Ricardo Roriz

Light Detection and Ranging (LiDAR) sensors play a critical role in enabling precise and reliable environmental perception for autonomous vehicles. However, handling the large amounts of data they generate presents a significant challenge. With the emergence of standards such as the G-PCC standard, octrees have been used as a key data structure for compressing 3D LiDAR data. Despite their advantages, octrees often lead to high memory utilization and computational overhead, particularly when dealing with high-resolution datasets, limiting their utilization in systems with real-time requirements. This letter presents FOG-zip, a hardwareaccelerated octree compression approach designed for embedded systems with limited resources. Experimental results demonstrate that FOG-zip achieves up to a 27.8% reduction in data size compared to the same uncompressed octree bitstream, while processing each frame within the frame rate limits of the sensor used.

The automotive industry is rapidly moving towards the deployment of fully autonomous vehicles, which rely on advanced driver-assistance systems (ADAS) and robust perception systems for safe and efficient navigation. Among these technologies, Light Detection and Ranging (LiDAR) sensors have gained prominence for their ability to provide high-resolution 3D representations of the vehicle's surroundings in real-time. This capability significantly improves obstacle detection and object recognition. However, the integration of LiDAR sensors with ADAS may still face several challenges, such as image noise and data output size, slowing their widespread adoption. This article introduces the Advanced LiDAR Framework for Automotive (ALFA), a tool designed for the development and evaluation of LiDAR data processing algorithms in different setups, with a focus on embedded platforms with acceleration capabilities. ALFA enables seamless interfacing with a wide range of devices and the creation and deployment of hardware accelerators for processing point cloud data across diverse applications, facilitating the integration with the computing system of the car. In addition to presenting the framework, this article provides a comprehensive evaluation and benchmarking of ALFA, including point cloud filtering and real-time ground segmentation.

As the need for realistic and immersive 3-D representations of the environment continues to increase across various industries, finding efficient ways to represent data has become paramount. A well-known approach to partitioning 3-D space into a structured data format is the use of octrees, primarily due to their efficiency in handling both sparse and dense 3-D data. This method is particularly useful in applications involving automotive light detection and ranging (LiDAR) sensors, which are widely used in autonomous driving systems for their ability to capture detailed spatial information in real-time. This letter introduces the fast octree generator (FOG), a novel approach for generating octrees from 3-D LiDAR point clouds that leverages hardware acceleration. FOG achieves a performance improvement of up to 88.8% compared to PCL's octree implementation, enabling real-time octree generation for high-end sensors on embedded platforms.

In the evolving landscape of autonomous driving technology, Light Detection and Ranging (LiDAR) sensors have emerged as a pivotal instrument for enhancing environmental perception. They can offer precise, high-resolution, real-time 3D representations around a vehicle, and the ability for long-range measurements under low-light conditions. However, these advantages come at the cost of the large volume of data generated by the sensor, leading to several challenges in transmission, processing, and storage operations, which can be currently mitigated by employing data compression techniques to the point cloud. This article presents a survey of existing methods used to compress point cloud data for automotive LiDAR sensors. It presents a comprehensive taxonomy that categorizes these approaches into four main groups, comparing and discussing them across several important metrics.

In the near future, autonomous vehicles with full self-driving features will populate our public roads. However, fully autonomous cars will require robust perception systems to safely navigate the environment, which includes cameras, RADAR devices, and Light Detection and Ranging (LiDAR) sensors. LiDAR is currently a key sensor for the future of autonomous driving since it can read the vehicle’s vicinity and provide a real-time 3D visualization of the surroundings through a point cloud representation. These features can assist the autonomous vehicle in several tasks, such as object identification and obstacle avoidance, accurate speed and distance measurements, road navigation, and more. However, it is crucial to detect the ground plane and road limits to safely navigate the environment, which requires extracting information from the point cloud to accurately detect common road boundaries. This article presents a survey of existing methods used to detect and extract ground points from LiDAR point clouds. It summarizes the already extensive literature and proposes a comprehensive taxonomy to help understand the current ground segmentation methods that can be used in automotive LiDAR sensors.

The world is facing a great technological transformation towards fully autonomous vehicles, where optimists predict that by 2030 autonomous vehicles will be sufficiently reliable, affordable, and common to displace most human driving. To cope with these trends, reliable perception systems must enable vehicles to hear and see all their surroundings, with light detection and ranging (LiDAR) sensors being a key instrument for recreating a 3D visualization of the world in real time. However, perception systems must rely on accurate measurements of the environment. Thus, these intelligent sensors must be calibrated and benchmarked before being placed on the market or assembled in a car. This article presents an Evaluation and Testing Platform for Automotive LiDAR sensors, with the main goal of testing both commercially available sensors and new sensor prototypes currently under development in Bosch Car Multimedia Portugal. The testing system can benchmark any LiDAR sensor under different conditions, recreating the expected driving environment in which such devices normally operate. To characterize and validate the sensor under test, the platform evaluates several parameters, such as the field of view (FoV), angular resolution, sensor’s range, etc., based only on the point cloud output. This project is the result of a partnership between the University of Minho and Bosch Car Multimedia Portugal.

The automotive industry is facing an unprecedented technological transformation towards fully autonomous vehicles. Optimists predict that, by 2030, cars will be sufficiently reliable, affordable, and common to displace most current human driving tasks. To cope with these trends, autonomous vehicles require reliable perception systems to hear and see all the surroundings, being light detection and ranging (LiDAR) sensors a key instrument for recreating a 3D visualization of the world. However, for a reliable operation, such systems require LiDAR sensors to provide high-resolution 3D representations of the car's vicinity, which results in millions of data points to be processed in real-time. With this article we propose the ALFA-Pi, a data packet decoder and reconstruction system fully deployed on an embedded reconfigurable hardware platform. By resorting to field-programmable gate array (FPGA) technology, ALFA-Pi is able to interface different LiDAR sensors at the same time, while providing custom representation outputs to high-level perception systems. By accelerating the LiDAR interface, the proposed system outperforms current software-only approaches, achieving lower latency in the data acquisition and data decoding tasks while reaching high performance ratios.

Nowadays, and more than a decade after the first steps towards autonomous driving, we keep heading to achieve fully autonomous vehicles on our roads, with LiDAR sensors being a key instrument for the success of this technology. Such advances trigger the emergence of new players in the automotive industry, and along with car manufacturers, this sector represents a multibillion-dollar market where everyone wants to take a share. To understand recent advances and technologies behind LiDAR, this article presents a survey on LiDAR sensors for the automotive industry. With this work, we show the measurement principles and imaging techniques currently being used, going through a review of commercial systems and development solutions available in the market today. Furthermore, we highlight the current and future challenges, providing insights on how both research and industry can step towards better LiDAR solutions.

This paper intends to present a different approach to solve the Self-Localization problem regarding a RoboCup's Middle Size League game, developed by MINHO team researchers. The method uses white field markings as key points, to compute the position with least error, creating an error-based graphic where the minimum corresponds to the real position, that are computed by comparing the key (line) points with a precomputed set of values for each position. This approach allows a very fast local and global localization calculation, allowing the global localization to be used more often, while driving the estimate to its real value. Differently from the majority of other teams in this league, it was important to come up with a new and improved method to solve the traditional slow Self-Localization problem.