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 Espirito 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.

Self-driving cars: A survey

A survey of robotic motion planning in dynamic environments

Currently, the use of virtual reality (VR) is being widely applied in different fields, especially in computer science, engineering, and medicine Concretely, the engineering applications based on VR cover approximately one half of the total number of VR resources (considering the research works published up to last year, 2016) In this paper, the capabilities of different computational software for designing VR applications in engineering education are discussed As a result, a general flowchart is proposed as a guide for designing VR resources in any application It is worth highlighting that, rather than this study being based on the applications used in the engineering field, the obtained results can be easily extrapolated to other knowledge areas without any loss of generality This way, this paper can serve as a guide for creating a VR application

On the Design of Virtual Reality Learning Environments in Engineering

The smart city embraces gradual adoption of autonomous vehicles (AVs) into the intelligent transportation system. Contributed by their full-fledged controllability, AVs can respond to instantaneous situations with high efficiency and flexibility. In this paper, we propose a novel AV logistic system (AVLS) to accommodate logistic demands for smart cities. We focus on determining the optimal routes for the governed AVs in consideration of various requirements imposed by the vehicles, logistic requests, renewable generations, and the underlying transportation system. By coordinating their routes and charging schedules, the system can effectively utilize the renewable energy generated by distributed generations. We formulate the joint routing and charging problem in the form of quadratic-constrained mixed integer linear program. To improve its scalability, we develop a distributed solution method via dual decomposition. We conduct extensive simulations to evaluate the performance of proposed system and solution methods. The results show that AVLS can effectively utilize excessive renewable energy while accomplishing all logistic requests. The distributed solution can develop near-optimal solutions with compelling improvement in computational speed.

Autonomous Vehicle Logistic System: Joint Routing and Charging Strategy

Obstacle detection is an essential element for the development of intelligent transportation systems so that accidents can be avoided. In this paper, we propose a stereovision-based method for detecting obstacles in urban environment. The proposed method uses a deep stacked auto-encoders (DSA) model that combines the greedy learning features with the dimensionality reduction capacity and employs an unsupervised $k$ -nearest neighbors (KNN) algorithm to accurately and reliably detect the presence of obstacles. We consider obstacle detection as an anomaly detection problem. We evaluated the proposed method by using practical data from three publicly available data sets, the Malaga stereovision urban data set, the Daimler urban segmentation data set, and the Bahnhof data set. Also, we compared the efficiency of DSA-KNN approach to the deep belief network-based clustering schemes. Results show that the DSA-KNN is suitable to visually monitor urban scenes.

/pdf/obstacle-detection-for-intelligent-transportation-systems-2xjzdlx2dd.pdf

Obstacle Detection for Intelligent Transportation Systems Using Deep Stacked Autoencoder and $k$ -Nearest Neighbor Scheme

An accurate method to detect obstacles and dangerous areas is the key to the safe performance of autonomous robots. Time of flight sensors can report their existence through the emission, reflection, and measurement of wave patterns, but large wavelength light projection is often unreliable in outdoors environments, due to solar radiation contamination. In this paper, a specific Microsoft Kinect arrangement on a robotic vehicle is proposed, such that outdoors detection is possible. The main contribution of this paper is the description of a sequence of filtering techniques, which translate the depth image provided by the sensor into definite obstacle projections in the navigability map used by the vehicle. A series of experiments proves that the Kinect device is more accurate at detecting obstacles using this procedure than a camera pair using two different stereovision techniques.

Using Kinect on an Autonomous Vehicle for Outdoors Obstacle Detection

In this paper, a method to combine a low-cost 16 beam solid state laser sensor and a conventional video camera for obstacle detection is presented. The system is intended to form a non-intrusive virtual barrier at both sides of an intelligent wheelchair, in order to protect the user in everyday outdoor and indoor environments, like office, home, or pedestrian areas. In this type of environments, the shape of the obstacles is very heterogeneous (for instance, having a variable width along their height), so their detection via the conventional sensors installed in the wheelchair presents difficulties, especially in the most exposed areas of the user that are the sides of their torso. With the proposed system, when an obstacle intersects a beam, the intersection point is projected in the associated image and optical flow is calculated at both sides of this point. Using the optical flow, several classifiers have been trained and tested in order to automatically discern between intersections produced by the user and those produced by external obstacles. Results show that the method accurately detects the presence of obstacles and the direction of their movement.

Laser and Optical Flow Fusion for a Non-Intrusive Obstacle Detection System on an Intelligent Wheelchair

The combined action of several sensing systems, so that they are able to compensate the technical flaws of each other, is common in robotics. Monte Carlo Localization (MCL) is a popular technique used to estimate the pose of a mobile robot, which allows the fusion of heterogeneous sensor data. Several sensor fusion schemes have been proposed which include sensors like GPS to improve the performance of this algorithm. In this paper, an Adaptive MCL algorithm is used to combine data from wheel odometry, an inertial measurement unit, a global positioning system and laser scanning. A particle weighting model which integrates GPS measurements is proposed, and its performance is compared with a particle generation approach. Experiments were conducted on a real robotic car within an urban environment.

MCL with sensor fusion based on a weighting mechanism versus a particle generation approach

This paper introduces a local planner which computes a set of commands, allowing an autonomous vehicle to follow a given trajectory. To do so, the platform relies on a localization system, a map and a cost map which represents the obstacles in the environment. The presented method computes a set of tentative trajectories, using a schema based on a Fren?t frame obtained from the global planner. These trajectories are then scored using a linear combination of weighted cost functions. In the presented approach, new weights are introduced in order to satisfy the specificities of our autonomous platform, Verdino. A study on the influence of the defined weights in the final behavior of the vehicle is introduced. From these tests, several configurations have been chosen and ranked according to two different proposed behaviors. The method has been tested both in simulation and in real conditions.

Safe and Reliable Path Planning for the Autonomous Vehicle Verdino

In this paper, some computer applications for teaching forward and inverse kinematics in Robotics are presented. These applications, developed in Unity3D and Python, allow both teachers and students to create and manipulate 3D interactive representations of the studied robotic models. The use of these tools has been proved to help students improve their understanding of the geometric transformations and mathematical operations required to solve both forward and inverse kinematics exercises. © 2017 Wiley Periodicals, Inc. Comput Appl Eng Educ 25:420–429, 2017; View this article online at wileyonlinelibrary.com/journal/cae; DOI 10.1002/cae.21809

Javier Hernández-Aceituno

Papers

Using Kinect on an Autonomous Vehicle for Outdoors Obstacle Detection

Laser and Optical Flow Fusion for a Non-Intrusive Obstacle Detection System on an Intelligent Wheelchair

MCL with sensor fusion based on a weighting mechanism versus a particle generation approach

Safe and Reliable Path Planning for the Autonomous Vehicle Verdino

Teaching kinematics with interactive schematics and 3D models