Autonomous Vehicle Perception Research Articles

How Well Can Driverless Vehicles Hear? An Introduction to Auditory Perception for Autonomous and Smart Vehicles

From sirens to car horns, the urban environment is full of sounds that are designed to direct drivers’ attention to conditions that require special care. Microphone-equipped autonomous vehicles can also use these acoustic cues to increase safety and performance. This article explores auditory perception in the context of autonomous driving and smart vehicles, in general, examining the potential of exploiting acoustic cues in driverless vehicle technology. With a journey through the literature, we discuss various applications of auditory perception in driverless vehicles, ranging from the identification and localization of external acoustic objects to leveraging ego noise for motion estimation and engine fault detection. In addition to solutions already proposed in the literature, we point out directions for further investigations, focusing, in particular, on parallel studies in the areas of acoustics and audio signal processing that demonstrate potential for improving the performance of driverless cars.

The politics of new driving technologies: Political ideology and autonomous vehicle adoption

Autonomous vehicles (AVs) typify the nexus of smart Internet-based technology and prior innovations in transportation. A challenge with AV research is that the technology is not yet readily available for consumers to experience. Thus, public perceptions of AVs are often assessed through survey research which has uncovered demographic and socio-economic differences in the willingness to adopt and pay for AVs. It has also provided information about the perceived benefits and risks associated with AVs and how these perceived benefits and risks affects support for self-driving car technology. More recently, studies have found that political ideology is linked to perceived concerns about self-driving cars but have not yet assessed whether this link extends to the intent to adopt AVs. Given this gap in our knowledge, the contributions of the present paper our twofold. One, we will assess whether political ideology impacts the intention to adopt AVs. Two, we will assess whether political ideology directly or indirectly affects the intention to adopt AVs. As regards the latter, we will conduct a mediation analysis with a path model to assess the extent that political ideology indirectly affects the intention to adopt via the perceived benefits and concerns survey respondents expressed about AVs. Our results reveal political ideology is an important predictor of individuals’ intent to adopt AVs, as characterized by both willingness to ride in and to own AVs. Specifically, compared to conservative participants, moderates and liberals reported higher AV adoption intentions. We also find that the effect of political ideology on AV adoption intention is mediated by participants’ perceived benefits and concerns about AVs. Compared to conservatives, political moderates reported AV adoption intention via higher perceived benefits about AVs. Compared to conservatives, liberals reported higher AV adoption intention through both higher perceived benefits and lower perceived concerns about AVs.

“They have to be better than human drivers!” Motorcyclists’ and cyclists’ perceptions of autonomous vehicles

Road users and the general population by and large recognise the value of vehicles with automated driving systems and features (otherwise typically known as Autonomous Vehicles (AVs)) in terms of road safety, reduced emissions and convenience, but are still wary of their capability, preferring the ‘comfort zone’ of human operator intervention. Motorcyclists and cyclists conversely, are vulnerable to human fallibility in driving, with the majority of crashes occurring as a consequence of other drivers’ inattention. The transition period associated with the introduction of AVs will require AVs and motorcyclists/cyclists sharing the road for a number of years yet, so we need to understand motorcyclists’/cyclists’ perception of AVs. The question of interest here is whether motorcyclists/cyclists reflect the historical literature in this area by having higher levels of trust for human drivers over AVs, or whether they have higher levels of trust in AVs because it removes the ‘human element’ that has been proven to be particularly dangerous for them. Here we surveyed motorcyclists and cyclists about their trust in human drivers and AVs, and developed a novel suite of questions designed to interrogate the difference between trust in general versus trust as a concept of their own personal safety. Some of the salient outcomes suggest that motorcyclists have medium to low levels of trust for both human drivers and AVs, but are significantly more likely to believe that AVs are safer in terms of their own personal safety, such as prioritising or detecting the rider, compared to human drivers. This relationship varies with age and crash experience. The results here are consistent with the logic that motorcyclists/cyclists have a heightened sense of vulnerability on the road and welcome the introduction of AVs as a way of mitigating personal risk when riding. This insight will be crucial to the subsequent roll-out of AVs in the future.

