Self-driving cars: A survey Badue, Claudine; Guidolini, Rânik; Carneiro, Raphael Vivacqua ...
Expert systems with applications,
03/2021, Volume:
165
Journal Article
Peer reviewed
We survey research on self-driving cars published in the literature focusing on autonomous cars developed since the DARPA challenges, which are equipped with an autonomy system that can be ...categorized as SAE level 3 or higher. The architecture of the autonomy system of self-driving cars is typically organized into the perception system and the decision-making system. The perception system is generally divided into many subsystems responsible for tasks such as self-driving-car localization, static obstacles mapping, moving obstacles detection and tracking, road mapping, traffic signalization detection and recognition, among others. The decision-making system is commonly partitioned as well into many subsystems responsible for tasks such as route planning, path planning, behavior selection, motion planning, and control. In this survey, we present the typical architecture of the autonomy system of self-driving cars. We also review research on relevant methods for perception and decision making. Furthermore, we present a detailed description of the architecture of the autonomy system of the self-driving car developed at the Universidade Federal do Espírito Santo (UFES), named Intelligent Autonomous Robotics Automobile (IARA). Finally, we list prominent self-driving car research platforms developed by academia and technology companies, and reported in the media.
•Recently developments of autonomous driving from academic and industry point of view.•Breakdown of the main aspects comprising autonomous driving and their evolution.•Autonomous driving architecture review and proposal.
•We present a mapping system for large-scale environments with changing features.•We describe in a high level of detail a mapping algorithm for 3D-LiDAR.•G-ICP was used for loop closure displacement ...calculation in GraphSLAM.•Experiments were made with an autonomous vehicle in 3 real world environments.
In this paper, we present an end-to-end framework for precise large-scale mapping with applications in autonomous driving. In special, the problem of mapping complex environments, with features changing from tree-lined streets to urban areas with dense traffic, is studied. The robotic car is equipped with an odometry sensor, a 3D LiDAR Velodyne HDL-32E, a IMU, and a low cost GPS, and the data generated by these sensors are integrated in a pose-based GraphSLAM estimator. A new strategy for identification and correction of odometry data using evolutionary algorithms is presented. This new strategy makes odometry data significantly more consistent with GPS. Loop closures are detected using GPS data, and GICP, a 3D point cloud registration algorithm, is used to estimate the displacement between the different travels over the same region. After path estimation, 3D LiDAR data is used to build an occupancy grid mapping of the environment. A detailed mathematical description of how occupancy evidence can be calculated from the point clouds is given, and a submapping strategy to handle memory limitations is presented as well. The proposed framework is tested in three real world environments with different sizes, and features: a parking lot, a university beltway, and a city neighborhood. In all cases, satisfactory maps were built, with precise loop closures even when the vehicle traveled long distances between them.
In general, proposed solutions for LiDAR-based localization used in autonomous cars require expensive sensors and computationally expensive mapping processes. Moreover, the global localization for ...autonomous driving is converging to the use of maps. Straightforward strategies to reduce the costs are to produce simpler sensors and use maps already available on the Internet. Here, an analysis is presented to show how simple can a LiDAR sensor be without degrading the localization accuracy that uses road and satellite maps together to globally pose the car. Three characteristics of the sensor are evaluated: the number of range readings, the amount of noise in the LiDAR readings, and the frame rate, with the aim of finding the minimum number of LiDAR lines, the maximum acceptable noise and the sensor frame rate needed to obtain an accurate position estimation. The analysis is performed using an autonomous car in complex field scenarios equipped with a 3D LiDAR Velodyne HDL-32E. Several experiments were conducted reducing the number of frames, the number of scans per 3D point-cloud and artificially adding up to 15% of error in the ray length. Among other results, we found that using only 4 vertical lines per scan and with an artificial error added up to 15% of the ray length, the car was capable to localize itself within 2.11 meters error average. All experimental results and the followed methodology are explained in detail herein.
•Localization with occupancy or reflectivity grid maps is more accurate.•Semantic grid maps lead to stable and reasonably accurate localization.•Localization with colour grid maps failed due to ...changes in illumination.•Entropy correlation coefficient is not a good metric for comparing colour maps.•The two-step mapping technique was successfully employed in all experiments.
