Predicting vulnerableroad user behavior is an essential prerequisite for deploying Automated Driving Systems (ADS) in the real-world. Pedestrian crossing intention should be recognized in real-time, especially for urban driving. Recent works have shown the potential of using vision-based deep neural network models for this task. However, these models are not robust and certain issues still need to be resolved. First, the global spatio-temporal context that accounts for the interaction between the target pedestrian and the scene has not been properly utilized. Second, the optimal strategy for fusing different sensor data has not been thoroughly investigated. This work addresses the above limitations by introducing a novel neural network architecture to fuse inherently different spatio-temporal features for pedestrian crossing intention prediction. We fuse different phenomena such as sequences of RGB imagery, semantic segmentation masks, and ego-vehicle speed in an optimal way using attention mechanisms and a stack of recurrent neural networks. The optimal architecture was obtained through exhaustive ablation and comparison studies. Extensive comparative experiments on the JAAD and PIE pedestrian action prediction benchmarks demonstrate the effectiveness of the proposed method, where state-of-the-art performance was achieved. Our code is open-source and publicly available: https://github.com/OSU-Haolin/Pedestrian_Crossing_Intention_Prediction .

Edge infrastructure and Industry 4.0 required services are offered by edge-servers (ESs) with different computation capabilities to run social application's workload based on a leased-price method. The usage of Social Internet of Things (SIoT) applications increases day-to-day, which makes social platforms very popular and simultaneously requires an effective computation system to achieve high service reliability. In this regard, offloading high required computational social service requests (SRs) in a time slot based on directed acyclic graph (DAG) is an NP-complete problem. Most state-of-art methods concentrate on the energy preservation of networks but neglect the resource sharing cost and dynamic subservice execution time (SET) during the computation and resource sharing. This article proposes a two-step deep reinforcement learning (DRL)-based service offloading (DSO) approach to diminish edge server costs through a DRL influenced resource and SET analysis (RSA) model. In the first level, the service and edge server cost is considered during service offloading. In the second level, the R-retaliation method evaluates resource factors to optimize resource sharing and SET fluctuations. The simulation results show that the proposed DSO approach achieves low execution costs by streamlining dynamic service completion and transmission time, server cost, and deadline violation rate attributes. Compared to the state-of-art approaches, our proposed method has achieved high resource usage with low energy consumption.

The use of edge computing for 3D perception has garnered interest in intelligent transportation systems (ITS) due to its potential to enhance Vehicle-to-Everything (V2X) orchestration through real-time traffic monitoring. The ability to accurately measure depth information in the environment using LiDAR has led to a growing emphasis on 3D detection based on this technology, which has significantly advanced the field of 3D perception. However, the computationally-intensive nature of these operations has made it challenging to meet the real-time deployment requirements using existing methods. The object detection task in the pointcloud domain is hindered by a substantial inconsistency problem caused by its high sparsity, which remains unaddressed. This paper conducts an in-depth analysis of the issue, which has been brought to light by recent research on detecting inconsistency problems in image specialization. To address this problem, we propose a solution in the form of a 3D harmonic loss function, which aims to alleviate the inconsistent predictions based on pointcloud data. In addition, we showcase the viability of optimizing 3D harmonic loss mathematically. Our simulations employ the KITTI dataset and DAIR-V2X-I dataset, and our proposed approach significantly surpasses the performance of benchmark models. Additionally, we validate the efficiency of our proposed model through its deployment on an edge device (Jetson Xavier TX) in a simulated environment.

3D object detection based on LiDAR point cloud and prior anchor boxes is a critical technology for autonomous driving environment perception and understanding. Nevertheless, an overlooked practical issue in existing methods is the ambiguity in training sample allocation based on box Intersection over Union (IoU_box). This problem impedes further enhancements in the performance of anchor-based LiDAR 3D object detectors. To tackle this challenge, this paper introduces a new training sample selection method that utilizes point cloud distribution for anchor sample quality measurement, named Point Assisted Sample Selection (PASS). This method has undergone rigorous evaluation on four widely utilized datasets. Experimental results demonstrate that the application of PASS elevates the average precision of anchor-based LiDAR 3D object detectors to a novel state-of-the-art, thereby proving the effectiveness of the proposed approach. The codes will be made available at https://github.com/ XJTU-Haolin/Point_Assisted_Sample_Selection.