Public acceptance and perception of autonomous vehicles: a comprehensive review.

Autonomous vehicles (AVs) or self-driving cars have the potential to provide many benefits such as improving mobility and reducing the energy and emissions consumed, travel time, and vehicle ownership. Thus, in the last few years, both research and industry have put significant efforts to develop AVs. However, laws and regulations are not ready yet for this switch and the legal sector is unable to take the lead but follow the development of AVs. Besides, the social acceptance is considered as a main key factor for the success of any new technology. Despite the enthusiastic speculation of AVs, little is known about the public acceptance and perception of the AVs technology or the factors that influence the public acceptance. This paper reviews the previous studies that focuses on testing the public acceptance and perception of AVs and sketches out the main trends in this area to provide some directions and recommendations for the future. This paper focuses on the influence of safety, ethics, liability, regulations, and the recent pandemic on the public acceptance of AVs.

Living with Autonomy: Public Perceptions of an AI-Mediated Future

The arrival of autonomous systems powered by artificial intelligence (AI) offers new possibilities for life, yet the focus tends to be more on the technology than the people it serves. Planners should consider the likely reception awaiting emerging intelligent systems. Using an online survey of 3,249 faculty, staff, and students at a major research university, we tested perceptions of autonomy, including domotics and autonomous vehicles. Embracing the new technology with variations in attitude associated with age, gender, and familiarity with new technology, people’s openness to AI-enabled devices applies if they remain a tool to support work and not replace human-centered interactions.

A Grid-Based Framework for Collective Perception in Autonomous Vehicles.

Today, perception solutions for Automated Vehicles rely on sensors on board the vehicle, which are limited by the line of sight and occlusions caused by any other elements on the road. As an alternative, Vehicle-to-Everything (V2X) communications allow vehicles to cooperate and enhance their perception capabilities. Besides announcing its own presence and intentions, services such as Collective Perception (CPS) aim to share information about perceived objects as a high-level description. This work proposes a perception framework for fusing information from on-board sensors and data received via CPS messages (CPM). To that end, the environment is modeled using an occupancy grid where occupied, and free and uncertain space is considered. For each sensor, including V2X, independent grids are calculated from sensor measurements and uncertainties and then fused in terms of both occupancy and confidence. Moreover, the implementation of a Particle Filter allows the evolution of cell occupancy from one step to the next, allowing for object tracking. The proposed framework was validated on a set of experiments using real vehicles and infrastructure sensors for sensing static and dynamic objects. Results showed a good performance even under important uncertainties and delays, hence validating the viability of the proposed framework for Collective Perception.

Data Processing for Perception of Autonomous Vehicles in Urban Traffic Environments

Data Processing for Perception of Autonomous Vehicles in Urban Traffic Environments

Listen to Social Media Users: Mining Chinese Public Perception of Autonomous Vehicles after Crashes

Listen to Social Media Users: Mining Chinese Public Perception of Autonomous Vehicles after Crashes

Autonomous Vehicle Perception Sensor Data in Sustainable and Smart Urban Transport Systems

Autonomous Vehicle Perception Sensor Data in Sustainable and Smart Urban Transport Systems

Intelligent Transportation Applications, Autonomous Vehicle Perception Sensor Data, and Decision-Making Self-Driving Car Control Algorithms in Smart Sustainable Urban Mobility Systems

Intelligent Transportation Applications, Autonomous Vehicle Perception Sensor Data, and Decision-Making Self-Driving Car Control Algorithms in Smart Sustainable Urban Mobility Systems

Learning Collision-Free Space Detection From Stereo Images: Homography Matrix Brings Better Data Augmentation

