It is still just a fantasy, but the robot who helps around the house is getting closer. Justina is a three-year-old robot and is getting more sophisticated by the day.
RoboCup 2014 is being held in Joao Pessoa, Brazil in July. If you think of it as just a soccer competition, fun though that is, then you need to think again. There are four major leagues including the well known soccer competition - the others are Rescue, @Home and @Work.
The @Home competition has been running since 2006 and the performance of the home help robots has improved each year. The rubric for the contest challenge states:
A set of benchmark tests is used to evaluate the robots’ abilities and performance in a realistic non-standardized home environment setting. Focus lies on the following domains but is not limited to:
- Human-Robot-Interaction and Cooperation
- Navigation and Mapping in dynamic environments
- Computer Vision and Object Recognition under natural light conditions
- Object Manipulation
- Standardization and System Integration
This may not have the glamor of the Darpa robot challenge but it might well produce something more useful.
Justina is the entry from the Universidad Nacional Autonoma de Mexico (UNAM) BioRobotics lab. This robot which is built using almost off the shelf components has been evolving since around 2011 but his year it looks impressive enough to be practical.
Watch the video and see if you agree:
The use of the Kinect and video-based face recognition both make things very much more possible than they were two years ago. Rather than having to solve basic problems like location and object recognition, you can simply download the required software. This doesn't mean that there isn't a lot of work to do, but we are unlikely to get a robot that does anything useful until things are just a matter of modular construction.
There is still a lot to be done to improve the robot's interaction with humans. Having it repeat everything back is a good way to make sure it doesn't do anything silly, but it is very irritating. And as with most robots, doing anything difficult your immediate reaction has to be - get on with it.
Robots currently are slow - we need to do something about it.