A Comprehensive Survey on Cooperative Intersection Management for Heterogeneous Connected Vehicles

Nowadays, with the advancement of technology, world is trending toward high mobility and dynamics. In this context, intersection management (IM) as one of the most crucial elements of the transportation sector demands high attention. Today, road entities including infrastructures, vulnerable road users (VRUs) such as motorcycles, moped, scooters, pedestrians, bicycles, and other types of vehicles such as trucks, buses, cars, emergency vehicles, and railway vehicles like trains or trams are able to communicate cooperatively using vehicle-to-everything (V2X) communications and provide traffic safety, efficiency, infotainment and ecological improvements. In this paper, we take into account different types of intersections in terms of signalized, semi-autonomous (hybrid) and autonomous intersections and conduct a comprehensive survey on various intersection management methods for heterogeneous connected vehicles (CVs). We consider heterogeneous classes of vehicles such as road and rail vehicles as well as VRUs including bicycles, scooters and motorcycles. All kinds of intersection goals, modeling, coordination architectures, scheduling policies are thoroughly discussed. Signalized and semi-autonomous intersections are assessed with respect to these parameters. We especially focus on autonomous intersection management (AIM) and categorize this section based on four major goals involving safety, efficiency, infotainment and environment. Each intersection goal provides an in-depth investigation on the corresponding literature from the aforementioned perspectives. Moreover, robustness and resiliency of IM are explored from diverse points of view encompassing sensors, information management and sharing, planning universal scheme, heterogeneous collaboration, vehicle classification, quality measurement, external factors, intersection types, localization faults, communication anomalies and channel optimization, synchronization, vehicle dynamics and model mismatch, model uncertainties, recovery, security and privacy.

View this article on IEEE Xplore


Robust Stereo Visual SLAM for Dynamic Environments With Moving Object

The accuracy of localization and mapping of automated guided vehicles (AGVs) using visual simultaneous localization and mapping (SLAM) is significantly reduced in a dynamic environment compared to a static environment due to incorrect data association caused by dynamic objects. To solve this problem, a robust stereo SLAM algorithm based on dynamic region rejection is proposed. The algorithm first detects dynamic feature points from the fundamental matrix of consecutive frames and then divides the current frame into superpixels and labels its boundaries with disparity. Finally, dynamic regions are obtained from dynamic feature points and superpixel boundaries types; only the static area is used to estimate the pose to improve the localization accuracy and robustness of the algorithm. Experiments show that the proposed algorithm outperforms ORB-SLAM2 in the KITTI dataset, and the absolute trajectory error in the actual dynamic environment can be reduced by 84% compared with the conventional ORB-SLAM2, which can effectively improve the localization and mapping accuracy of AGVs in dynamic environments.

*Published in the IEEE Vehicular Technology Society Section within IEEE Access.

View this article on IEEE Xplore


Collision Avoidance in Pedestrian-Rich Environments With Deep Reinforcement Learning

Collision avoidance algorithms are essential for safe and efficient robot operation among pedestrians. This work proposes using deep reinforcement (RL) learning as a framework to model the complex interactions and cooperation with nearby, decision-making agents, such as pedestrians and other robots. Existing RL-based works assume homogeneity of agent properties, use specific motion models over short timescales, or lack a principled method to handle a large, possibly varying number of agents. Therefore, this work develops an algorithm that learns collision avoidance among a variety of heterogeneous, non-communicating, dynamic agents without assuming they follow any particular behavior rules. It extends our previous work by introducing a strategy using Long Short-Term Memory (LSTM) that enables the algorithm to use observations of an arbitrary number of other agents, instead of a small, fixed number of neighbors. The proposed algorithm is shown to outperform a classical collision avoidance algorithm, another deep RL-based algorithm, and scales with the number of agents better (fewer collisions, shorter time to goal) than our previously published learning-based approach. Analysis of the LSTM provides insights into how observations of nearby agents affect the hidden state and quantifies the performance impact of various agent ordering heuristics. The learned policy generalizes to several applications beyond the training scenarios: formation control (arrangement into letters), demonstrations on a fleet of four multirotors and on a fully autonomous robotic vehicle capable of traveling at human walking speed among pedestrians.

View this article on IEEE Xplore