Collision-free space detection is a critical component of autonomous vehicle perception. The state-of-the-art algorithms are typically based on supervised deep learning. Their performance is dependent on the quality and amount of labeled training data. It remains an open challenge to train deep convolutional neural networks (DCNNs) using only a small quantity of training samples. Therefore, in this article, we mainly explore an effective training data augmentation approach that can be employed to improve the overall DCNN performance, when additional images captured from different views are available. Due to the fact that the pixels in collision-free space (generally regarded as a planar surface) between two images, captured from different views, can be associated using a homography matrix, the target image can be transformed into the reference view. This provides a simple but effective way to generate training data from additional multiview images. Extensive experimental results, conducted with six state-of-the-art semantic segmentation DCNNs on three datasets, validate the effectiveness of the proposed method for enhancing collision-free space detection performance. When validated on the KITTI road benchmark, our approach provides the best results, compared with other state-of-the-art stereo vision-based collision-free space detection approaches.

People with disabilities’ perceptions of autonomous vehicles as a viable transportation option to improve mobility: An exploratory study using mixed methods

Autonomous vehicles (AVs) are expected to bring significant changes to the mobility of people, especially those with disabilities. Despite the strong potential of AVs to impact the lives of people with disabilities, little attention has been paid to understand their perspectives on this technology. This study aims to fill the gap, by exploring the mobility challenges experienced by people with disabilities and the overall perceptions of autonomous vehicle transportation (AVT) services among people with disabilities. The specific focus is on individuals with physical disabilities and individuals with visual impairments. This study used a three-phase exploratory sequential mixed-methods design. We began by conducting focus groups and analyzing the collected data. From the focus group results, we developed a survey instrument in the second phase. In the third phase, we collected and analyzed the survey data to verify the initial focus group findings. Additionally, the survey included stated preference choice experiments to assess the AV acceptance level of people with disabilities. The results revealed that people with disabilities’ mobility issues with current public transit services and neighborhood built environments may influence their positive attitudes toward AVT services. Despite several concerns raised about AVs regarding accessibility, safety, and reliability, most participants showed a high acceptance level of AVT. The findings provide industry and policy-makers with insights into the expectations, concerns, and needs regarding AVT from the perspectives of people with disabilities.

Deep Dual-Modal Traffic Objects Instance Segmentation Method Using Camera and LIDAR Data for Autonomous Driving

Recent advancements in environmental perception for autonomous vehicles have been driven by deep learning-based approaches. However, effective traffic target detection in complex environments remains a challenging task. This paper presents a novel dual-modal instance segmentation deep neural network (DM-ISDNN) by merging camera and LIDAR data, which can be used to deal with the problem of target detection in complex environments efficiently based on multi-sensor data fusion. Due to the sparseness of the LIDAR point cloud data, we propose a weight assignment function that assigns different weight coefficients to different feature pyramid convolutional layers for the LIDAR sub-network. We compare and analyze the adaptations of early-, middle-, and late-stage fusion architectures in depth. By comprehensively considering the detection accuracy and detection speed, the middle-stage fusion architecture with a weight assignment mechanism, with the best performance, is selected. This work has great significance for exploring the best feature fusion scheme of a multi-modal neural network. In addition, we apply a mask distribution function to improve the quality of the predicted mask. A dual-modal traffic object instance segmentation dataset is established using a 7481 camera and LIDAR data pairs from the KITTI dataset, with 79,118 manually annotated instance masks. To the best of our knowledge, there is no existing instance annotation for the KITTI dataset with such quality and volume. A novel dual-modal dataset, composed of 14,652 camera and LIDAR data pairs, is collected using our own developed autonomous vehicle under different environmental conditions in real driving scenarios, for which a total of 62,579 instance masks are obtained using semi-automatic annotation method. This dataset can be used to validate the detection performance under complex environmental conditions of instance segmentation networks. Experimental results on the dual-modal KITTI Benchmark demonstrate that DM-ISDNN using middle-stage data fusion and the weight assignment mechanism has better detection performance than single- and dual-modal networks with other data fusion strategies, which validates the robustness and effectiveness of the proposed method. Meanwhile, compared to the state-of-the-art instance segmentation networks, our method shows much better detection performance, in terms of AP and F1 score, on the dual-modal dataset collected under complex environmental conditions, which further validates the superiority of our method.

