Instituição Proponente: IST
Unidade de Investigação Principal: ISR
LARSyS Plurianual Budget
PEst-OE/EEI/LA0009/2011

  • ERL Barcelona

  • ERL Tournament ISRoboNet@Home Testbed

  • ERL @Barcelona

  • ERL @Barcelona

  • ERL Tournament ISRoboNet@Home Testbed

  • ERL @Barcelona

  • Testbed 2017

  • ERL Barcelona 9

  • RoboCup 2018

  • ERL Barcelona 3

  • ERL Barcelona 8

  • ERL Barcelona 1

  • ERL Tournament ISRoboNet@Home Testbed

  • ERL Tournament ISRoboNet@Home Testbed

  • ERL Tournament ISRoboNet@Home Testbed

  • ERL Tournament ISRoboNet@Home Testbed

SocRob@Home is an active team of SocRob, a long-term project at Institute for Systems and Robotics from Instituto Superior Técnico, which encompasses a broad range of efforts towards a team of robots to perform tasks, with a particular focus on the participation in scientific competitions.

Research focus

The Intelligent Robots and Systems research group of the Institute for Systems and Robotics coordinated a major EU funded project directly related to human-robot interactions and social behaviours. The MOnarCH project aimed to provide a set of autonomous robots with the capabilities of performing tasks to entertain kids with health issues (more specifically, cancer) from Instituto Português de Oncologia Francisco Gentil in Lisbon (IPO).

After that, from 2013 until 2015, the EU funded project RoCKIn, in collaboration with five other partners, encompassed a set of competitions related to domestic and work environments, which were organized to test new benchmark methods for evaluating challenging aspects of state-of-the-art robots

The legacy of these two projects, plus the challenge to find a domestic solution for robotics convinced us to gather and form a unique team, highly motivated and ready for the challenges to come!

  • Perception and sensor fusion: how to extract meaningful information from one or more sensors, and fuse together information from several sources, taking into account their associated uncertainty. We take a probabilistic approach to quantitatively representing uncertainty, as well as performing inference, on the solid theoretical framework provided by Bayesian statistics;
  • Decision making under uncertainty: how perception and action affect the real world is inherently uncertain so it’s important to take a decision-theoretic approach on the maximization of the expected utility;
  • Human-robot interaction: once robots operate in human-inhabited environments they need to interact with humans. In this context, we pursue multiple communication modalities, including speech, web-based remote interface, and onboard touch interface;
  • Manipulation and grasping: the problem of robots being capable of grasping and manipulating real-world objects, which raises interest in topics from finger design to motion planning.

Team

The team is comprised of students and researchers related to robotics. From Post-Docs to MSc students on a voluntary basis, all of them contribute hand-on to the project. Check former members here

null

Pedro Lima

Associate Professor, Project Coordinator
null

Rodrigo Ventura

Assistant Professor, Professor in charge
null

Guilherme Lawless

PhD Student - Team Leader
null

Carlos Azevedo

PhD Student
null

Enrico Piazza

PhD Student
null

Rute Luz

MSc Student
Past team members
Francisco Lera (PhD Student)
Pedro Miraldo (Post-doc)
Meysam Basiri (Post-doc)
Tiago Veiga (Post-doc)
Aamir Ahmad (ex-Post-doc)
João Messias (ex-Post-doc)
Filipe Jesus (ex-Research Engineer)
André Farinha (ex-MSc student)
João O’Neill (ex-MSc student)
João Mendes (Research Engineer)
Pedro Resende (MSc Student)
Diogo Pires (MSc Student)
Maria Braga (MSc Student)
Carolina Loureiro (MSc Student)
André Mateus (MSc Student)
Pedro Santos (MSc Student)
Ricardo Simas (MSc Student)
Nuno Mendes (MSc Student)
José Iglesias (MSc Student)
João Garcia (MSc Student)
Luis Luz (MSc Student)
João Cartucho (MSc Student)
Inês Alexandre (MSc Student)
João Cerejeira (MSc Student)
Soraia Ferreira (MSc Student)
Diogo Maximino (MSc Student)
Oscar Lima (PhD Student – Team leader)Tiago Dias (PhD Student)
Mithun Kinarullathil (Researcher Engineer)
Jhielson Pimentel (Researcher Engineer)
Miguel Silve (MSc Student)
João Gonçalves (MSc Student)
Diogo Serra (Lab Technician)

Robots

The MBot is composed of two main parts: body and head. The head can pan and has LED backlight to express emotions through a drawn mouth, eyes and checks. The body has all of the CPU devices (two motherboards with i7 processors), a touchscreen and all of the navigation mechanics, based on a Four-Wheel Omnidirectional Mecanum drive.

Regarding additional sensors and actuators needed specifically for @Home competitions, a Cyton 1500 Robai Arm with 7 DoF was attached to the left side of the body for manipulation capabilities and a microphone was placed on the top of the head for voice recognition.

The MBot is continuously developed and tested at the ISRoboNet@Home Testbed.

Previous Robot: ISR-CoBot

ISR-CoBot was an experimental platform for research in Human-Robot Interaction (HRI). A service robot for office environments, it was designed to perform tasks for users. The research was targeted towards a robust platform capable of navigating in crowded environments, to create robots that were aware of their own limitations and are thus capable to autonomously asking humans for help.

