Autonomous Driving Research Articles

Designing Black Yet Highly LiDAR-detectable Double-shell Hollow Nanoparticles for Autonomous Driving Environments

Novel LiDAR-detectable black double-shell hollow nanoparticles (BDS-HNPs) with internal white shell are successfully utilized as materials for autonomous vehicle paint for the first time. These BDS-HNPs are carefully designed to achieve excellent near-infrared (NIR) reflectance, blackness, hydrophilicity, and applicability as monolayer coatings. An emphasis is placed on the NIR reflectance by forming double-shell hollow morphologies embracing the internal white shell and multiple interfaces within the nanoparticles. Accordingly, the BDS-HNPs exhibit NIR reflectance of ca. 33.2, 36.9, and 40.9 R% at wavelengths of 793, 850, and 905 nm, respectively, comparable to NIR reflectance of the commercially available NIR-reflective bilayer dark-tone coating. For the practical LiDAR visualization, BDS-HNPs mixed with hydrophilic varnish are spray-coated onto the various objects. As a result, the BDS-HNPs-painted objects are clearly recognized by three different types of LiDAR sensors (robot, rotating, and MEMs mirror) under various conditions of inside and outside. These results clearly demonstrate the great potential of BDS-HNPs as a new type of LiDAR-detectable black material for future autonomous driving environments.

Designing Reward Functions Using Active Preference Learning for Reinforcement Learning in Autonomous Driving Navigation

This study presents a method based on active preference learning to overcome the challenges of designing reward functions for autonomous navigation. Results obtained from training with artificially designed reward functions may not accurately reflect human intentions. We focus on the limitations of traditional reward functions, which often fail to facilitate complex tasks in continuous state spaces. We propose the adoption of active preference learning to resolve these issues and to generate reward functions that align with human preferences. This approach leverages an individual’s subjective preferences to guide an agent’s learning process, enabling the creation of reward functions that reflect human desires. We utilize mutual information to generate informative queries and apply information gained to balance the agent’s uncertainty with the human’s response capacity, encouraging the agent to pose straightforward and informative questions. We further employ the No-U-Turn Sampler (NUTS) method to refine the belief model, which outperforms that constructed using the Metropolis algorithm. Subsequently, we retrain the agent using reward weights derived from active preference learning. As a result, our autonomous driving vehicle can navigate between random starting and ending points without dependence on high-precision maps or routing, relying solely on its forward vision. We validate our approach’s performance within the CARLA simulation environment. Our algorithm significantly improved the success rate of autonomous driving navigation tasks that originally failed due to artificially designed rewards, increasing it to approximately 60%. Experimental results show significant improvement over the baseline algorithm, providing a solid foundation for enhancing navigation capabilities in autonomous driving systems and advancing the field of autonomous driving intelligence.

Real-Time Fire Surveillance with Machine Learning Twilio Integration

Fire threats pose significant risks to people and property, necessitating efficient surveillance systems. A complete fire surveillance system is proposed using machine learning and artificial intelligence to monitor fire incidents in real time. The system is built using React.js for frontend development and MongoDB for backend storage. Node.js is integrated for server-side operations, ensuring data management and user interaction. The system sends alerts via WhatsApp when image analysis identifies a fire concern, leveraging Twilio for seamless messaging. Robo Flow simplifies computer vision model management, while YOLOv8, a cutting-edge object recognition algorithm, enhances detection speed and accuracy. YOLOv8 is widely used in real-time object identification applications like robotics, autonomous cars and surveillance systems. Twilio is a cloud communication platform that allows developers to integrate voice, video, and SMS into their apps, enabling notifications, alarms, and two-way communication. The research utilizes Machine Learning, React.js, MongoDB, YOLOv8, and Twilio to offer efficient real-time fire surveillance.

An Analysis on Recent Approaches for Image Captioning

Image captioning is an interdisciplinary area that uses techniques from computer vision and natural language processing to provide a textual description of a picture. The Image captioning task is the process of understanding the scene present in the image by identifying objects and associated actions present to create a meaningful human-like caption which can be used for wide range of applications, including image retrieval, video indexing, assistive technology for the visually impaired, content-based image search, biomedicine, and autonomous cars. Formerly, Machine Learning was utilized for this purpose which will be extensive use of hand-crafted features such as Scale-Invariant Feature Transform (SIFT), Local Binary Patterns (LBP), the Histogram of Oriented Gradients (HOG), and combinations of these features. Extracting handmade characteristics from huge datasets is not straightforward or viable. Many deep learning-based techniques were later proposed. Deep Learning retrieval and template-based approaches were presented; however, both had drawbacks such as losing crucial objects. Recent breakthroughs in deep learning and natural language processing have resulted in considerable increases in image captioning system performance which involves adopting attention mechanisms, transformer-based architectures, multi modal connections, Object-Detection based encoder-decoder and many others. In this survey will explore some of the most recent techniques for image captioning, the datasets and evaluation measures that have been employed in deep learning-based automatic image captioning. The ultimate intention of this study is to act as a guide for researchers by emphasizing future directions for research work. Index Terms: image captioning, computer vision, deep learning, Textual description, natural language processing.

