Autonomous Driving Cars Research Articles

A Dispersed Federated Learning Framework for 6G-Enabled Autonomous Driving Cars

Sixth-Generation (6G)-based Internet of Everything applications (e.g. autonomous driving cars) have witnessed a remarkable interest. Autonomous driving cars using federated learning (FL) has the ability to enable different smart services. Although FL implements distributed machine learning model training without the requirement to move the data of devices to a centralized server, it its own implementation challenges such as robustness, centralized server security, communication resources constraints, and privacy leakage due to the capability of a malicious aggregation server to infer sensitive information of end-devices. To address the aforementioned limitations, a dispersed federated learning (DFL) framework for autonomous driving cars is proposed to offer robust, communication resource-efficient, and privacy-aware learning. A mixed-integer non-linear programming (MINLP) optimization problem is formulated to jointly minimize the loss in federated learning model accuracy due to packet errors and transmission latency. Due to the NP-hard and non-convex nature of the formulated MINLP problem, we propose the Block Successive Upper-bound Minimization (BSUM) based solution. Furthermore, the performance comparison of the proposed scheme with three baseline schemes has been carried out. Extensive numerical results are provided to show the validity of the proposed BSUM-based scheme.

An Elderly-Oriented Design of HMI in Autonomous Driving Cars Based on Rough Set Theory and Backpropagation Neural Network

An Elderly-Oriented Design of HMI in Autonomous Driving Cars Based on Rough Set Theory and Backpropagation Neural Network

Drivable Area Detection in Unstructured Environments based on Lightweight Convolutional Neural Network for Autonomous Driving Car

Road detection technology is an important part of the automatic driving environment perception system. With the development of technology, the situations that automatic driving needs to consider will become broader and more complex. This paper contributes a lightweight convolutional neural network model, incorporating novel convolution and parallel pooling modules, an improved network activation function, and comprehensive training and verification with multiple datasets. The proposed model achieves high accuracy in detecting drivable areas in complex autonomous driving situations while significantly improving real-time performance. In addition, we collect data in the field and create small datasets as reference datasets for testing algorithms. This paper designs relevant experimental scenarios based on the datasets and experimental platforms and conducts simulations and real-world vehicle experiments to verify the effectiveness and stability of the algorithm models and technical solutions. The method achieves an MIoU of 90.19 and a single batch time of 340 ms with a batch size of 8, which substantially reduces the runtime relative to a typical deep network structure like ResNet50.

A robust and real-time DNN-based multi-baseline stereo accelerator in FPGAs

Stereo vision is essential to many robotic applications such as obstacle avoidance and 3D mapping in autonomous-driving cars, requiring substantial design efforts to achieve an appropriate balance between robustness and speed. Currently, most existing solutions for stereo vision accelerators are designed under two-camera stereo setups using handcrafted features for stereo estimation. This setup generally suffers from several drawbacks, including limited sensing range and high error rates. To resolve the above issues, we present a deep neural network based multi-baseline stereo accelerator for resource-constrained FPGAs, called Ultra-Stereo, that provides a robust and real-time solution for depth sensing. In Ultra-Stereo, binary neural network (BNN) is leveraged to obtain discriminative feature descriptors while a dynamic weighted cost fusion strategy helps to suppress the local minima in the matching cost function which effectively avoids incorrect stereo estimates. In addition, we provide a set of optimized hardware modules for Ultra-Stereo to estimate the depth map from multi-cameras in real-time. To process the data streams from multi-cameras efficiently, we first propose specific multi-baseline fusion hardware architectures against shorter and larger baseline stereo pairs. Then a time-sharing BNN is used to bridge the gap between processing speed and resource efficiency. Evaluation results demonstrate that Ultra-Stereo achieves higher matching accuracy while guaranteeing real-time responsiveness when compared with existing solutions.

TrEP: Transformer-Based Evidential Prediction for Pedestrian Intention with Uncertainty

With rapid development in hardware (sensors and processors) and AI algorithms, automated driving techniques have entered the public’s daily life and achieved great success in supporting human driving performance. However, due to the high contextual variations and temporal dynamics in pedestrian behaviors, the interaction between autonomous-driving cars and pedestrians remains challenging, impeding the development of fully autonomous driving systems. This paper focuses on predicting pedestrian intention with a novel transformer-based evidential prediction (TrEP) algorithm. We develop a transformer module towards the temporal correlations among the input features within pedestrian video sequences and a deep evidential learning model to capture the AI uncertainty under scene complexities. Experimental results on three popular pedestrian intent benchmarks have verified the effectiveness of our proposed model over the state-of-the-art. The algorithm performance can be further boosted by controlling the uncertainty level. We systematically compare human disagreements with AI uncertainty to further evaluate AI performance in confusing scenes. The code is released at https://github.com/zzmonlyyou/TrEP.git.

