![](bg9.png)
service and assistive robot technology with high relevance for future domestic appli-
cations.
At the time of writing, the core components of our spoken dialog framework were
integrated, allowing us to run and test some of the RoboCup@Home tasks. As addi-
tional features become available on the CAMBADA@Home robotic platform, more
home-centered tasks foreseen in RoboCup@Home rulebook are planned to be added
to its speech interface repository. This includes tasks related to object detec-
tion/recognition/manipulation, human detection/recognition, and other tasks with
increased complexity in terms of speech recognition and dialog management, and
where actions have to be carried out without predefined order.
As future work, we intend to investigate further more the issues related to the
overall system accuracy and robustness, especially the ones related to the speech
recognition component. Using Microsoft Kinnect microphone array as an input unit,
we are exploring its audio features and processing tools to better integrate them in our
spoken dialog framework. Still related to the speech recognition component, we are
investigating various approaches by combining different types of acoustic and lan-
guage models for restricted domains. Moreover, due to the multimodal communica-
tion features present in the robotic framework, we will pursuit research efforts to
improve the overall dialog system performance by taking advantage of information
from other system components such as localization and vision. The
CAMBADA@Home team plans to build on these results in order to participate in the
RoboCup@Home challenges at the RoboCup'2012.
Acknowledgements
We would like to thank people from the Olympus framework developer’s team for
providing it, and for helping and answering our technical questions. This work is part
of the Living Usability Lab for Next Generation Networks (www.livinglab.pt)
project, a QREN project, co-funded by COMPETE and FEDER.
References
1. EUROP Executive Board Committee: Robotic Visions (To 2020 and Beyond). The Strateg-
ic Research Agenda for Robotics in Europe, July 2009
2. Tapus, A., Mataric, M. and Scassellati, B.: The grand challenges in socially assistive robot-
ics. IEEE Robotics and Automation Magazine, vol. 14, no. 1, March 2007
3. Lopes, L.: Carl: from Situated Activity to Language Level Interaction and Learning, Proc.
IEEE Int'l Conf. on Intelligent Robots and Systems (IROS), Lausanne, Switzerland, p. 890-
896, 2002
4. Neves, A., Azevedo, J., Cunha, B., Lau, N., Silva, J., Santos, F., Corrente, G., Martins, D.,
Figueiredo, N., Pereira, A., Almeida, L., Lopes, L., Pinho, A., Rodrigues, J. and Pedreiras,
P.: CAMBADA soccer team - from robot architecture to multiagent coordination. In Robot
Soccer. INTECH, January 2010
5. Cunha, J., Neves, A., Azevedo, J., Cunha, B., Lau, N. and Pereira, A.: A Mobile Robotic
Platform for Elderly Care. AAL Workshop, BIOSTEC 2011, Rome, Italy, 2011
35