Perception of autonomous vehicles by the modern society: a survey

Autonomous vehicles (AVs) are undergoing rapid worldwide development. They will only become a success if they are accepted by their users. Therefore, there is a need for user acceptance for these vehicles. Previous studies on acceptance of AV have identified several predictors. Inspired by these studies, the authors’ investigation is aimed at sociodemographic characteristics, including broader individual and societal acceptance, beyond technical issues to get a clear view of user acceptance. In this study, they surveyed 229 respondents, using a 46-item online questionnaire. Overall, the authors’ analysis revealed that the respondents are most concerned about crashing/malfunctioning, purchase price, liability for incidents, interaction with non-AV, performance in unexpected situations, hacking and safety. The results also revealed that the AV is perceived as ‘somewhat low risk’ to drive. Gender, age, education level and employment status had varied relationships with the perceived concerns and general attitude towards the AV. For instance, respondents with a university degree (Bachelor/Master/PhD) are less concerned about the liability of accidents and AV system failure than those without it. Similarly, respondents between 36 and 65 years of age are more concerned and even refused to drive AV in comparison to the age ranges of 18–35 years and 65 + years.

Deep Learning Sensor Fusion for Autonomous Vehicle Perception and Localization: A Review.

Autonomous vehicles (AV) are expected to improve, reshape, and revolutionize the future of ground transportation. It is anticipated that ordinary vehicles will one day be replaced with smart vehicles that are able to make decisions and perform driving tasks on their own. In order to achieve this objective, self-driving vehicles are equipped with sensors that are used to sense and perceive both their surroundings and the faraway environment, using further advances in communication technologies, such as 5G. In the meantime, local perception, as with human beings, will continue to be an effective means for controlling the vehicle at short range. In the other hand, extended perception allows for anticipation of distant events and produces smarter behavior to guide the vehicle to its destination while respecting a set of criteria (safety, energy management, traffic optimization, comfort). In spite of the remarkable advancements of sensor technologies in terms of their effectiveness and applicability for AV systems in recent years, sensors can still fail because of noise, ambient conditions, or manufacturing defects, among other factors; hence, it is not advisable to rely on a single sensor for any of the autonomous driving tasks. The practical solution is to incorporate multiple competitive and complementary sensors that work synergistically to overcome their individual shortcomings. This article provides a comprehensive review of the state-of-the-art methods utilized to improve the performance of AV systems in short-range or local vehicle environments. Specifically, it focuses on recent studies that use deep learning sensor fusion algorithms for perception, localization, and mapping. The article concludes by highlighting some of the current trends and possible future research directions.

Hybrid Sensing Data Fusion of Cooperative Perception for Autonomous Driving With Augmented Vehicular Reality

Augmented vehicular reality (AVR) is one of the key technologies to realize intelligent transportation in the future, which can significantly improve traffic safety and transportation efficiency of autonomous driving. However, available computation and spectrum resources of vehicles are not well utilized to meet the requirements of cooperative perception of autonomous vehicles. In order to meet the needs of sharing sensing data to cooperatively perceive the surrounding environment, executing delay-sensitive and computationally intensive tasks of autonomous driving applications, we propose computation offloading and resource allocation optimization for AVR (CoroAVR) algorithm with hybrid sensing data fusion of cooperative perception to process the real-time data in fog-edge computing for maximizing system throughput and spectrum utilization on the premise of ensuring the quality of task completion. First, the minimum signal to interference plus noise ratio needed to complete the task is obtained with the given maximum computing resources. Second, the optimal power allocation is carried out by using convex optimization theory, and the throughput gain is calculated, and the offloading decision is made by comparing the throughput gain. Finally, the channel allocation problem is solved by using the maximum matching algorithm of the bipartite graph, and the computation resource allocation is studied. The simulation results show that the performance of the proposed algorithm is better than that of the contrast algorithm.

