Showing papers by "David Martin published in 2020"

3D Trajectory Planning Method for UAVs Swarm in Building Emergencies.

Abstract: 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.

Emergency Support Unmanned Aerial Vehicle for Forest Fire Surveillance

Abstract: 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 Telefonica Digital Espana, 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.

Learning Probabilistic Awareness Models for Detecting Abnormalities in Vehicle Motions

Abstract: This paper proposes a method to detect abnormal motions in real vehicle situations based on trajectory data. Our approach uses a Gaussian process (GP) regression that facilitates to approximate expected vehicle’s movements over a whole environment based on sparse observed data. The main contribution of this paper consists in decomposing the GP regression into spatial zones, where quasi-constant velocity models are valid. Such obtained models are employed to build a set of Kalman filters that encode observed vehicle’s dynamics. This paper shows how proposed filters enable the online identification of abnormal motions. Detected abnormalities can be modeled and learned incrementally, automatically by intelligent systems. The proposed methodology is tested on real data produced by a vehicle that interacts with pedestrians in a closed environment. Automatic detection of abnormal motions benefits the traffic scene understanding and facilitates to close the gap between human driving and autonomous vehicle awareness.

Vehículo aéreo no tripulado para vigilancia y monitorización de incendios.

Abstract: Forest fires continue to be one of the major environmental problems facing society today. In addition to the high environmental impact, the destruction of ecosystems and possible human losses, the economic costs of fire-fighting must be added. All these reasons have led to the search, in current technology, for tools and systems to help in fire-fighting tasks and, more specifically, the use of Unmanned Aerial Vehicles (UAVs). The fact that UAVs can reach remote locations quickly and embark on sensors and devices to assist in dangerous and risky tasks makes them ideal for firefighting. This work includes the development, in collaboration with Telefonica Digital Espana, of an effective tool using current technology present in robotics, in which a drone is capable of carrying out fire surveillance and monitoring tasks autonomously, thanks to the sensors and devices on board. In addition, a graphical interface is implemented that allows the exchange of information between the aircraft and the ground user.

Obstacle Avoidance Manager for UAVs Swarm

Abstract: Multi-Robot Systems for a swarm of autonomous UAVs are critical in providing essential solutions to numerous applications. However, working in complex environments requires higher levels of safety in navigation. One of the problems is the detection and avoidance of static and dynamic obstacles that appear in the UAVs paths.In this paper, two complementary methods are presented; to provide safe autonomous navigation of a swarm of UAVs. On the one hand, a method based on the Velocity Obstacle (VO) is responsible for avoiding collisions between the UAVs of the swarm by decreasing the velocity of the UAVs when they approach the same location. This method has the advantage of reducing the use of UAV resources and computational time. On the other hand, a method based on Light Detection and Ranging (LiDAR) information and Probabilistic Roadmaps (PRM) allows detecting dynamic obstacles appear in the path, exploring the environment in search of alternative paths, and finally establishing the one that minimizes the distance, and allows reaching a location avoiding the detected obstacles. The proposed methods have been tested and validated in simulation environments; as a previous step to their implementation in real UAVs. Moreover, the obtained results show the robustness and the efficiency of the system in detecting and avoiding the possible collisions.

A Research Platform for Autonomous Vehicles Technologies Research in the Insurance Sector

Abstract: This work presents a novel platform for autonomous vehicle technologies research for the insurance sector. The platform has been collaboratively developed by the insurance company MAPFRE-CESVIMAP, Universidad Carlos III de Madrid and INSIA of the Universidad Politecnica de Madrid. The high-level architecture and several autonomous vehicle technologies developed using the framework of this collaboration are introduced and described in this work. Computer vision technologies for environment perception, V2X communication capabilities, enhanced localization, human–machine interaction and self awareness are among the technologies which have been developed and tested. Some use cases that validate the technologies presented in the platform are also presented; these use cases include public demonstrations, tests of the technologies and international competitions for self-driving technologies.

Wilderness Search and Rescue with Heterogeneous Multi-Robot Systems*

Abstract: Recent developments in autonomous and communication technologies led the use of cooperative aerial and ground vehicles in Wilderness Search and Rescue missions (WiSAR). The use of a heterogeneous Multi-Robot System (MRS) improves the robustness and efficiency in achieving these tasks, comparing to the homogeneous systems with vehicles of the same characteristics. From this point, this paper proposed a Multi-Robot Task Allocation (MRTA) algorithm for heterogeneous vehicles (UAVs and UGVs) using the Market-based Approach to optimize the mission resources. The algorithm checks the availability of the vehicles, the characteristics of each task, and the payload required as inputs, then it provides each vehicle with a plan of tasks and charging commands. The proposed algorithm has been validated by performing several missions in simulations of mountains terrain with real dimensions, and the obtained results show the robustness and efficiency of the proposed system.

Mono-LSDE: Lightweight Semantic-CNN for Depth Estimation from Monocular Aerial Images*

Abstract: In the last decade, with the advances in autonomous technologies, Unmanned Aerial Vehicles (UAVs) have been encountered a significant focus on several applications. With the complexity of the tasks performed by the UAVs, this addresses the necessity to obtain information about the surrounding environment. Estimating depth maps from monocular images is considered a key role when working small or micro UAVs, this is due to the Size, Weight, and Power (SWaP) constraints on these vehicles. Therefore, this paper proposed a lightweight Semantic Neural Network based on Encoder-Decoder architecture; to obtain a depth map from a monocular camera.The proposed method has been tested in several scenarios of complex environments, and the obtained results show its robustness and efficiency against different weather and light conditions, illustrating the functionality of the proposed method in real-time applications.

Unsupervised Anomaly Detection Using Intelligent and Heterogeneous Autonomous Systems: Highlights From the 2020 IEEE Signal Processing Cup Student Competition [SP Competitions]

Abstract: Presents highlights from the Highlights from the 2020 IEEE Signal Processing Cup student competition.