A Dynamic Evolution Model for Decentralized Autonomous Car Clusters in a Highway Scene

A Dynamic Evolution Model for Decentralized Autonomous Car Clusters in a Highway Scene

EgoFormer: Ego-Gesture Classification in Context of Autonomous Driving

EgoFormer: Ego-Gesture Classification in Context of Autonomous Driving

Hierarchical Perception Enhancement for Different Levels of Autonomous Driving: A Review

Hierarchical Perception Enhancement for Different Levels of Autonomous Driving: A Review

Lane-Level Positioning Method Based on Vector Map Matching for Autonomous Driving: A Polynomial Fitting Method

Lane-Level Positioning Method Based on Vector Map Matching for Autonomous Driving: A Polynomial Fitting Method

A Novel Reinforcement Learning Method for Autonomous Driving With Intermittent Vehicle-to-Everything (V2X) Communications

A Novel Reinforcement Learning Method for Autonomous Driving With Intermittent Vehicle-to-Everything (V2X) Communications

A GoA4 Control Architecture for the Autonomous Driving of High-Speed Trains Over ETCS: Design and Experimental Validation

A GoA4 Control Architecture for the Autonomous Driving of High-Speed Trains Over ETCS: Design and Experimental Validation

A RGB-Thermal Image Segmentation Method Based on Parameter Sharing and Attention Fusion for Safe Autonomous Driving

A RGB-Thermal Image Segmentation Method Based on Parameter Sharing and Attention Fusion for Safe Autonomous Driving

Implementation of Smart Vehicle Assistant using Computer vision and Deep Learning

bstract: Autonomous cars are a popular research topic in the field of intelligent transportation systems because they have the potential to greatly reduce traffic and improve travel efficiency. Scene classification is a key technology for autonomous cars because it forms the basis of these vehicles' decision-making. In recent years, deep learning-based methods have demonstrated promise in resolving the scene classification issue. However, further research is needed on a few difficulties related to scene classification methodologies, such as how to treat similarities and contrasts within the same category. To tackle these problems, this research suggests an improved deep network-based scene classification method. Autonomous cars are a popular research topic in the field of intelligent transportation systems because they have the potential to greatly reduce traffic and improve travel efficiency.

Advanced method for Image detection using OpenCV

Abstract: In computer vision, object detection is an essential job with many real-world applications, such as robots, autonomous cars, and surveillance. Because of its great accuracy and speed, the YOLO (You Only Look Once) method is a well-liked realtime object recognition technique that has attracted a lot of attention. This technique is perfect for time-sensitive applications since it examines the full image at once and predicts bounding boxes and class probabilities for recognized items. YOLO has undergone many iterations, with YOLO v5 being the most recent and sophisticated version. It utilizes anchor boxes and a feature pyramid network (FPN) to increase the accuracy of object recognition. Our goal in this research is to apply YOLO v5 to realtime picture and object identification applications stage. The model will be trained using an appropriate dataset, and its performance will be assessed against a range of benchmarks and advanced object detection methods. The project's output will offer a reliable and effective real-time object detection system that will facilitate prompt decision-making in the identification of item types and their corresponding placements. It has useful uses in robotics, autonomous driving, and surveillance.

