Search

The growing on-board processing capabilities have led to more complex sensor configurations, enabling autonomous car prototypes to expand their operational scope. Nowadays, the joint use of LiDAR data and multiple cameras is almost a standard and poses new challenges for existing multi-modal perception pipelines, such as dealing with contradictory or redundant detections caused by inference on overlapping images. In this paper, we address this last issue in the context of sequential schemes like F-PointNets, where object candidates are obtained in the image space, and the final 3D bounding box is then inferred from point cloud information. To this end, we propose the inclusion of a re-identification branch into the 2D detector, i.e., Faster R-CNN, so that objects seen from adjacent cameras can be handled before the 3D box estimation takes place, removing duplicates and completing the object's cloud. Extensive experimental evaluations covering both the 2D and 3D domains affirm the effectiveness of the suggested methodology. The findings indicate that our approach outperforms conventional Non-Maximum Suppression (NMS) methods. Particularly, we observed a significant gain of over 5% in terms of accuracy for cars in camera overlap regions. These results highlight the potential of our upgraded detection and re-identification system in practical scenarios for autonomous driving. [ABSTRACT FROM AUTHOR]

Connected autonomous electric vehicles (CAEVs) are essential actors in the decarbonization process of the transport sector and a key aspect of home energy management systems (HEMSs) along with PV units, CAEVs and battery energy storage systems. However, there are associated uncertainties which present new challenges to HEMSs, such as aleatory EV arrival and departure times, unknown EV battery states of charge at the connection time, and stochastic PV production due to weather and passing cloud conditions. The proposed HEMS is based on proximal policy optimization (PPO), which is a deep reinforcement learning algorithm suitable for continuous complex environments. The optimal solution for HEMS is a tradeoff between CAEV driver's range anxiety, batteries degradation, and energy consumption, which is solved by means of incentives/penalties in the reinforcement learning formulation. The proposed PPO algorithm was compared to conventional methods such as business-as-usual (BAU) and value iteration (VI) solutions based on dynamic programming. Simulation results indicate that the proposed PPO's performance showed a daily energy cost reduction of 54% and 27% compared to BAU and VI, respectively. Finally, the developed PPO algorithm is suitable for real-time operations due to its fast execution and good convergence to the optimal solution. [ABSTRACT FROM AUTHOR]

Advances in the field of unmanned aerial vehicles (UAVs) have led to an exponential increase in their market, thanks to the development of innovative technological solutions aimed at a wide range of applications and services, such as emergencies and those related to fires. In addition, the expansion of this market has been accompanied by the birth and growth of the so-called UAV swarms. Currently, the expansion of these systems is due to their properties in terms of robustness, versatility, and efficiency. Along with these properties there is an aspect, which is still a field of study, such as autonomous and cooperative navigation of these swarms. In this paper we present an architecture that includes a set of complementary methods that allow the establishment of different control layers to enable the autonomous and cooperative navigation of a swarm of UAVs. Among the different layers, there are a global trajectory planner based on sampling, algorithms for obstacle detection and avoidance, and methods for autonomous decision making based on deep reinforcement learning. The paper shows satisfactory results for a line-of-sight based algorithm for global path planner trajectory smoothing in 2D and 3D. In addition, a novel method for autonomous navigation of UAVs based on deep reinforcement learning is shown, which has been tested in 2 different simulation environments with promising results about the use of these techniques to achieve autonomous navigation of UAVs. [ABSTRACT FROM AUTHOR]

One of the most challenging problems in the domain of autonomous aerial vehicles is the designing of a robust real-time obstacle detection and avoidance system. This problem is complex, especially for the micro and small aerial vehicles, that is due to the Size, Weight and Power (SWaP) constraints. Therefore, using lightweight sensors (i.e., Digital camera) can be the best choice comparing with other sensors; such as laser or radar.For real-time applications, different works are based on stereo cameras in order to obtain a 3D model of the obstacles, or to estimate their depth. Instead, in this paper, a method that mimics the human behavior of detecting the collision state of the approaching obstacles using monocular camera is proposed. The key of the proposed algorithm is to analyze the size changes of the detected feature points, combined with the expansion ratios of the convex hull constructed around the detected feature points from consecutive frames. During the Aerial Vehicle (UAV) motion, the detection algorithm estimates the changes in the size of the area of the approaching obstacles. First, the method detects the feature points of the obstacles, then extracts the obstacles that have the probability of getting close toward the UAV. Secondly, by comparing the area ratio of the obstacle and the position of the UAV, the method decides if the detected obstacle may cause a collision. Finally, by estimating the obstacle 2D position in the image and combining with the tracked waypoints, the UAV performs the avoidance maneuver. The proposed algorithm was evaluated by performing real indoor and outdoor flights, and the obtained results show the accuracy of the proposed algorithm compared with other related works. [ABSTRACT FROM AUTHOR]

