Scientific objectives

Scientific contributions

We present the main scientific contributions achieved by the two research groups and the research topics relevant to the RoboCup@Home competitions and outline how they will contribute and be further developed in this context.
The teams contribute complementary achievements so that their integration will allow for increased robustness and effectiveness of the proposed solutions. We thus believe that our RoboCup@Home project will be the basis to achieve additional novel results on the topics mentioned below.
  • Planning and plan execution
The deployment of robots in populated environments interacting with non-expert users requires facing many sources of uncertainty during task execution such as incomplete information about the environment or unpredictable behaviours coming from humans. Planning and plan execution under such uncertainties is also an important problem to be addressed within the RoboCup@Home competition and in this context, both Sapienza and Lincoln partners have recent research results. In [Iocchi-ICAPS16], a practical framework based on a decision-theoretic formalism for generation and execution of robust plans for service robots is presented and, in [Hanheide-AI15], task failure is handled intelligently by combining different types of robot's knowledge to solve the problem of task planning and execution under uncertainty and in open worlds, explanation of task failure and verification of those explanations.

Furthermore, robots interacting with humans are expected to demonstrate socially acceptable behaviours and to follow social norms. However, most of the recent works in this field do not address the problem of explicit representation of the social norms and their integration in the reasoning and the execution components of a cognitive robot. In [Carlucci-IROS15], we present a framework for planning and execution of social plans, in which social norms are described in a domain and language independent form.
  • Human-Robot Interaction
Social robots deployed in large public spaces have to carry out short-term interactions with many unknown people. In order to provide a better user experience, personalized multi-modal interactions have shown to be more effective. In this context, [Iocchi-ICSR15] presented a module for HRI based on explicit representation of social norms that provides a high degree of variability in the personalization of the interactions, maintaining easy extendibility and scalability. 
However, the design of such multi-modal interactions can be a complex and time-consuming process. [Lazaro17] proposes a formalism for the description of multi-modal interactions and the methods for their automatic generation and execution. The approach is based on the use of interaction templates to facilitate the design and management of the multi-modal behaviour.

Generating appropriate robot behaviours during the interaction it is also a key factor to achieve successful interactions. In [Dondrup-Rob15], the problem of maintaining Human-Robot Spatial Interactions (HRSI) is studied from the point of view of the Proxemics, where distances between the agents are included into a probabilistic model based on a Qualitative Trajectory Calculus.

Finally, analysing the performance of an HRI system in order to improve the interactions requires a systematic approach. In [Lohse-HRI09], a method is proposed to jointly  analyse system level and interaction level in an integrated manner. The approach allows to trace back patterns that deviate from prototypical interaction sequences to the distinct system components of the robot. 
  • Long-term autonomy
One of the main goals of the RoboCup@Home is to develop a system able to robustly navigate in dynamic environments subject to changes and unpredictable situations. In this context, [Pulido-IROS16] presented a localization and mapping system based on a spatio-temporal occupancy grid that explicitly represents the persistence and periodicity of the individual cells and can predict the probability of their occupancy in the future. The proposed representation improves localisation accuracy and the efficiency of path planning.
In [Pulido-ICRA15], we present an approach for topological navigation of service robots in dynamic indoor environments this approach uses a topological representation of the environment that simplifies definition of navigation actions, and is augmented with a spatio-temporal model that specifically represent changes that stem from events in the environment, which impact on the success probability of planned actions which allows the robot to predict action outcomes and to devise better navigation plans.
In [Hanheide-HRI17], we have also shown how better HRI can be facilitated by exploiting long-term spatio-temporal experience, similar to the approached above, but directly linking long-term autonomy with setting goals for a mobile robot.

Publications
  • [Hanheide-HRI17] M. Hanheide, D. Hebesberger, and T. Krajnik. The When, Where, and How: An Adaptive Robotic Info-Terminal for Care Home Residents – A long-term Study. In Proc ACM/IEEE Int. Conf. on Human-Robot Interaction (HRI), Vienna, 2017.
  • [Lazaro17] M. T. Lázaro, F. Montesanti, A. Vanzo, and L. Iocchi. High-level formalization and execution of human-robot multi-modal interactions. Under review.
  • [Iocchi-ICAPS16] L. Iocchi, L. Jeanpierre, M. T. Lázaro, and A.-I. Mouaddib. A practical framework for robust decision-theoretic planning and execution for service robots. In Int. Conf. on Automated Planning and Scheduling (ICAPS), pages 486–494, London, UK, June 12-17, 2016. PDF
  • [Pulido-IROS16] J. Pulido Fentanes, T. Krajnik, M. Hanheide, and T. Duckett. Persistent localization and life-long mapping in changing environments using the frequency map enhancement. In Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), Daejeon, Korea, Oct. 9 - 14 2016.  PDF
  • [Hanheide-AI15] M. Hanheide et al. Robot task planning and explanation in open and uncertain worlds. Artificial Intelligence, 2015. DOI
  • [Carlucci-IROS15] F. M. Carlucci, L. Nardi, L. Iocchi, and D. Nardi. Explicit representation of social norms for social robots. In Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), 2015. PDF
  • [Iocchi-ICSR15] L. Iocchi, M. T. Lázaro, L. Jeanpierre, and A.-I. Mouaddib. Personalized short-term multi-modal interaction for social robots assisting users in shopping malls. In Int. Conf. on Social Robotics, Paris, France, Oct 26-30 2015. PDF
  • [Dondrup-Rob15] C. Dondrup, N. Bellotto, M. Hanheide, K. Eder, and U. Leonards. A computational model of human-robot spatial interactions based on a qualitative trajectory calculus. Robotics, 4(1):63, 2015. DOI
  • [Pulido-ICRA15] J. Pulido Fentanes, B. Lacerda, T. Krajn ́ık, N. Hawes, and M. Hanheide. Now or later? predicting and maximising success of navigation actions from long-term experience. In Int. Conf. on Robotics and Automation (ICRA), 2015. PDF
  • [Lohse-HRI09] M. Lohse, M. Hanheide, K. J. Rohlfing, and G. Sagerer. Systemic interaction analysis (SInA) in HRI. In The 4th ACM/IEEE Int. Conf. on Human Robot Interaction, HRI ’09, pages 93–100, New York, NY, USA, 2009. ACM. DOI