Deep Learning Inspired Object Consolidation Approaches Using LiDAR Data for Autonomous Driving: A Review

Abstract

Autonomous Driving Vehicle (ADV) services have become a prominent motif in intelligent vehicle technology by adapting deep learning features. Automated driverless services are a hercules task due to the dynamic driving environment and the performance is deliberately reliant on the quality of data fusion from sensors. Therefore, considering advanced 3D LiDAR sensors is essential to measure the surrounding with 360 • coverage. However, accomplishing maximum autonomy is the main challenge because of debilitated and complex driving environmenst. Deep Learning (DL) based models potentially impact surrounding measures for object detection, classification, and tracking. This study describes the importance of DL-LiDAR strategies to formulate ADV research challenges followed by a comprehensive analysis of Semantic Segmentation, Data Fusion, Data Representation, Feature Extraction, Dynamic Object Detection, and Autonomous Driving-Multi-Objective Tracking mechanisms. Unlike existing review papers, we examine various deep learning influenced approaches and describe their precarious measurements. Also, we analyze the impact of systematic methods based on open-source data sets for objectx (x=classification, localization, tracking) consolidation. Most of the summaries confine scalability, and feasibility of DL techniques in ADV to accomplish an intelligent driving system without human interference. Open research problems are discussed in the last section of the article.

Deep Learning and Autonomous Vehicles: Strategic Themes, Applications, and Research Agenda Using SciMAT and Content-Centric Analysis, a Systematic Review

“…Thus, the evolution of the topic of object detection in AVs in recent years can be associated with the revival of CNN research and sensor innovations. As examples, LiDAR [31] and RADAR [32] sensors contributed to enhancing the precision of environment recognition. With the advancement of AV hardware, current models account for not only images captured by cameras, but also the LiDAR point cloud and/or distance measured by the RADAR [13].…”

An effective communication and computation model based on a hybridgraph-deeplearning approach for SIoT

“…[32][33][34], Energy Harvesting-Mobile Edge Computing (EH-MEC) approach has been designed to optimize the service offloading cost based on game theory and Lyapunov optimization theory. A User-centric resource-instance allocation has been designed based on virtual machine capacity to reduce the service execution delay for effective communication [35][36][37]. In this regard, an adaptive trust-weight measurement index and accurate channel selection model are designed to enhance social edge systems' reliability and service quality.…”

Enhancing Indoor Robot Pedestrian Detection Using Improved PIXOR Backbone and Gaussian Heatmap Regression in 3D LiDAR Point Clouds

“…Among these, PIXOR [8] distinguishes itself as a noteworthy single-stage detector that has shown remarkable proficiency with raw point cloud data, though it encounters some challenges when applied to the complex JRDB dataset [1]. These deep learning approaches, especially those that integrate CNNs [9], have transformed 2D image processing and are now making significant strides in the realm of 3D LiDAR data interpretation [10,11]. VoxelNet, for instance, has been instrumental in converting point clouds into structured voxel grids, effectively balancing precision with computational efficiency [5].…”