accurate absolute localization. Instead, emphasis is placed on estimating the pose change between consecutive planning timesteps from motion sensors and on integrating the relative locations of traffic objects into the local planning problem within the ego vehicle’s local coordinate system, thereby eliminating the need for absolute localization. Without the availability of absolute localization for correction, the measurement errors of speed and yaw rate greatly affect the estimation accuracy of the relative pose change between timesteps. This paper proved that the stability of the continuous planning problem under such motion sensor errors can be guaranteed at certain defined conditions. This was achieved by formulating it as a Lyapunov-stability analysis problem. Moreover, a simulation pipeline was developed to further validate the proposed local planning method, which features adjustable driving environment with multiple lanes and dynamic traffic objects to replicate real-world conditions. Simulations were conducted at two traffic scenes with different sensor error settings for speed and yaw rate measurements. The results substantiate the proposed framework’s functionality even under relatively inferior sensor errors distributions, i.e., speed error $v_{\mathrm{err}}$∼$\mathcal{N}(-0.1,0.1)$ m/s and yaw rate error ${\dot{\theta }}_{\mathrm{err}}$∼$\mathcal{N}(0.57,1.72)$ deg/s. Experiments were also conducted to evaluate the stability limits of the planned results under abnormally larger motion sensor errors. The results provide a good match to the previous theoretical analysis. Our findings suggested that precise absolute localization may not be the sole path to achieving reliable trajectory planning, eliminating the necessity for high-accuracy dual-antenna Global Positioning System (GPS) as well as the pre-built high-fidelity (HD) maps for map-based localization. Full article

Accurate longitudinal control is crucial in autonomous driving, but inherent delays and lag in electric vehicle powertrains hinder precise control. This paper presents a two-stage design for a longitudinal speed controller to enhance speed tracking performance in autonomous electric vehicles. The first stage involves designing a Model Predictive Control (MPC) system that accounts for powertrain signal delay and response lag using a First Order Plus Dead Time (FOPDT) model integrated with the vehicle’s longitudinal dynamics. The second stage employs lookup tables for the drive motor and brake system to convert control signals into actual vehicle inputs, ensuring precise throttle/brake pedal values for the desired driving torque. The proposed controller was validated using the CarMaker simulator and real vehicle tests with a Hyundai IONIQ5. In real vehicle tests, the proposed controller achieved a mean speed error of 0.54 km/h, outperforming conventional PID and standard MPC methods that do not account for powertrain delays. It also eliminated acceleration and deceleration overshoots and demonstrated real-time performance with an average computation time of 1.32 ms. Full article

Object detection, as a crucial aspect of computer vision, plays a vital role in traffic management, emergency response, autonomous vehicles, and smart cities. Despite the significant advancements in object detection, detecting small objects in images captured by high-altitude cameras remains challenging, due to factors such as object size, distance from the camera, varied shapes, and cluttered backgrounds. To address these challenges, we propose small object detection YOLOv8 (SOD-YOLOv8), a novel model specifically designed for scenarios involving numerous small objects. Inspired by efficient generalized feature pyramid networks (GFPNs), we enhance multi-path fusion within YOLOv8 to integrate features across different levels, preserving details from shallower layers and improving small object detection accuracy. Additionally, we introduce a fourth detection layer to effectively utilize high-resolution spatial information. The efficient multi-scale attention module (EMA) in the C2f-EMA module further enhances feature extraction by redistributing weights and prioritizing relevant features. We introduce powerful-IoU (PIoU) as a replacement for CIoU, focusing on moderate quality anchor boxes and adding a penalty based on differences between predicted and ground truth bounding box corners. This approach simplifies calculations, speeds up convergence, and enhances detection accuracy. SOD-YOLOv8 significantly improves small object detection, surpassing widely used models across various metrics, without substantially increasing the computational cost or latency compared to YOLOv8s. Specifically, it increased recall from 40.1% to 43.9%, precision from 51.2% to 53.9%, mAP_0.5 from 40.6% to 45.1%, and mAP_0.5:0.95 from 24% to 26.6%. Furthermore, experiments conducted in dynamic real-world traffic scenes illustrated SOD-YOLOv8’s significant enhancements across diverse environmental conditions, highlighting its reliability and effective object detection capabilities in challenging scenarios. Full article

This paper explores new sensor technologies and their integration within Connected Autonomous Vehicles (CAVs) for real-time road condition monitoring. Sensors like accelerometers, gyroscopes, LiDAR, cameras, and radar that have been made available on CAVs are able to detect anomalies on roads, including potholes, surface cracks, or roughness. This paper also describes advanced data processing techniques of data detected with sensors, including machine learning algorithms, sensor fusion, and edge computing, which enhance accuracy and reliability in road condition assessment. Together, these technologies support instant road safety and long-term maintenance cost reduction with proactive maintenance strategies. Finally, this article provides a comprehensive review of the state-of-the-art future directions of condition monitoring systems for traditional and smart roads. Full article

In addressing the optimal formation obstacle avoidance control problem for Autonomous Underwater Vehicles (AUVs) in environments with unknown and moving obstacles, this paper employs the Modified Fireworks Algorithm based on a Loser Elimination Mechanism (MLoTFWA) and constructs a Distributed Model Predictive Control (DMPC) framework to achieve obstacle avoidance for AUV formations. Initially, a prediction model is established, followed by feedback compensation to mitigate the effects of unknown perturbations. An appropriate fitness function is then formulated, and enhancements such as the loser elimination rule are introduced to optimize the fireworks algorithm. Additionally, the concept of an adaptive DMPC prediction window is proposed to conserve resources. The local and global stability of the DMPC formation control framework is theoretically proven. Simulations verify that the control system based on the DMPC framework ensures safe obstacle avoidance for the formation, maintains formation consistency, and achieves the shortest and smoothest path. The improved fireworks algorithm demonstrates superior performance compared with the original fireworks algorithm and other optimization algorithms. In testing, the improved fireworks algorithm exhibits better adaptability, higher average fitness, and best fitness, along with a significantly faster convergence speed. Compared with the ordinary fireworks algorithm, the convergence speed is reduced by 30%. Full article