Deep Neural Network-based Approach to Identifying Road Lanes

In this paper, we present a new method for Lane Detection (LD) to reduce the impact of some issues associated with Autonomous Driving Cars (ADCs). It relies on the fact that self-driving will be the getaway of the transportation future. The ADC technology has expanded as it does not require human assistance. For ACD to be fully utilized, Machine Learning (ML) tools, such as Deep Neural Networks (DNNs), are required. However, ACD technology uses tools like a camera, GPS, Ultrasonic Sensor (US), and others, which work together to produce accurate ACDs. While adopting ACD, several issues need to be addressed such as carves, blurry, unclean, shadow, sunlight, pedestrians, and weather conditions. The paper proposes a new method to detect when a portion of a road line is missing due to weather conditions or old marking, protecting pedestrians and cars. For lane detection, the DNN model and Hough transform are used. CULane datasets including training and testing samples were used in the experiments. The results show high accuracy levels of 92%, indicating the ability to detect road lanes.

Entangled Intelligent Driving: Relations with Automated Cars

ABSTRACT As machines become increasingly intelligent, the HCI community is presented with new challenges regarding methods to capture and understand user experience (UX). In the case of autonomous driving (AD), this involves new scenarios where humans and intelligent vehicles need to act together in real-life traffic situations with other road users. This article responds to this context by 1) outlining a longitudinal design ethnography method whereby participants drove semiautonomous cars in their everyday environments to capture such human-machine relations in real-life settings, 2) demonstrating the complexities of the relations between humans and AD vehicles, 3) engaging theories of socio-materiality and entanglement to understand the human-machine relations of AD cars, and 4) identifying anticipatory experiences that emerge from these relations and their implications for informing UX design.

A Proposal of System for Promoting the Development of Autonomous Driving Cars and AI Computer-Aided Detection

A Proposal of System for Promoting the Development of Autonomous Driving Cars and AI Computer-Aided Detection

A Comprehensive Survey on Autonomous Driving Cars: A Perspective View

Over the past decades Machine Learning and Deep Learning algorithm played a vital part in the development of Autonomous Vehicle. It is indeed for the perception system to examine the environment around the vehicle and identify the objects such as pedestrian, vehicle and traffic signals, etc. Using this information, control system module can take necessary action to control the vehicle in terms of braking, speed, lane change or steering, etc. This paper focuses on the survey of machine learning algorithms and techniques applied in the design of autonomous driving system over a decade. Performance of each algorithm was analyzed in terms of prediction time and accuracy have been documented and compared.

Design anthropology for emerging technologies: Trust and sharing in autonomous driving futures

In this article we demonstrate how design anthropology theory, methodology and practice can be mobilised to create interventions in how possible human futures with emerging technologies are understood and imagined. Drawing on our research into Human Experience and Expectations of Autonomous Driving (AD) cars we show how: we engaged ethnographic insights to redefine concepts of trust and sharing which contest dominant problem-solution narratives; and we mobilised these insights in applied contexts, through our AD Futures cards which employ ethnographic quotes and examples to disrupt common assumptions, align stakeholders with everyday experience, and pose new questions.

Anticipatory experience in everyday autonomous driving

In this paper, we discuss how people’s user experience (UX) of autonomous driving (AD) cars can be understood as a shifting anticipatory experience, as people experience degrees of AD through evolving advanced driver assistance systems (ADAS) in their everyday context. We draw on our ethnographic studies of five families, who had access to AD research cars with evolving ADAS features in their everyday lives for a duration of 1½ years. Our analysis shows that people gradually adopt AD cars, through a process that involves anticipating if they can trust them, what the ADAS features will do and what the longer-term technological possibilities will be. It also showed that this anticipatory UX occurs within specific socio-technical and environmental circumstances, which could not be captured easily in experimental settings. The implication is that studying anticipation offers us new insights into how people adopt AD in their everyday commute driving.

