Figure - available from: Sensors
This content is subject to copyright.
Source publication
The advancement in sensor technologies, mobile network technologies, and artificial intelligence has pushed the boundaries of different verticals, e.g., eHealth and autonomous driving. Statistics show that more than one million people are killed in traffic accidents yearly, where the vast majority of the accidents are caused by human negligence. Hi...
Citations
... Wang et al. [62] introduced a variety of approaches for modeling and learning social interaction between AVs and HDVs, including rational utility-based, deep neural networks-based, graph-based, social fields and forces, and computational cognitive approaches. Malik et al. [63] and Abdallaoui [64] categorized decision-making approaches for AVs, while Reda et al. [65] and Song et al. [66] summarized the motion planning methods for autonomous driving. However, recent research that contributes to the advancement of interactive driving has not been included in the previous reviews. ...
Interactive autonomous driving is an evolving research domain that demands an autonomous vehicle (AV) to exhibit adaptability to new environments, cognizance of surrounding traffic conditions, and proficient decision-making ability in complex human-dominated scenarios to guarantee safe navigation and promote social compatibility. This paper reviews the diverse methodologies utilized in interactive driving for AVs. Various techniques will be investigated for their unique contributions and capabilities in developing AV systems, such as long short-term memory (LSTM), transformer, artificial potential field (APF), game theory, reinforcement learning (RL)/deep reinforcement learning (DRL), and partially observable Markov decision processes (POMDP), among others. Recent advancements based on these methodologies are summarized to elucidate their application rationale in interactive driving scenarios. The strengths and challenges inherent to each approach within the context of interactive driving are further assessed. Additionally, the resolution of these challenges is explored through integrating different methods. Therefore, a comparative analysis offers crucial perspectives for advancing autonomous driving technologies. This review exclusively focuses on the interactions between AVs and human-driven vehicles (HDVs).
... Although there is no unified formal definition (yet) of what it means to drive safely, at its core, solving the multi-objective motion planning problem largely depends on the competency to contend solutions within a hierarchical framework [4]. AV decision-making has been previously characterized as lexicographic [5] -for instance, avoiding a collision is incomparably more important than violating lane-change rules. ...
... Note that how to design the time scales is outside the scope of this work. See[33] for an example theoretical framework.4 Since trajectories are a by product of the decisions (inputs), trajectories will be used as a synonym for decisions. ...
A key challenge in autonomous driving is that Autonomous Vehicles (AVs) must contend with multiple, often conflicting, planning requirements. These requirements naturally form in a hierarchy -- e.g., avoiding a collision is more important than maintaining lane. While the exact structure of this hierarchy remains unknown, to progress towards ensuring that AVs satisfy pre-determined behavior specifications, it is crucial to develop approaches that systematically account for it. Motivated by lexicographic behavior specification in AVs, this work addresses a lexicographic multi-objective motion planning problem, where each objective is incomparably more important than the next -- consider that avoiding a collision is incomparably more important than a lane change violation. This work ties together two elements. Firstly, a multi-objective candidate function that asymptotically represents lexicographic orders is introduced. Unlike existing multi-objective cost function formulations, this approach assures that returned solutions asymptotically align with the lexicographic behavior specification. Secondly, inspired by continuation methods, we propose two algorithms that asymptotically approach minimum rank decisions -- i.e., decisions that satisfy the highest number of important rules possible. Through a couple practical examples, we showcase that the proposed candidate function asymptotically represents the lexicographic hierarchy, and that both proposed algorithms return minimum rank decisions, even when other approaches do not.
... 2. Localization and Mapping: AI algorithms are used to generate high-definition maps to precisely determine the vehicle's position in real time [20]. Simultaneous localization and mapping (SLAM) techniques combine sensor data and AI to generate a map of the surrounding and control the vehicle's position in it [21,22]. ...
... AI-enabled AVs require collaboration of robotics, computer science, mechanical engineering, and many other relevant fields [5,35]. The goal here is to create vehicles that are not only technically proficient but also safe, efficient, and capable of navigating real-world situations with a high degree of autonomy [5,6,22]. In this manuscript, we have analyzed the same. ...
... LiDAR maps a 3D structure of the surrounding environment and the road integrating the data read from incoming reflected light [21]. The emitter releases a laser beam that bounces off a mirror rotating at 10 revolutions per minute [22]. After bouncing from an object, the beam returns to the mirror from where it is bounced to the receiver which interprets it appropriately [23]. ...
... The extracted information is subsequently used to generate commands. Finally, the decision layer takes responsibility for translating orders into mechanical actions such as braking, acceleration, and steering [31], [32]. These layers are summarized as follows: ...
In Intelligent Transportation Systems (ITS), ensuring road safety has paved the way for innovative advancements such as autonomous driving. These self-driving vehicles, with their variety of sensors, harness the potential to minimize human driving errors and enhance transportation efficiency via sophisticated AI modules. However, the reliability of these sensors remains challenging, especially as they can be vulnerable to anomalies resulting from adverse weather, technical issues, and cyber-attacks. Such inconsistencies can lead to imprecise or erroneous navigation decisions for autonomous vehicles that can result in fatal consequences, e.g., failure in recognizing obstacles. This survey delivers a comprehensive review of the latest research on solutions for detecting anomalies in sensor data. After laying the foundation on the workings of the connected and autonomous vehicles, we categorize anomaly detection methods into three groups: statistical, classical machine learning, and deep learning techniques. We provide a qualitative assessment of these methods to underline existing research limitations. We conclude by spotlighting key research questions to enhance the dependability of autonomous driving in forthcoming studies.
