Digital Twin-Assisted Cooperative Driving at Non-Signalized Intersections

Abstract

Digital Twin, as an emerging technology related to Cyber-Physical Systems (CPS) and Internet of Things (IoT), has attracted increasing attentions during the past decade. Conceptually, a Digital Twin is a digital replica of a physical entity in the real world, and this technology is leveraged in this study to design a cooperative driving system at non-signalized intersections, allowing connected vehicles to cooperate with each other to cross intersections without any full stops. Within the proposed Digital Twin framework, we developed an enhanced first-in-firstout (FIFO) slot reservation algorithm to schedule the sequence of crossing vehicles, a consensus motion control algorithm to calculate vehicles' referenced longitudinal motion, and a modelbased motion estimation algorithm to tackle communication delay and packet loss. Additionally, an augmented reality (AR) humanmachine-interface (HMI) is designed to provide the guidance to drivers to cooperate with other connected vehicles. Agent-based modeling and simulation of the proposed system is conducted in Unity game engine based on a real-world map in San Francisco, and the human-in-the-loop (HITL) simulation results prove the benefits of the proposed algorithms with 20% reduction in travel time and 23.7% reduction in energy consumption, respectively, when compared with traditional signalized intersections.

Vision-Cloud Data Fusion for ADAS: A Lane Change Prediction Case Study

“…Game engines (such as Unity [32] and Unreal [33]) are software systems that consist of a graphics rendering engine, a physical engine (for object movement, interaction, and collision detection), and an UI interference for managing elements (e.g., sound tracks, models, visual effects, etc.). Game engine-based test environments were explored by various studies to prototype connected vehicles [34] , [35], model driver behaviors [36], and simulate autonomous driving [25], [37]. In this study, Unity is adopted to conduct modeling and evaluation of the proposed data fusion system, given its strengths in visualization, graphics design, as well as external joystick (i.e., driving simulator) integration.…”

Improved model‐free adaptive predictive control‐based cooperative driving control for connected and automated vehicles subject to time‐varying communication delays and packet losses at signal‐free intersections

“…In addition, similar to existing research [17–19], several assumptions regarding the studied scenario must be considered as follows: Assumption CAVs driving at a signal‐free intersection simultaneously experience different communication time‐varying delays and packet losses, and each vehicle also encounters time‐varying delays and packet losses at different times. Assumption The random time‐varying communication delay is bounded, and it can be considered as τ and satisfies $${\tau _{\min }} \le \tau \le {\tau _{\max }}$$, where $${\tau _{\min }}$$ is the minimum delay and $${\tau _{\max }}$$ is the maximum delay. Assumption All vehicles involved are CAVs.…”

“…In addition, similar to existing research [17][18][19], several assumptions regarding the studied scenario must be considered as follows: Assumption 1. CAVs driving at a signal-free intersection simultaneously experience different communication timevarying delays and packet losses, and each vehicle also encounters time-varying delays and packet losses at different times.…”

“…Wang et al. [19] proposed a model‐based motion estimation algorithm to address the issues of communication time‐varying delays and packet losses. Although these studies attempted to provide many effective solutions for CAVs to cross communication‐constrained unsignallized intersections, the potential for reducing the negative effects on driving CAVs after encountering the time‐varying delays and random packet losses in the V2I communication control system is yet to be well understood.…”

“…Further, the solution in ref. [19] is greatly affected by the model accuracy of the controlled plant, resulting in a larger control error, which affects the driving states.…”