About

Motivation

Starting from 2006, RoboCup@Home has been the largest international annual competition for autonomous service robots as part of the RoboCup initiative [1]. The challenge consists of a set of benchmark tests to evaluate the robots' abilities and performance in a realistic non-standardized home environment setting [2]. It has greatly fostered artificial intelligence development in various domains including human-robot interaction, navigation and mapping in dynamic environments, computer vision, object recognition and manipulation, and many more developments on robot intelligence.

The RoboCup@Home initiative [2] has successfully established a solid ground for domestic service robots development with an effective benchmarking framework to gauge and foster continuous developments in both the robot performances and the competition designs. Over the years of competitions, it is observed the undeniable facts that the participating community is growing steadily, the increasing public awareness over the media, press and internet, and the improvement of robot performances and scientific contributions [1].

However, the development direction of current RoboCup@Home has also certain room for improvement awaiting to be addressed. In RoboCup@Home, the participants are given total freedom in designing their own robots (hardware). We can observed that majority of the teams in RoboCup@Home are using custom made robot hardware. It is a logical approach to encourage novel robot design, but it is also resulting an open ended question to the development of service robots.

We all understand that the software is generally crafted closely based on the hardware design for optimized solution. By having customized robot hardware also means that the control software has to be coded accordingly. Even with the existence of general software framework likes ROS [3], the implementation is still fairly complex when the hardware differs significantly. Hence, even under the open source promotion by the initiative, code sharing in RoboCup@Home for collective development is still not very effective.

With the complexity in both hardware and software, it is obvious that the development curve of the RoboCup@Home teams have a very steep start. The amount of technical knowledge and resources (both manpower and cost) required to start a new team has made the event exclusive to only established research organizations. For instance, in domestic RoboCup Japan Open challenge, the participating teams in RoboCup@Home were less than 10 teams with similar teams ever since the past few years. There were actually several new team requests but the development gap was too huge for them to even complete the robots.

To address the above open ended question, a new proposal of RoboCup@Home SPL (Standard Platform League) has been initiated in early 2014. Different from the concept of the other Standard Platform League [4] in RoboCup, a standard robot platform is not just the mean but also the goal of RoboCup@Home SPL. Similar to RoboCup@Home, where a flexible benchmarking framework is established to allow evolution of the competition rules in contrast to minimal rules change in soccer league, the SPL of RoboCup@Home has also a mechanism to evolve the standard robot platform along with the development of the league.

The RoboCup@Home SPL Concepts

Apart from the original RoboCup@Home initiative, the RoboCup@Home SPL initiative comprises of the following concepts:

Standard yet Flexible

Similar to RoboCup@Home, where a fixed set of competition rules cannot address the dynamic evolution of service robot development, finding a fixed robot solution as standard robot platform for @Home challenge is also not possible. Hence in RoboCup@Home SPL, a framework of standardization is formulated to provide a well-defined robot platform as a basis with modification allowance to pitch ideas of improvement through the competitions. A similar benchmarking approach is adapted to gauge the robot performance, while ideas of improvement will be considered as upgrade to the next standard robot platform.

Gathering the Crowd Efforts

RoboCup@Home SPL aims to narrow down the open ended question by converging the research efforts into the same direction. By getting everyone to work on the same robot platform, we can formulate a more general problems and solutions in service robot development. While RoboCup@Home addresses on the functionality of the robots, RoboCup@Home SPL is aiming on the optimization and practicability of the robot design for the given functions. Ultimately, this may impact the waiting time till the day robots can serving you at home.

Open Source and Reproducibility

RoboCup@Home SPL aims to further promote the obligation to open source service robot development. It is aims to prioritize open source code-sharing and giving incentive to the participants to develop support wiki and tutorials. By having a standard robot platform, we can increase the reproducibility of the open source contributions, and hence, open up service robot development into a bigger community. It is also important to justify the cost-to-performance ratio of the standard platform to keep the affordability by a large community.

References

[1] Thomas Wisspeintner, Tijn van der Zant, Luca Iocchi and Stefan Schiffer, “RoboCup@Home: Scientific Competition and Benchmarking for Domestic Service Robots”, Interaction Studies, Vol.10, No.3 (2009), pp.392-426.

[2] Tijn van der Zant and Luca Iocchi, “Robocup@Home: Adaptive Benchmarking of Robot Bodies and Minds”, Social Robotics, (2011), pp.214-225.

[3] Quigley, Morgan, Ken Conley, Brian Gerkey, Josh Faust, Tully Foote, Jeremy Leibs, Rob Wheeler, and Andrew Y. Ng. "ROS: an open-source Robot Operating System." In ICRA workshop on open source software, vol. 3, no. 3.2, 2009.

[4] Standard Platform League - RoboCup Federation Wiki, http://wiki.robocup.org/wiki/Standard_Platform_League#Rules