The localization of self-driving cars is needed for several tasks such as keeping maps updated, tracking objects, and planning. Localization algorithms often take advantage of maps for estimating the car pose. Since maintaining and using several maps is computationally expensive, it is important to analyze which type of map is more adequate for each application. In order to contribute with this analysis, in this work, we compare the accuracy of a particle filter localization when using occupancy, reflectivity, color, or semantic grid maps. To the best of our knowledge, such evaluation is missing in the literature. For building semantic and color grid maps, point clouds from a Light Detection and Ranging (LiDAR) sensor are fused with images captured by a front-facing camera. Semantic information is extracted from images with the deep neural network DeepLabv3+. Experiments are performed in varied environments, under diverse conditions of illumination and traffic. Results show that occupancy grid maps lead to more accurate localization, followed by reflectivity grid maps. In most scenarios, the localization with semantic grid maps kept the position tracking without catastrophic losses, but with errors from 2 to 3 times bigger than the previous. Color grid maps led to inaccurate and unstable localization in most scenarios even using a robust metric, the entropy correlation coefficient, for comparing online data and the map.
Bone age estimation has been used in medicine to verify whether the bone structure development degree of a person corresponds to their chronological age. Such estimate is useful for prognosis about ...the development of children and adolescents, as well as for the diagnosis of endocrinological diseases. This work proposes a fully automated methodology for bone age estimation from carpal radiography images. The methodology comprises two steps, the preprocessing of the image and the classification using a convolutional neural network. The system accuracy for different types of preprocessing is evaluated. We compare the accuracy achieved using the full radiography image as input for the neural network and using only parts of the image corresponding to the Phalangeal region, the Epiphyseal region, and the concatenation of these parts with a crop around the wrist. Digital image processing techniques are employed to segment these regions. Experiments are performed using radiography images from the California University Database. The impact of using different pre‐trained neural networks for transfer learning is evaluated.
We develop Upside-Down Reinforcement Learning (UDRL), a method for learning to act using only supervised learning techniques. Unlike traditional algorithms, UDRL does not use reward prediction or ...search for an optimal policy. Instead, it trains agents to follow commands such as "obtain so much total reward in so much time." Many of its general principles are outlined in a companion report; the goal of this paper is to develop a practical learning algorithm and show that this conceptually simple perspective on agent training can produce a range of rewarding behaviors for multiple episodic environments. Experiments show that on some tasks UDRL's performance can be surprisingly competitive with, and even exceed that of some traditional baseline algorithms developed over decades of research. Based on these results, we suggest that alternative approaches to expected reward maximization have an important role to play in training useful autonomous agents.
A reinforcement learning agent that needs to pursue different goals across episodes requires a goal-conditional policy. In addition to their potential to generalize desirable behavior to unseen ...goals, such policies may also enable higher-level planning based on subgoals. In sparse-reward environments, the capacity to exploit information about the degree to which an arbitrary goal has been achieved while another goal was intended appears crucial to enable sample efficient learning. However, reinforcement learning agents have only recently been endowed with such capacity for hindsight. In this paper, we demonstrate how hindsight can be introduced to policy gradient methods, generalizing this idea to a broad class of successful algorithms. Our experiments on a diverse selection of sparse-reward environments show that hindsight leads to a remarkable increase in sample efficiency.
In this work, we present a novel strategy for correcting imperfections in occupancy grid maps called map decay. The objective of map decay is to correct invalid occupancy probabilities of map cells ...that are unobservable by sensors. The strategy was inspired by an analogy between the memory architecture believed to exist in the human brain and the maps maintained by an autonomous vehicle. It consists in merging sensory information obtained during runtime (online) with a priori data from a high-precision map constructed offline. In map decay, cells observed by sensors are updated using traditional occupancy grid mapping techniques and unobserved cells are adjusted so that their occupancy probabilities tend to the values found in the offline map. This strategy is grounded in the idea that the most precise information available about an unobservable cell is the value found in the high-precision offline map. Map decay was successfully tested and is still in use in the IARA autonomous vehicle from Universidade Federal do Espírito Santo.
The localization of self-driving cars is needed for several tasks such as keeping maps updated, tracking objects, and planning. Localization algorithms often take advantage of maps for estimating the ...car pose. Since maintaining and using several maps is computationally expensive, it is important to analyze which type of map is more adequate for each application. In this work, we provide data for such analysis by comparing the accuracy of a particle filter localization when using occupancy, reflectivity, color, or semantic grid maps. To the best of our knowledge, such evaluation is missing in the literature. For building semantic and colour grid maps, point clouds from a Light Detection and Ranging (LiDAR) sensor are fused with images captured by a front-facing camera. Semantic information is extracted from images with a deep neural network. Experiments are performed in varied environments, under diverse conditions of illumination and traffic. Results show that occupancy grid maps lead to more accurate localization, followed by reflectivity grid maps. In most scenarios, the localization with semantic grid maps kept the position tracking without catastrophic losses, but with errors from 2 to 3 times bigger than the previous. Colour grid maps led to inaccurate and unstable localization even using a robust metric, the entropy correlation coefficient, for comparing online data and the map.