Hidden Voice Commands: Attacks and Defenses on the VCS of Autonomous Driving Cars

Autonomous driving is becoming one of the most popular applications of AI. Meanwhile, the advances in deep learning have promoted the rapid development of the voice controllable systems (VCSs), which have almost reached the maturity stage. Before autonomous driving cars reach the highest level of automation, intelligent voice interaction remains the primary approach for human-vehicle interaction. Recent works show that such intelligent systems are vulnerable to hidden voice commands that are unnoticed or unintelligible to humans. In particular, an adversary utilizing hidden voice commands is able to control autonomous driving cars. For example, malicious voice commands embedded into the sound of online shared videos can stealthily control the vehicle when people watch the videos in the car. In this article, we investigate the potential perniciousness of hidden voice commands on the VCS of autonomous driving cars, and then discuss feasible defense strategies. We finally propose a pop-noisebased general defense strategy that can resist various kinds of attacks.

Efficient Resource Allocation for Time-Sensitive IoT Applications in Cloud and Fog Environments

Nowadays, with the quick development of internet and cloud technologies, a big number of physical objects are linked to the Internet and every day, more objects are connected to the Internet. It provides great benefits that lead to a significant improvement in the quality of our daily life. Examples include: Smart City, Smart Homes, Autonomous Driving Cars or Airplanes and Health Monitoring Systems. On the other hand, Cloud Computing provides to the IoT systems a series of services such as data computing, processing or storage, analysis and securing. It is estimated that by the year 2025, approximately trillion IoT devices will be used. As a result, a huge amount of data is going to be generated. In addition, in order to efficiently and accurately work, there are situations where IoT applications (such as Self Driving, Health Monitoring, etc.) require quick responses. In this context, the traditional Cloud Computing systems will have difficulties in handling and providing services. To balance this scenario and to overcome the drawbacks of cloud computing, a new computing model called fog computing has proposed. In this paper, a comparison between fog computing and cloud computing paradigms were performed. The scheduling task for an IoT application in a cloud-fog computing system was considered. For the simulation and evaluation purposes, the CloudAnalyst simulation toolkit was used. The obtained numerical results showed the fog computing achieves better performance and works more efficient than Cloud computing. It also reduced the response time, processing time ,and cost of transfer data to the cloud.

Autonomous Driving Cars in Smart Cities: Recent Advances, Requirements, and Challenges

An unprecedented proliferation of autonomous driving technologies has been observed in recent years, resulting in the emergence of reliable and safe transportation services. In the foreseeable future, millions of autonomous cars will communicate with each other and become prevalent in smart cities. Thus, scalable, robust, secure, fault-tolerant, and interoperable technologies are required to support such a plethora of autonomous cars. In this article, we investigate, highlight, and report premier research advances made in autonomous driving by devising a taxonomy. A few indispensable requirements for successful deployment of autonomous cars are enumerated and discussed. Furthermore, we discover and present recent synergies and prominent case studies on autonomous driving. Finally, several imperative open research challenges are identified and discussed as future research directions.

Designing a Modular Safety Certification System for Convergence Products - Focusing on Autonomous Driving Cars -

Designing a Modular Safety Certification System for Convergence Products - Focusing on Autonomous Driving Cars -

Simultaneous Localization and Map Change Update for the High Definition Map-Based Autonomous Driving Car.

High Definition (HD) maps are becoming key elements of the autonomous driving because they can provide information about the surrounding environment of the autonomous car without being affected by the real-time perception limit. To provide the most recent environmental information to the autonomous driving system, the HD map must maintain up-to-date data by updating changes in the real world. This paper presents a simultaneous localization and map change update (SLAMCU) algorithm to detect and update the HD map changes. A Dempster–Shafer evidence theory is applied to infer the HD map changes based on the evaluation of the HD map feature existence. A Rao–Blackwellized particle filter (RBPF) approach is used to concurrently estimate the vehicle position and update the new map state. The detected and updated map changes by the SLAMCU are reported to the HD map database in order to reflect the changes to the HD map and share the changing information with the other autonomous cars. The SLAMCU was evaluated through experiments using the HD map of traffic signs in the real traffic conditions.

Research on Day Night/All-Weather Video SAR Technologies for Autonomous Driving Car

Research on Day Night/All-Weather Video SAR Technologies for Autonomous Driving Car