Projects

In the pursuit of enhancing communication capabilities and preserving bandwidth in unstructured underground environments, we propose two innovative approaches: exploring the utilization of Free-Space Optics (FSO) and employing RF directional antennas to extend Line of Sight (LOS) communication range. Additionally, to bolster bandwidth, we aim to further investigate protocols facilitating spatial reuse in RF networks through the integration of diverse technologies. Another significant focus lies in developing advanced planning and reactive techniques tailored for dynamic and crowded 2D and 3D scenarios, encompassing multiple agents such as people and vehicles. Our approach involves integrating environment models with Deep Reinforcement Learning to mitigate the challenge of data requirements inherent in learning-based navigation techniques, ensuring efficacy in real-world settings without extensive input examples. Furthermore, we are dedicated to pioneering alternative navigation solutions for underground environments, emphasizing the development of algorithms centered on topological-semantic mapping, localization, and navigation. By prioritizing topological-semantic features over metric ones, such as galleries and intersections, we aim to exploit the inherent structure of subterranean environments, circumventing key challenges like unreliable odometry and sparse geometric features in expansive underground passages.

The overarching objective of this project is to develop a robust robotic system capable of operating effectively in challenging environments like tunnels, mines, and caves, either under semi-autonomous human guidance or autonomously, for tasks such as inspection, intervention, and exploration. Core focuses include refining 3D localization techniques for both geometric and topological mapping, utilizing classical and deep-learning methodologies, alongside exploration of radio frequency time-of-flight ranging for enhanced positional accuracy. Additionally, the project aims to advance planning techniques based on topological-semantic information, adapting classic reactive navigation methods to 3D environments, and enabling coordinated planning and navigation for heterogeneous robot teams. Communication among robots will be facilitated by novel protocols optimized for spatial reuse and simultaneous technology utilization, including exploration of alternative platforms like Ultra Wide Band and LoRa, as well as the deployment of repeaters for extended communication range and robust team connectivity.

The proposal presents a novel conductive thread in the current state of the art: the use of the communication signal at the location, navigation and deployment of robots in such challenging environments. In addition to ensuring the integrity in the robot communication, using the communication signal as an additional sensor integrated with the rest (inertial, range, RGBD), will provide a better localization, navigation and deployment. This will also require the study of the propagation of the communication signal in this type of environment for the development of propagation models and maps of communications.

The objective of this project is to design and develop a new kit to robotize a conventional dumper used in construction, transforming it to an autonomous mobile robot for tunnel construction. It must be capable of reaching the excavation front without human intervention, then wait to be loaded, and finally autonomously transport the debris outside of the tunnel towards the dump. The new robotic kit will be a breakthrough in the technology used to carry out work performances of various kinds. In addition, the kit developed also represents a major technological challenge to maximize the autonomy of the process and its ability to react in a dynamic and minimally structured environment such as a tunnel in construction. These factors besides offering a marketable product, require the development of different subsystems involved to ensure robustness, compactness and economic viability of the system.

The complex nature of mobile robot tasks leads to the necessity of systems with several coordinated robots (agents) working in cooperation. Some international directives refer to robotic elements connected to the communication nets or wireless nets including the robots themselves and the sensors distributed in the working place (static agents) exchanging and sharing information. This concept is extended to robot interactions between humans, the sensors and the environment. We propose this project which is very related with previous MEC projects obtained by this research team, to continue working on subjects related to multi-robot cooperation techniques, computer vision, robot vision for motion and communications.

The project proposes to investigate techniques for a multi-robot team to act in coordination in realistic scenarios. For the deployment, it is necessary to deal with algorithms and methods related to task planning and allocation, coordinated navigation planning, environment perception from multiple views provided by every member of the team, while the communication connectivity among all the elements of the system is maintained – robots, infrastructure, supervisor team, etc. Although some of the techniques involved are usually proposed in the literature and in many projects somehow independently, the research in this project will also be oriented to develop techniques integrating the different subjects involved. Only in this way it will be possible to develop realistic applications using systems with autonomous and supervised behaviours.

The complex nature of mobile robot tasks leads to the necessity of systems with several coordinated robots (agents) working in cooperation. Some international directives refer to robotic elements connected to the communication nets or wireless nets including the robots themselves and the sensors distributed in the working place (static agents) exchanging and sharing information. This concept is extended to robot interactions between humans, the sensors and the environment. We propose this project which is very related with previous MEC projects obtained by this research team, to continue working on subjects related to multi-robot cooperation techniques, computer vision, robot vision for motion and communications.

The URUS project will be focused in designing a network of robots that in a cooperative way interact with human beings and the environment for tasks of assistance, transportation of goods, and surveillance in urban areas. Specifically, our objective is to design and develop a cognitive network robot architecture that integrates cooperating urban robots, intelligent sensors, intelligent devices and communications. Among the specific technology that will be developed in the project, there will be: navigation coordination; cooperative perception; cooperative map building; task negotiation; human robot interaction; and wireless communication strategies between users (mobile phones), the environment (cameras), and the robots. Moreover, in order to make easy the tasks in the urban environment, commercial platforms that have been specifically designed to navigate and assist humans in such urban settings will be given autonomous mobility capabilities. Proof-of concept tests of the systems developed will take place in a car free area of Barcelona. The initiative of this project comes from the European Group inside of the Research Atelier on Network Robot Systems (a European project) which is producing a Roadmap of Network Robots in Europe.