... AI opaqueness poses obvious challenges when decisions reached by, or with the help of, AI systems have major consequences. Thus, opaqueness is often discussed in the medical context [35][36][37][38] or in the context of autonomous driving [39,40]. It should be clear, however, that opaqueness is a general issue inherent in this kind of technology. ...
Societies in the global North face a future of accelerated ageing. In this context, advanced technology, especially that involving artificial intelligence (AI), is often presented as a natural counterweight to stagnation and decay. While it is a reasonable expectation that AI will play important roles in such societies, the manner in which it affects the lives of older people needs to be discussed. Here I argue that older people should be able to exercise, if they so choose, a right to refuse AI-based technologies, and that this right cannot be purely negative. There is a public duty to provide minimal conditions to exercise such a right, even if majorities in the relevant societies disagree with skeptical attitudes towards technology. It is crucial to recognize that there is nothing inherently irrational or particularly selfish in refusing to embrace technologies that are commonly considered disruptive and opaque, especially when the refusers have much to lose. Some older individuals may understandably decide that they indeed stand to lose a whole world of familiar facts and experiences, competencies built in decades of effort, and autonomy in relation to technology. The current default of investigating older people’s resistance to technology as driven by fear or exaggerated emotion in general, and therefore as something to be managed and extinguished, is untenable.
... Autonomous driving is an advanced automotive technology that utilizes onboard sensors, computer vision, and machine learning to enable vehicles to autonomously perceive, analyze, and respond to road environments, achieving full or partial driverless operation [1]. Through autonomous driving technology, vehicles can automatically control their movements, comply with traffic rules, avoid obstacles, and make reasonable driving decisions based on the actual road conditions [2]. The development of this technology aims to enhance road safety, reduce traffic accidents, improve traffic efficiency, and provide passengers with a more convenient and comfortable travel experience. ...
To enhance the lane-changing safety of autonomous vehicles, it is crucial to accurately identify the driving styles of human drivers in scenarios involving the coexistence of autonomous and human-driven vehicles, aiming to avoid encountering vehicles exhibiting hazardous driving patterns. In this study, based on the real traffic flow data from the Next Generation Simulation (NGSIM) dataset in the United States, 301 lane-changing vehicles that meet the criteria are selected. Six evaluation parameters are chosen, and principal component analysis (PCA) is employed for dimensionality reduction in the data. The K-means algorithm is then utilized to cluster the driving styles, classifying them into three categories. Finally, ant colony optimization (ACO) of a backpropagation (BP) neural network model was constructed, utilizing the dimensionality reduction results as inputs and the clustering results as outputs for the purpose of driving style recognition. Simulation experiments are conducted using MATLAB Version 9.10 (R2021a) for comparative analysis. The results indicate that the constructed ACO-BP model achieved an overall recognition accuracy of 96.7%, significantly higher than the recognition accuracies of the BP, artificial neural network (ANN), and gradient boosting machine (GBM) models. The ACO-BP model also exhibited the fastest recognition speed among the four models. Moreover, the ACO-BP model shows varied improvements in recognition accuracy for each of the three driving styles, with an increase of 13.7%, 4.4%, and 4.3%, respectively, compared to the BP model. The simulation results validate the high accuracy, real-time capability, and classification effectiveness of this model in driving style recognition, providing new insights for this field.
... AI encompasses all forms of classical machine learning and modern artificial neural networks and through the processing of large amounts of available data (2) develop more and more human-like capabilities for decision-making and planning. The various applications of artificial intelligence (AI) are revolutionizing numerous aspects of our society (3)(4)(5), including the academic community (5) focusing on applied research relevant to sports. ...
Here, we performed a non-systematic analysis of the strength, weaknesses, opportunities, and threats (SWOT) associated with the application of artificial intelligence to sports research, coaching and optimization of athletic performance. The strength of AI with regards to applied sports research, coaching and athletic performance involve the automation of time-consuming tasks, processing and analysis of large amounts of data, and recognition of complex patterns and relationships. However, it is also essential to be aware of the weaknesses associated with the integration of AI into this field. For instance, it is imperative that the data employed to train the AI system be both diverse and complete, in addition to as unbiased as possible with respect to factors such as the gender, level of performance, and experience of an athlete. Other challenges include e.g., limited adaptability to novel situations and the cost and other resources required. Opportunities include the possibility to monitor athletes both long-term and in real-time, the potential discovery of novel indicators of performance, and prediction of risk for future injury. Leveraging these opportunities can transform athletic development and the practice of sports science in general. Threats include over-dependence on technology, less involvement of human expertise, risks with respect to data privacy, breaching of the integrity and manipulation of data, and resistance to adopting such new technology. Understanding and addressing these SWOT factors is essential for maximizing the benefits of AI while mitigating its risks, thereby paving the way for its successful integration into sport science research, coaching, and optimization of athletic performance.
Obstacle avoidance in multi-lane traffic scenarios remains a critical challenge for autonomous vehicles, requiring robust decision-making and precise path planning to ensure safety and efficiency in dynamic environments. This paper proposes an integrated framework combining a Time-to-Collision (TTC)-based module for rapid risk assessment and a Large Language Model (LLM)-assisted decision-making module to handle complex situations involving conflicting risks. A novel Velocity-Direction Decomposition (VDD) kinematic model is introduced to address the limitations of classical Longitudinal-Lateral Decomposition (LLD) methods, ensuring smooth and dynamically feasible motion. Model Predictive Control (MPC) is employed to generate collision-free trajectories that respect vehicle dynamics while maintaining stability and passenger comfort. Simulations validate the framework across various scenarios, demonstrating its capability to adapt to diverse traffic conditions, enhance path feasibility, and improve overall system safety and efficiency.
