Green Light Optimal Speed Advisory (GLOSA) systems are a key innovation in Intelligent Transportation Systems (ITS), aiming to optimise vehicle speed profiles while harmonising with traffic light schedules. This paper presents a GLOSA system based on Non-linear Model Predictive Control (NMPC). The proposed system uses real traffic light data and accounts for bus stop dwell times to provide optimal speed alerts. The system has been assessed using a realistic simulation scenario built upon real-world data collected in Milan and implemented within IPG TruckMaker environment. Simulation results demonstrate the effectiveness of the proposed approach compared to a previously developed rule-based algorithm, as it enables the prediction of the vehicle’s future states while ensuring intersection crossings during green light phases. Moreover, real-time feasibility has been verified through deployment as a standalone ROS C++ node, achieving computational times of around 60 ms, thereby providing a new solution within the NMPC update interval of 1 s.

Urban transportation systems are undergoing significant transformations to mitigate environmental impacts while enhancing efficiency and passenger experience. In this context, optimizing bus operations allows to achieve these goals. This paper presents an experimental approach to customize Green Light Optimal Speed Advisory (GLOSA) systems specifically tailored for urban buses (B-GLOSA). B-GLOSA systems provide real-time speed recommendations to the bus driver, aiming to synchronize the vehicle movement with traffic signal timing, thereby reducing energy consumption while improving travel time reliability and passengers comfort. However, existing GLOSA implementations primarily focus on private vehicles and lack customization for the unique characteristics of urban buses that must stop at specific locations for a certain amount of time to allow passengers to load and unload. Our proposed approach involves a comprehensive experimental framework, integrating real-world data analysis, simulation modeling, and field tests. The experimental results demonstrate the potential of B-GLOSA systems in optimizing urban bus operations while reducing energy consumption by 26% and longitudinal acceleration RMS by 21%.

Intelligent Transportation Systems (ITS) are pushing an increasing interest and development when dealing with eco-driving systems. In this framework, this paper presents a method to define speed profiles specifically designed for Green Light Optimal Speed Advisory (GLOSA) systems on buses. GLOSA aims to optimize traffic flow by providing vehicles with real-time speed recommendations synchronized with traffic signal timings. Leveraging statistical analysis of experimental data collected from an urban bus, the study develops a methodology to extract meaningful insights into bus behaviour and traffic dynamics. The proposed approach considers road topology, scheduled bus stops, and signal timings to define simple although suitable speed profiles considering the peculiarities of the motion of a bus in an urban scenario. Through extensive data collection robust statistical data are defined, allowing the definition of vehicle motion profile for effectively develop and implement GLOSA systems. This research contributes to the advancement of Intelligent Transportation Systems by providing realistic data and practical insights for optimizing bus operations in urban environments.

The recent developments in Intelligent Transportation Systems (ITS) have unveiled a great potential for the improvement of traffic management through Advanced Driver Assist Systems (ADAS), both from a safety and environmental point of view. This paper proposes a vehicle localization technique based on Kalman filtering, being the ego-vehicle position a prerequisite for the Traffic Light Advisor (TLA) system to work. The localization algorithm implemented is thought to provide accurate results that can be used for the implementation of ADAS designed to achieve a safer and smoother driving style, which will translate into fewer safety hazards and less energy consumption. In particular, the challenge is to cope with the issues that Global Positioning Systems (GPS) face in urban scenarios, thus proposing a multi-rate sensor fusion approach based on Kalman Filter with Map Matching and a simple kinematic one-dimensional model. The experimental results show an estimation accuracy below 0.5 m on an urban road with long GPS missing areas. Moreover, the paper presents an experimental validation of a Traffic Light Advisor adopting the proposed localization algorithm, showing a 40

In recent years, the research on object detection and tracking is becoming important for the development of advanced driving assistance systems (ADASs) and connected autonomous vehicles (CAVs) aiming to improve safety for all road users involved. Intersections, especially in urban scenarios, represent the portion of the road where the most relevant accidents take place; therefore, this work proposes an I2V warning system able to detect and track vehicles occupying the intersection and representing an obstacle for other incoming vehicles. This work presents a localization algorithm based on image detection and tracking by a single camera installed on a roadside unit (RSU). The vehicle position in the global reference frame is obtained thanks to a sequence of linear transformations utilizing intrinsic camera parameters, camera height, and pitch angle to obtain the vehicle’s distance from the camera and, thus, its global latitude and longitude. The study brings an experimental analysis of both the localization accuracy, with an average error of 0.62 m, and detection reliability in terms of false positive (1.9%) and missed detection (3.6%) rates.

