(Foto)

(Foto Haru 1)

SIAR-ECHORD++

Research

Research Highlights

We research on different lines related to perception, decision making and adaption in robotic systems, including multi-robot systems. Here we highlight some of them:

	Robot Localization, Mapping and SLAM It is essential for an autonomous robot to acquire knowledge about its position in order to be able to fulfill its commanded tasks. To this end, our group has a remarkable background on developing algorithms for robot localization when there exists prior knowledge of the topology of the environment as done here and here. In cases in which this knowledge is not available or not given to the robot, Simultaneous Localization And Mapping(SLAM) algorithms should be employed, as done in our works Vision-Based Odometry and SLAM and Range Only SLAM.
	Robot Autonomous Navigation We have a long experience on robot autonomous navigation techniques and systems, for both ground and aerial robots, with an special focus on real-life deployments. We have deployed robots for autonomous transportation of persons in pedestrian areas, autonomous inspection of sewers, guiding of persons in cultural heritage sites and touristic places,
	Robot Decision Making under Uncertainties Robots have to face uncertainties when performing their tasks. Uncertainties arise due to sensor noise, occlusions, inaccurate models, failures, etc. We work in the use of Partially Observable Markov Decision Processes (POMDPs) as principled tools for planning under uncertainties in robotics. We have developed techniques based on POMDPs for single and multi-robot systems.
	Exploration and Active Sensing One of the definitions of exploration is “the act of searching for the purpose of discovery of information or resources”. We have developed different algorithms for efficient mapping of unknown environments. For instance, myopic strategies for range-only mapping can be found here . Also, we have developed novel non-myopic informative path planning and multi-robot planning strategies for exploration using Gaussian Processes as models.
	Multi-Robot Systems In applications such as mapping, surveillance and search and rescue, to name a few, the use of a system with multiple robots can be of great interest. For this reason, we have designed algorithms to coordinate heterogeneous teams of robots in several publications including here and here. Also, the works here and here discuss about some of the advantages when using such multi-robot systems.
	Social Robotics We also research on robot navigation systems that consider persons in a proper way, taking into account not only safety constraints, but also social rules, in what is called human-aware navigation. For that, we have developed novel algorithms that learn these social constraints and costs from data, and can be incorporated into motion planners like RRT* (see below) We have also develop methods to consider people intentions when performing joint navigation tasks. We have developed such systems in real setups considering social settings, like here and here.
	Machine Learning for Robotics Some robotics tasks are easier to demonstrate than to program. Thus, we have worked on methods for robot programing by demonstration applied to robot navigation using Inverse Reinforcement Learning with RRT planners (here, and the code here). We are also applying Deep Networks for robot vision tasks, like vision-based velocity estimation for UAVs or identification of sewer elements for robot localization.

Application Areas

We have applied the previous techniques and developed robotic and vision systems in different applications areas. We show here some examples:

Service Robotics for Personal/Domestic Use

Social Robots devoted to edutainment
Assisted living robots

Service Robotics for Professional Use

Inspection applications
Environmental monitoring
Autonomous navigation and transportation in pedestrian areas

Datasets & Code

Code

The code can be accessed at our GitHub page: https://github.com/robotics-upo

Datasets

FROG dataset in Alcazar of Seville, Spain

A novel set of data for the evaluation of visual place recognition in both indoors and outdoors environment in addition to sensor information to evaluate human-robot interactions in crowded areas. The datasets were recorded in the Royal Alcázar of Seville (Spain) in the frame of the EU Project FROG. We recorded a large set of images sequences from a stereo camera and scan measurements from three laser mounted on a moving robot.

Moreover, we present a fully annotated version of the FROG dataset for people detection using 2D LiDAR sensors. Compared to existing datasets such as DROW, FROG contains annotations for 100% of its laser scans (unlike DROW which only annotates 5%), 17x more annotated scans, 100x more people annotations, and over twice the distance traveled by the robot.

Link to FROG’s datasets

Link to FROG people detection dataset

Echord++ Dataset in the sewage system of Barcelona, Spain

We present a, to the best of our knowledge, unprecedented set of data in a challenging indoor environment: the visitable sewers of Barcelona. The datasets were recorded in real sewers of different places of Barcelona with two different platorms: Our SIAR ground robot, which was designed by IdMind company, and the ARSI aerial platform from EURECAT. They were designed to participate in the Urban Robotic Challenge for Sewer Inspection of the Echord++ project.

Link to Echord++ datasets

Smoky Datasets

Datasets of an indoor scenario with artificial smoke

We present a dataset obtained in an underground location with reduced-visibility conditions (artificial smoke). The set consists of logs obtained with different levels of smoke. In addition, we provide the users with a partial ground-truth and baselines of the localization of the platforms, which can be used for testing localization and SLAM algorithms.

Link to Smoke datasets

(Foto Haru 2)

Robots

Some of the robots and robot systems we have contributed in their creation. You can check more videos at Vimeo and YouTube

Haru, the Social Robot

We are collaborating with Honda Research Institute, Japan, in the research and development for the social robot Haru.

MBZIRC 2020 Competition

NIx: ATEX Certifiable Navigation Module for Ground Robotic Inspection

ARCO: Autonomous Robot Co-Worker

TERESA (TElepresence REinforcement-learning Social Agent) robot

A summary of the Teresa project on Vimeo.

SIAR: Sewer Inspection Autonomous Robot

FROG: Fun Robotic Outdoor Guide

FROG at the Lisbon Zoo here

URUS (Ubiquituous Robotics in Urban Settings)

URUS FP6 Project: Romeo as autonomous taxi on Vimeo.

This videos highlights some experiments on the final review of the EU Project URUS, in November 2009. Our robot Romeo was able to provide autonomous transportation of persons between different points in the Campus Nord of UPC, in Barcelona. The main results can be found in:

A. Sanfeliu, J. Andrade-Cetto, M. Barbosa, R. Bowden, J. Capitan, A. Corominas, A. Gilbert, J. Illingworth, L. Merino, J.M. Mirats, P. Moreno, A. Ollero, J. Sequeira, and M.T.J. Spaan. Decentralized Sensor Fusion for Ubiquitous Networking Robotics in Urban Areas. Sensors, 10:2274–2314, 2010.

http://www.mdpi.com/1424-8220/10/3/2274

SRL

The Service Robotics Lab is a research group on Robotics and related technologies in the Universidad Pablo de Olavide, Seville, Spain.

↑↑↑ Come with us this Saturday, February 21 to enjoy FLL ↑↑↑

Research Highlights

Robot Localization, Mapping and SLAM

Robot Autonomous Navigation

Robot Decision Making under Uncertainties

Exploration and Active Sensing

Multi-Robot Systems

Social Robotics

Machine Learning for Robotics