Nowadays, intelligent systems applied to vehicles have grown very rapidly; their goal is not only the improvement of safety, but also making autonomous driving possible. Many of these intelligent systems are based on making use of computer vision in order to know the environment and act accordingly. It is of great importance to be able to estimate the pose of the vision system because the measurement matching between the perception system (pixels) and the vehicle environment (meters) depends on the relative position between the perception system and the environment. A new method of camera pose estimation for stereo systems is presented in this paper, whose main contribution regarding the state of the art on the subject is the estimation of the pitch angle without being affected by the roll angle. The validation of the self-calibration method is accomplished by comparing it with relevant methods of camera pose estimation, where a synthetic sequence is used in order to measure the continuous error with a ground truth. This validation is enriched by the experimental results of the method in real traffic environments. [ABSTRACT FROM AUTHOR]

A driver behaviour analysis tool is presented. The proposal offers a novel contribution based on low-cost hardware and advanced software capabilities based on data fusion. The device takes advantage of the information provided by the in-vehicle sensors using Controller Area Network Bus (CAN-BUS), an Inertial Measurement Unit (IMU) and a GPS. By fusing this information, the system can infer the behaviour of the driver, providing aggressive behaviour detection. By means of accurate GPS-based localization, the system is able to add context information, such as digital map information, speed limits, etc. Several parameters and signals are taken into account, both in the temporal and frequency domains, to provide real time behaviour detection. The system was tested in urban, interurban and highways scenarios. [ABSTRACT FROM AUTHOR]

Among Advanced Driver Assistance Systems (ADAS) pedestrian detection is a common issue due to the vulnerability of pedestrians in the event of accidents. In the present work, a novel approach for pedestrian detection based on data fusion is presented. Data fusion helps to overcome the limitations inherent to each detection system (computer vision and laser scanner) and provides accurate and trustable tracking of any pedestrian movement. The application is complemented by an efficient communication protocol, able to alert vehicles in the surroundings by a fast and reliable communication. The combination of a powerful location, based on a GPS with inertial measurement, and accurate obstacle localization based on data fusion has allowed locating the detected pedestrians with high accuracy. Tests proved the viability of the detection system and the efficiency of the communication, even at long distances. By the use of the alert communication, dangerous situations such as occlusions or misdetections can be avoided. [ABSTRACT FROM AUTHOR]

Traffic accidents are still one of the main health problems in the World. A number of measures have been applied in order to reduce the number of injuries and fatalities in roads, i.e., implementation of Advanced Driver Assistance Systems (ADAS) based on image processing. In this paper, a real time speed supervisor based on road sign recognition that can work both in urban and non-urban environments is presented. The system is able to recognize 135 road signs, belonging to the danger, yield, prohibition obligation and indication types, and sends warning messages to the driver upon the combination of two pieces of information: the current speed of the car and the road sign symbol. The core of this paper is the comparison between the two main methods which have been traditionally used for detection and recognition of road signs: template matching (TM) and neural networks (NN). The advantages and disadvantages of the two approaches will be shown and commented. Additionally we will show how the use of well-known algorithms to avoid illumination issues reduces the amount of images needed to train a neural network. [ABSTRACT FROM AUTHOR]

The lack of trustworthy sensors makes development of Advanced Driver Assistance System (ADAS) applications a tough task. It is necessary to develop intelligent systems by combining reliable sensors and real-time algorithms to send the proper, accurate messages to the drivers. In this article, an application to detect and predict the movement of pedestrians in order to prevent an imminent collision has been developed and tested under real conditions. The proposed application, first, accurately measures the position of obstacles using a two-sensor hybrid fusion approach: a stereo camera vision system and a laser scanner. Second, it correctly identifies pedestrians using intelligent algorithms based on polylines and pattern recognition related to leg positions (laser subsystem) and dense disparity maps and u-v disparity (vision subsystem). Third, it uses statistical validation gates and confidence regions to track the pedestrian within the detection zones of the sensors and predict their position in the upcoming frames. The intelligent sensor application has been experimentally tested with success while tracking pedestrians that cross and move in zigzag fashion in front of a vehicle. [ABSTRACT FROM AUTHOR]

There are increasing applications that require precise calibration of cameras to perform accurate measurements on objects located within images, and an automatic algorithm would reduce this time consuming calibration procedure. The method proposed in this article uses a pattern similar to that of a chess board, which is found automatically in each image, when no information regarding the number of rows or columns is supplied to aid its detection. This is carried out by means of a combined analysis of two Hough transforms, image corners and invariant properties of the perspective transformation. Comparative analysis with more commonly used algorithms demonstrate the viability of the algorithm proposed, as a valuable tool for camera calibration. [ABSTRACT FROM AUTHOR]

