In the autonomous vehicles field, localization is a crucial aspect. While the ORB-SLAM algorithm is a recognized solution for these tasks, it poses challenges due to its computational intensity. Although accelerated implementation exists, a bottleneck persists in the Point Filtering phase which relies on the Distribute Octree algorithm that is not suitable for GPU processing. In this paper, we introduce a novel GPU-suitable algorithm designed to enhance the Point Filtering step, surpassing Distribute Octree. We conducted a comprehensive comparison with state-of-the-art CPU and GPU implementations, considering both computational time and trajectory accuracy. Our experimental results, demonstrate significant speed-ups up to 3x compared to previous contributions.

In recent years, Smart Cities have become a focal point for integrating advanced technologies and intelligent systems to create sustainable urban environments. A key issue in these cities is reducing emissions, and smart traffic lights have emerged as an important tool in addressing this challenge. This work builds on a previously proposed system designed to reduce pollution through smart traffic lights, which was initially limited to three-way intersections and tested on a single traffic signal. We extend the system to manage various types of signalized intersections and evaluate its performance across multiple intersections in a city. Our findings show that smart traffic lights can reduce pollution even without coordination between traffic lights and vehicles.

Smart cities’ infrastructures offer several opportunities to increase cities’ livability. One of these is the chance to improve Emergency Vehicles’ response time. Reducing Emergency Vehicles’ response time can save lives and reduce congestion in traffic flow. On the other hand, the response time can be affected by uncontrolled traffic situations. Smart city’s capabilities can be exploited to manage traffic conditions to reduce response time, but it is not a trivial task. In this work, we analyze the challenges that must be considered in the design of traffic management systems and we show the enabling technologies able to sense traffic status and provide the necessary information to the traffic management system.

Autonomous vehicles are increasingly utilized in safety-critical and time-sensitive settings like urban environments and competitive racing. Planning maneuvers ahead is pivotal in these scenarios, where the onboard compute platform determines the vehicle’s future actions. This paper introduces an optimized implementation of the Frenet Path Planner, a renowned path planning algorithm, accelerated through GPU processing. Unlike existing methods, our approach expedites the entire algorithm, encompassing path generation and collision avoidance. We gauge the execution time of our implementation, showcasing significant enhancements over the CPU baseline (up to 22x of speedup). Furthermore, we assess the influence of different precision types (double, float, half) on trajectory accuracy, probing the balance between completion speed and computational precision. Moreover, we analyzed the impact on the execution time caused by the use of Nvidia Unified Memory and by the interference caused by other processes running on the same system. We also evaluate our implementation using the F1tenth simulator and in a real race scenario. The results position our implementation as a strong candidate for the new state-of-the-art implementation for the Frenet Path Planner algorithm.

Reducing the execution time of ORB-SLAM algorithm is a crucial aspect of autonomous vehicles since it is computationally intensive for embedded boards. We propose a parallel GPU-based implementation, able to run on embedded boards, of the Tracking part of the ORB-SLAM2/3 algorithm. Our implementation is not simply a GPU port of the tracking phase. Instead, we propose a novel method to accelerate image Pyramid construction on GPUs. Comparison against state-of-the-art CPU and GPU implementations, considering both computational time and trajectory errors shows improvement on execution time in well-known datasets, such as KITTI and EuRoC.