An Inference Similarity-based Federated Learning Framework for Enhancing Collaborative Perception in Autonomous Driving

An Inference Similarity-based Federated Learning Framework for Enhancing Collaborative Perception in Autonomous Driving

Comprehensive Survey of Autonomous Driving Systems and Advanced Technologies: Literature Review, Gap Analysis and Future Directions

Abstract: This article presents a literature review of numerous research papers focusing around the topic ‘Development of Autonomous Driving Vehicle System’, and related works. The advent of autonomous driving technology has revolutionized the automotive industry, promising enhanced safety, efficiency, and convenience on the road. A critical aspect of autonomous vehicle development is the assessment of their performance ina controlled and risk-free environment. Virtual environments, enabled by cutting-edge technologies, offer a dynamic plat- form for rigorous testing and training of autonomous vehicles. This paper aims to study and analyze different approaches and methodologies that are implemented for the development of Autonomous Driving Systems(ADS). Some of the primary aspects that are found common in most papers are Virtual Environment, pedestrians’ safety, privacy, security, real-time datapresentation, precise torque control, Reinforcement Learning, Deep Learning, Hardware-in-the-loop (HIL)- simulation, Model- in-the-loop (MIL)-simulation, etc. The sole idea of extracting valuable information from a virtual environment ensures a sense of safety as there are no humans involuntarily involved to take part in the development. However, the data extracted from the virtual environment must be highly accurate and reliable, as it will be trained and tested in real environments post deployment. Collision scenarios need to be carefully studied, for which relative positioning of vehicle and pedestrians should be taken into account, so as to examine their velocities, time to collision, and appropriately taking actions. Above all, it should be noted that the safety of human lives holds the highest priority, if a method suggests a high risk factor for a human life, then it should be either discarded, or improved

A Review of Deep Learning Advancements in Road Analysis for Autonomous Driving

A Review of Deep Learning Advancements in Road Analysis for Autonomous Driving

On Evaluating Black-Box Explainable AI Methods for Enhancing Anomaly Detection in Autonomous Driving Systems.

The recent advancements in autonomous driving come with the associated cybersecurity issue of compromising networks of autonomous vehicles (AVs), motivating the use of AI models for detecting anomalies on these networks. In this context, the usage of explainable AI (XAI) for explaining the behavior of these anomaly detection AI models is crucial. This work introduces a comprehensive framework to assess black-box XAI techniques for anomaly detection within AVs, facilitating the examination of both global and local XAI methods to elucidate the decisions made by XAI techniques that explain the behavior of AI models classifying anomalous AV behavior. By considering six evaluation metrics (descriptive accuracy, sparsity, stability, efficiency, robustness, and completeness), the framework evaluates two well-known black-box XAI techniques, SHAP and LIME, involving applying XAI techniques to identify primary features crucial for anomaly classification, followed by extensive experiments assessing SHAP and LIME across the six metrics using two prevalent autonomous driving datasets, VeReMi and Sensor. This study advances the deployment of black-box XAI methods for real-world anomaly detection in autonomous driving systems, contributing valuable insights into the strengths and limitations of current black-box XAI methods within this critical domain.

Multi-Scale Target Detection in Autonomous Driving Scenarios Based on YOLOv5-AFAM

Multi-scale object detection is critically important in complex driving environments within the field of autonomous driving. To enhance the detection accuracy of both small-scale and large-scale targets in complex autonomous driving environments, this paper proposes an improved YOLOv5-AFAM algorithm. Firstly, the Adaptive Fusion Attention Module (AFAM) and Down-sampling Module (DownC) are introduced to increase the detection precision of small targets. Secondly, the Efficient Multi-scale Attention Module (EMA) is incorporated, enabling the model to simultaneously recognize small-scale and large-scale targets. Finally, a Minimum Point Distance IoU-based Loss Function (MPDIou-LOSS) is introduced to improve the accuracy and efficiency of object detection. Experimental validation on the KITTI dataset shows that, compared to the baseline model, the improved algorithm increased precision by 2.4%, recall by 2.6%, mAP50 by 1.5%, and mAP50-90 by an impressive 4.8%.

Interconnection and Autonomous Driving: Concepts, Development process and Applications

This paper provides an in-depth discussion on the concepts, development process, applications and integration of interconnection technology and autonomous driving technology. Through a comprehensive introduction to these two technologies, it reveals their positive impacts in the field of transportation and analyzes the advantages of their integration. As a technology which can connect various domains, interconnection has become a transformative force. Its implications are far-reaching, which impacts not only the digital field, but also the transportation field. Concurrently, autonomous driving technology, which dedicates to enabling vehicles to move without human intervention, is representing the future of efficient and safe transportation. In the parts of the integration of these two technologies, this paper introduces its positive impacts on driving efficiency, traffic management, and safety. However, challenges such as privacy concerns and cybersecurity threats are existed, too. Finally, some possible solutions to these issues are concluded and the future of interconnection and autonomous driving technology is anticipated.

Systematic development of an autonomous robotic car for fire-fighting based on the interactive design approach

Systematic development of an autonomous robotic car for fire-fighting based on the interactive design approach