Enhanced Traffic Light Guidance for Safe and Energy-Efficient Driving: A Study on Multiple Traffic Light Advisor (MTLA) and 5G Integration

Journal of Intelligent & Robotic Systems (2024) 110:73 https://doi.org/10.1007/s10846-024-02110-6 REGULAR PAPER Enhanced Traffic Light Guidance for Safe and Energy-Efficient Driving: A Study on Multiple Traffic Light Advisor (MTLA) and 5G Integration Michael Khayyat1 · Alberto Gabriele1 · Francesca Mancini1 · Stefano Arrigoni1 · Francesco Braghin1 Received: 2 February 2023 / Accepted: 30 April 2024 © The Author(s) 2024 Abstract This paper presents Multiple Traffic Light Advisor (MTLA), a novel Green Light Optimal Speed Advisory (GLOSA) system that leverages 5G communication technology. GLOSA systems are emerging as a key component in intelligent transportation systems, thanks to the development of effective communication technologies. At its core, MTLA serves as a guidance system for drivers, providing real-time instructions to adjust vehicle speed to optimize the utilization of current and future states of traffic lights along their route.The work addresses several limitations in the current state-of-the-art approaches, including the use of an overly simplified velocity profile, the omission of potential grip and jerk in problem formulation, and the absence of a detailed description of the algorithm’s implementation aspects. Initially, we comprehensively present an optimizationfree implementation of the overall control architecture based on an unconventional speed profile. Subsequently, MTLA is improved within a non-linear Model Predictive Control (MPC) framework which uses the latter nonoptimal solution as an initial guess and considers potential grip and jerk in the problem formulation. The developed systems are numerically tested and compared within a high-fidelity simulation environment using the IPG CarMaker simulator. The results demonstrate promising performance in terms of energy savings, with a significant reduction of 37% in energy usage, as well as improved overall comfort with respect to the case where no guidance is given to the driver. These findings suggest a high potential for future developments in this domain. Keywords GLOSA · ADAS · Traffic light advisor · Connected vehicles · 5G · V2X · MPC 1 Introduction Green Light Optimal Speed Advisory (GLOSA) is an advisory system aimed at improving safety and sustainability in intelligent transportation systems (ITS) [1]. These systems are a subset of vehicle-to-infrastructure (V2I) applications that facilitate the transfer of signal information between B Michael Khayyat Alberto Gabriele Francesca Mancini Stefano Arrigoni Francesco Braghin 1 Department of Mechanical Engineering, Politecnico di Milano, Via La Masa, 1, Milano 20156, MI, Italy vehicles and traffic lights. The primary objective of GLOSA systems is to provide drivers with speed recommendations that allow for a smoother approach to intersections, ideally passing through without the need to stop, thus reducing travel time [2–5] and improving fuel efficiency [6–8]. This is typically achieved through the utilization of road data and the integration of traffic light schedules into the architecture of the advisory system [9]. 1.1 Literature Review The current literature on GLOSA systems has demonstrated their efficiency and fostered their role as a key component within the realm of intelligent transportation systems. GLOSA systems can be categorized into two types based on the number of traffic lights they consider in real-time to provide recommended speeds: Single-segment GLOSA (S-GLOSA) and multiple-segment GLOSA (M-GLOSA). In [6], the performance and effectiveness of both types are compared, offering valuable insight into their respective 0123456789().: V,-vol 123 73 Page 2 of 22 advantages and limitations in optimizing traffic flow and improving overall transportation efficiency. S-GLOSA systems analyze only the first traffic light encountered by the vehicle, while the M-GLOSA systems take into consideration multiple traffic lights along the vehicle route. S-GLOSA algorithms typically rely on modeling approaches, as demonstrated in [10], which incorporate velocity profiles upstream and downstream of the intersection. The determination of the speed profile takes into account various criteria. In [11], Barth et al. optimize the speed profile based on minimizing the total tractive power demand and idle time. In [12], the priority is to reduce driver annoyance by minimizing the difference between the suggested speed and the actual speed, or by aiming to pass the traffic light as quickly as possible [12]. In [13], GLOSA is optimized, taking into account considerations of both fuel efficiency and traffic efficiency. The approach to determine the target velocity involves calculating the time required for a given vehicle to reach the upcoming traffic light, assuming a uniformly accelerated motion profile. In cases where the vehicle approaches the traffic light while it is displaying a green signal, the driver is guided to maintain the maximum allowable speed on the road. Conversely, if the vehicle is anticipated to arrive during a red phase, the target speed is computed to facilitate the vehicle’s arrival at the traffic light during the subsequent green phase, once again utilizing a uniformly accelerated motion profile. The simulation results demonstrate that, in scenarios with high traffic density, the benefits increase with a higher number of equipped vehicles. In [14], the performance of three velocity planning algorithms was evaluated, with the objective of minimizing the acceleration rates for a vehicle traversing an empty signalized 10-intersection corridor. The result of the stochastic simulations revealed a notable 12%-14% reduction in both fuel consumption and pollutant emissions. Empirical studies, such as the experimental campaigns conducted in [15–17], have demonstrated the efficacy of GLOSA systems. In [15], a system designed specifically for buses (referred to as B-GLOSA), where a moving-horizon dynamic programming problem is designed and solved using an A-star search method. The proposed approach is limited to a single traffic light and does not take into account ground friction and comfort parameters, such as jerk. This system was developed and tested on a group of 30 participants. The results revealed significant savings in fuel and travel time, with an average reduction of 22.1% in fuel consumption and 6.1% in travel time compared to uninformed driving practices. These findings provide empirical evidence of the benefits and effectiveness of implementing GLOSA systems in real-world scenarios. In [16], Zhang et al. present a hierarchical GLOSA system. The simulation and field test evaluated the energy saving performance of the GLOSA system by considering queuing effects and driver tracking errors. 123 Journal of Intelligent & Robotic Systems (2024) 110:73 The effectiveness of M-GLOSA systems compared to SGLOSA is demonstrated in [18], specifically under free-flow traffic conditions. It should be noted that the cons (...truncated)