The platform resulted from an ongoing collaboration with the CoBot project at Carnegie Mellon University, based on a customized Nomadic Scout differential drive platform. The equipment included a touchscreen on a laptop for HRI and computing, an Hokuyo UTM-30LX laser range finder (range 30m), a Kinect RGB-D camera, and an IP PTZ camera.

Event Participations

2018

2017

2016

2015

  • 19-23 Nov 2015 — RoCKin Competition 2015 (Lisbon, Portugal), a very successful presence, winning two out of three Task Benchmarks and winning ex-aequo (with the Home@Koblenz team) the RoCKIn@Home Challenge!

2014

  • 24-30 Nov 2014 – ROCKIn Toulouse, France

Media

In the SocRob Youtube channel, you’ll find many videos of demos, participation in  International and National competitions, or even relevant events such as the Mbot interacting with the President of Portugal.

You can also see many photos that are taken during competitions and other demos, like the latest album from RoboCup 2018.

Follow the team on Facebook and keep track of the team’s blog, to be a part of the latest developments and achievements.

Publications

 

  • Eric Price, Guilherme Lawless, Roman Ludwig, Igor Martinovic, Heinrich H Buelthoff, Michael J Black, Aamir Ahmad, Deep Neural Network-based Cooperative Visual Tracking through Multiple Micro Aerial Vehicles, IEEE Robotics and Automation Letters, Vol. 3, Issue: 4, pp. 3193-3200, October 2018
  • Rute Luz, Guilherme Lawless, Oscar Lima, Rodrigo Ventura. Small Obstacle Detection and Avoidance using a depth camera: a Case Study in RoboCup@Home, Workshop on Robots for Assisted Living of IEEE/RSJ International Conference On Intelligent Robots And Systems (IROS), 2018, Madrid, Spain.
  • Mithun Kinarullathil, Pedro H. Martins, Carlos Azevedo, Oscar Lima, Guilherme Lawless, Pedro U. Lima, Luís Custódio, Rodrigo Ventura. From User Spoken Commands to Robot Task Plans: a Case Study in RoboCup@Home. Workshop on Language and Robotics of IEEE/RSJ International Conference On Intelligent Robots And Systems (IROS), 2018, Madrid, Spain
  • Oscar Lima, Rodrigo Ventura, and Iman Awaad. Integrating classical planning and real robots in industrial and service robotics domains. In Workshop on Planning and Robotics (PlanRob), International Conference on Automated Planning and Scheduling (ICAPS), Netherlands, 2018. URL: http://users2.isr.tecnico.ulisboa.pt/~yoda/papers/Lima18.pdf
  • João Cartucho, Rodrigo Ventura, and Manuela Veloso. Robust object recognition through symbiotic deep learning in mobile robots. In IEEE/RSJ International Conference On Intelligent Robots And Systems (IROS), 2018, Madrid, Spain.
  • Pedro U. Lima. A Probabilistic Approach to Benchmarking and Performance Evaluation of Robot Systems. In IEEE/RSJ International Conference On Intelligent Robots And Systems (IROS), 2018, Madrid, Spain.
  • Pedro Miraldo, Francisco Eiras, Srikumar Ramalingam. Analytical Modeling of Vanishing Points and Curves in Catadioptric Cameras. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018, Salt Lake City, USA. URL: https://arxiv.org/abs/1804.09460
  • Pedro Miraldo, Tiago Dias, Srikumar Ramalingam. A Minimal Closed-Form Solution for Multi-Perspective Pose Estimation using Points and Lines. In European Conference on Computer Vision (ECCV), 2018, Munich, Germany. URL: https://arxiv.org/abs/1807.09970
  • Gonçalo Pais, Jacinto C. Nascimento, Pedro Miraldo. OmniDRL: Robust Pedestrian Detection using Omnidirectional Cameras and Deep Reinforcement Learning. In PMLR Conference on Robot Learning (CoRL), 2018, Zurich, Switzerland
  • Gonçalo Pais, Pedro Miraldo, and Jacinto C. Nascimento. Multi-task Learning for Pedestrian Detection in Omnidirectional Vision Systems. International Journal on Computer Vision (IJCV), 2018
  • José Iglésias, Pedro Miraldo, Rodrigo Ventura, Towards an Omnidirectional Catadioptric RGB-D Camera, Proc. of IROS 2016 – IEEE/RSJ International Conference on Intelligent Robots and Systems, Daejeon, Korea. http://users2.isr.tecnico.ulisboa.pt/~yoda/papers/Iglesias16.pdf
  • Oscar Lima, Rodrigo Ventura, A case study on automatic parameter optimization of a mobile robot localization algorithm, Proc. of ICARSC 2017 – IEEE 17th International Conference on Autonomous Robot Systems and Competitions, Coimbra, Portugal. http://users2.isr.tecnico.ulisboa.pt/~yoda/papers/Lima17.pdf

Contacts

Pedro Lima

pedro.lima (at) tecnico.ulisboa.pt

+351 21 841 8289

null

Pedro Lima

Associate Professor, Project Coordinator

Are you looking for an amazing experience with real robots in a team environment, while contributing actively for state-of-art research and gaining personal experience that will prove fruitful to your academic and professional future?

If you’re interested in joining SocRob, please send an email to socrob-info (at) isr.ist.utl.pt, or directly contact the responsible, stating who you are, your motivations, your academic background and how you would contribute to this project. Also, check here for more information about our work and some requisites.