The recent development in the framework of Intelligent Transportation Systems (ITS) relies on the availability of ultra-fast networks for achieving low-latency communication. In fact, for the actual implementation of the Cooperative-Advanced Driving Assistance System(C-ADAS) based on V2X communication, a limited delay can be tolerated for safety-critical control algorithms such as Automatic Emergency Braking (AEB). This work proposes a detailed evaluation of the latency involved in a roadside detection system based on a commercial thermal camera aimed at communicating with surrounding connected vehicles through Message Queue Telemetry Transport (MQTT) protocol. In particular, the focus is pointed on the proposed communication architecture that has been designed and implemented, as well as on how delay can affect the performance of an AEB control logic implementation, highlighting limitations and possible ways to cope with this issue. Experimental results show that the SG-based communication architecture proposed limits E2E latency below 200 ms, which, on the basis of simulation tests for a large public transportation vehicle, still represents a relevant amount of time for safety-critical ADAS implementation, thus requiring some methodologies for delay compensation.

Teleoperation provides the human operator with sophisticated perceptual and cognitive skills in an over-the-network control loop. It gives hope of addressing some challenges related to vehicular autonomy which is based on artificial intelligence by providing a fallback plan. Variable network time-delay in data transmission is the major problem in teleoperating a vehicle. On 4G network, variability of this delay is significant (70-150 ms ping). Due to this, both video streaming and driving commands encounter variable time-delay. This paper presents an approach to provide the human-operator with a forecasted video stream that replicates future perspective of vehicle's field of view accounting for the delay present in the network. Regarding the image transformation, perspective projection technique is combined with correction given by Smith predictor in the control loop. This image transformation accounts current time-delay and tries to address both issues, time-delays as well as variability. For experiment sake, only frontward field of view is forecasted. Performance is evaluated by performing vehicle teleoperation with real vehicle on street edge-case maneuvers and later comparing the cross-track error with and without perspective projection. Results obtained show improvement in path following tasks.

The recent advancements in Intelligent Transportation Systems (ITS) have revealed significant potential for enhancing traffic management through Advanced Driver Assist Systems (ADASs), with benefits for both safety and environment. This research paper proposes a vehicle localization technique based on Kalman filtering, as accurate positioning of the ego-vehicle is essential for the proper functioning of the Traffic Light Advisor (TLA) system. The aim of the TLA is to calculate the most suitable speed to safely reach and pass the first traffic light in front of the vehicle and subsequently keep that velocity constant to overcome the following traffic light, thus allowing safer and more efficient driving practices, thereby reducing safety risks, and minimizing energy consumption. To overcome Global Positioning Systems (GPS) limitations encountered in urban scenarios, a multi-rate sensor fusion approach based on the Kalman filter with map matching and a simple kinematic one-dimensional model is proposed. The experimental results demonstrate an estimation error below 0.5 m on urban roads with GPS signal loss areas, making it suitable for TLA application. The experimental validation of the Traffic Light Advisor system confirmed the expected benefits with a 40% decrease in energy consumption compared to unassisted driving.

People detection and counting is becoming of great relevance in many application fields which range from the video surveillance of shopping centres to the management of public services such as bus stops. Various computer vision applications exploit Deep Learning technology for people recognition which recently showed great achievements. A very important task along with object/people detection is their tracking which is of fundamental importance especially when counting has to be performed. In this research work, a specific application for people counting at a bus stop is proposed, taking advantage of NVIDIA DeepStream SDK 5.0 detection and tracking algorithms. The final number of people is obtained through a Kalman Filter which aims at avoiding occlusion issues which are typical of people detection-tracking applications. The experimental results show the effectiveness of this approach in three scenarios with different complexity, significantly reducing the counting error with respect to pure detection counting.