Modelling the acceptance of fully autonomous vehicles: A media-based perception and adoption model

As the technology matures, fully autonomous vehicles (AVs) are on the corner. This calls for exploring the factors that might influence potential users’ perception and acceptance of AVs. Limited existing studies related to acceptance modeling investigated the effects of media and human on fully AVs’ beliefs. Hence, a media-based perception and adoption model (MPAM) is developed to investigate how information and opinion (from mass media and social media) affect human self-perception (including self-efficacy and subjective norms) and product value perception (including perceived usefulness and risks), which in turn drive users’ adoption intention to private AVs and public AVs as well. Through a questionnaire survey, 355 samples from two universities were collected in Beijing. The structural equation model results confirm that media channels have salient effects on consumer and product with different emphases. Mass media enhances potential users’ self-efficacy of fully AVs, while social media strengthens subjective norms. Both usefulness and risks of AVs are perceived simultaneously via mass media, whereas risks perception can be significantly eliminated by social media. All constructs of user’s self-perception and product perception are verified to drive users’ intention to using AVs and public AVs. Besides the theoretical and modeling contributions, practical implications are provided for the marketers and stakeholders in the early stages of AVs launch.

Public perception of autonomous vehicles: A qualitative study based on interviews after riding an autonomous shuttle

Autonomous vehicles (AVs) can potentially compensate for human error whilst driving. Thus, the number of accidents and the amount of congestion, emissions and fuel consumption could be reduced. For such reduction to occur, insights into public acceptance of AVs must be considered because they are a crucial factor for the successful implementation of AVs in existing traffic systems. PurposeThis study aims to explore (1) the mobility behaviour of current passengers, (2) the perception of the public of how AVs can be applied, (3) the perceived challenges of AVs in terms of integration into existing traffic systems, (4) the general attitude of the public towards AVs and (5) the perceived safety of passengers after riding an autonomous shuttle with a maximum SAE level of 3 in the setting of mixed traffic. MethodThis qualitative study was conducted in Carinthia (Austria) in September 2018. Interviews were conducted with 19 participants aged between 20 and 75 years. The participants were recruited through purposeful sampling, and data were collected through in-depth, semistructured interviews which were recorded, transcribed, organised and analysed using systematic, qualitative content analysis. ResultsResults show that transport mobility plays an important role in social life. In rural areas, AVs can shift transportation modes from private cars to public transportation. The respondents perceive AVs as an alternative more than as a substitute for existing means of transportation. With the integration of AVs into existing traffic systems, the transportation of goods and people could be improved despite related uncertainties. This study explores different aspects of societal, technical, legal and economic challenges. Overall, the respondents feel positive about AVs. Responses regarding safety show that experience with AVs and speed are key factors. Originality/ValueThis study is one of the first to explain qualitatively public perceptions of AVs after an actual ride in an AV under real-life conditions. The results, which help understand AVs from the public’s perspective, may also provide guidelines for the successful integration of AVs in Austria.

A Study on the Users’ Perception of Autonomous Vehicles using Q Methodology

A Study on the Users’ Perception of Autonomous Vehicles using Q Methodology

Deep Learning-Based Localization and Perception Systems: Approaches for Autonomous Cargo Transportation Vehicles in Large-Scale, Semiclosed Environments

Vehicles capable of delivering heavy cargoes are a major means for the promotion of social productivity and are widely applied in industry. Even though self-driving technologies have been studied for a few decades and several successful applications have been demonstrated, autonomous industry vehicles are currently applied only in some specific scenarios with very low speed and fixed routes and are typically implemented in the indoor closed area of small-scale warehouses. In this article, we introduce the main perception and localization approaches of autonomous cargo transportation vehicles for industrial applications. We also demonstrate how these technologies can enable autonomous cargo transportation in the Hong Kong International Airport.