Joint Optimization of Depth and Ego-Motion for Intelligent Autonomous Vehicles

Abstract

The three-dimensional (3D) perception of autonomous vehicles is crucial for localization and analysis of the driving environment, while it involves massive computing resources for deep learning, which can't be provided by vehiclemounted devices. This requires the use of seamless, reliable, and efficient massive connections provided by the 6G network for computing in the cloud. In this paper, we propose a novel deep learning framework with 6G enabled transport system for joint optimization of depth and ego-motion estimation, which is an important task in 3D perception for autonomous driving. A novel loss based on feature map and quadtree is proposed, which uses feature value loss with quadtree coding instead of photometric loss to merge the feature information at the texture-less region. Besides, we also propose a novel multi-level V-shaped residual network to estimate the depths of the image, which combines the advantages of V-shaped network and residual network, and solves the problem of poor feature extraction results that may be caused by the simple fusion of low-level and high-level features. Lastly, to alleviate the influence of image noise on pose estimation, we propose a number of parallel sub-networks that use RGB image and its feature map as the input of the network. Experimental results show that our method significantly improves the quality of the depth map and the localization accuracy and achieves the state-of-the-art performance.

Intelligent Embedded Systems Platform for Vehicular Cyber-Physical Systems

“…By integrating computing, communication, and control with physical tasks, CPSs can often optimise industrial operations to achieve improved reliability, efficiency and flexibility [22]. Moreover, the ability to monitor and control operations in real-time often results in quicker fault resolution and improved safety, especially in the context of autonomous vehicles [1]. In fact, CPSs serve as the foundation of Industry 4.0, a term used to describe increased automation, connectivity and data exchange in industrial processes.…”

“…These systems are designed to interact with a physical environment, collect data from sensors, and analyse that data in real-time using advanced algorithms and machine learning (ML) techniques. Consequently, ICPSs can make intelligent decisions and execute actions based on incoming data [1]. ICPSs have the ability to transform various industries such as manufacturing, transportation, and energy.…”

Autonomous Vehicles With a 6G-Based Intelligent Cybersecurity Model

“…According to [20], the optimization of accuracy in ITS and intelligent AV (IAV) is the strongest measurement of finding a decision for technical issues and developments. Here, all calculations and measurements must be accurate, with precise values optimized through an efficient optimization method.…”

Analysis of the Influence of the Front Vehicle on the Propagation Loss of ETC System of the Back Vehicle

“…However, it neglects the influence of the front vehicle. The attenuation of radio signals and the composition of multipath components are affected not only by the obstacle's position and material but also by the geometry features of the obstacle [24]- [26]. Therefore, in analyzing the ETC scene with the interference of the front vehicle, the geometric shape of the front vehicle and the back vehicle should be considered.…”