Human–machine interaction is an active area of research due to the rapid development of autonomous systems and the need for communication. This review provides further insight into the specific issue of the information flow between pedestrians and automated vehicles by evaluating recent advances in external human–machine interfaces (eHMI), which enable the transmission of state and intent information from the vehicle to the rest of the traffic participants. Recent developments will be explored and studies analyzing their effectiveness based on pedestrian feedback data will be presented and contextualized. As a result, we aim to draw a broad perspective on the current status and recent techniques for eHMI and some guidelines that will encourage future research and development of these systems. [ABSTRACT FROM AUTHOR]

The advances in autonomous technologies and microelectronics have increased the use of Autonomous Unmanned Aerial Vehicles (UAVs) in more critical applications, such as forest fire monitoring and fighting. In addition, implementing surveillance methods that provide rich information about the fires is considered a great tool for Emergency Response Teams (ERT). From this aspect and in collaboration with Telefónica Digital España, Dronitec S.L, and Divisek Systems, this paper presents a fire monitoring system based on perception algorithms, implemented on a UAV, to perform surveillance tasks allowing the monitoring of a specific area, in which several algorithms have been implemented to perform the tasks of autonomous take-off/landing, trajectory planning, and fire monitoring. This UAV is equipped with RGB and thermal cameras, temperature sensors, and communication modules in order to provide full information about the fire and the UAV itself, sending these data to the ground station in real time. The presented work is validated by performing several flights in a real environment, and the obtained results show the efficiency and the robustness of the proposed system, against different weather conditions. [ABSTRACT FROM AUTHOR]

The development in Multi-Robot Systems (MRS) has become one of the most exploited fields of research in robotics in recent years. This is due to the robustness and versatility they present to effectively undertake a set of tasks autonomously. One of the essential elements for several vehicles, in this case, Unmanned Aerial Vehicles (UAVs), to perform tasks autonomously and cooperatively is trajectory planning, which is necessary to guarantee the safe and collision-free movement of the different vehicles. This document includes the planning of multiple trajectories for a swarm of UAVs based on 3D Probabilistic Roadmaps (PRM). This swarm is capable of reaching different locations of interest in different cases (labeled and unlabeled), supporting of an Emergency Response Team (ERT) in emergencies in urban environments. In addition, an architecture based on Robot Operating System (ROS) is presented to allow the simulation and integration of the methods developed in a UAV swarm. This architecture allows the communications with the MavLink protocol and control via the Pixhawk autopilot, for a quick and easy implementation in real UAVs. The proposed method was validated by experiments simulating building emergences. Finally, the obtained results show that methods based on probability roadmaps create effective solutions in terms of calculation time in the case of scalable systems in different situations along with their integration into a versatile framework such as ROS. [ABSTRACT FROM AUTHOR]

The automation of the Wilderness Search and Rescue (WiSAR) task aims for high levels of understanding of various scenery. In addition, working in unfriendly and complex environments may cause a time delay in the operation and consequently put human lives at stake. In order to address this problem, Unmanned Aerial Vehicles (UAVs), which provide potential support to the conventional methods, are used. These vehicles are provided with reliable human detection and tracking algorithms; in order to be able to find and track the bodies of the victims in complex environments, and a robust control system to maintain safe distances from the detected bodies. In this paper, a human detection based on the color and depth data captured from onboard sensors is proposed. Moreover, the proposal of computing data association from the skeleton pose and a visual appearance measurement allows the tracking of multiple people with invariance to the scale, translation and rotation of the point of view with respect to the target objects. The system has been validated with real and simulation experiments, and the obtained results show the ability to track multiple individuals even after long-term disappearances. Furthermore, the simulations present the robustness of the implemented reactive control system as a promising tool for assisting the pilot to perform approaching maneuvers in a safe and smooth manner. [ABSTRACT FROM AUTHOR]

The deployment of Intelligent Vehicles in urban environments requires reliable estimation of positioning for urban navigation. The inherent complexity of this kind of environments fosters the development of novel systems which should provide reliable and precise solutions to the vehicle. This article details an advanced GNSS/IMU fusion system based on a context-aided Unscented Kalman filter for navigation in urban conditions. The constrained non-linear filter is here conditioned by a contextual knowledge module which reasons about sensor quality and driving context in order to adapt it to the situation, while at the same time it carries out a continuous estimation and correction of INS drift errors. An exhaustive analysis has been carried out with available data in order to characterize the behavior of available sensors and take it into account in the developed solution. The performance is then analyzed with an extensive dataset containing representative situations. The proposed solution suits the use of fusion algorithms for deploying Intelligent Transport Systems in urban environments.