The European Commission has founded a project named 'Co-operative Human Robot Interaction Systems' (CHRIS) for a cost of €3.65 million. The project, which started in March 2008, will last 4 years. It is based at Bristol Robotics Lab (BRL) which will work with the University of the West of England (UWE Bristol) and several other European institutions. At this time, the scientists are trying to answer a -- not so -- simple question: can you trust a robot to work safely with you in the kitchen? For example, a service robot might be stirring soup while you add cream. But how will it act if you get burned? Will it stop stirring if you ask it? As said one of the lead researcher, 'This project aims to develop the rules we need to introduce this level of sophistication into service robots who are working closely with people.' But read more...
You can see on the left several pictures of the CHRIS robotic system. The top one comes from the CHRIS project at BRL. Here is the introduction to the project. "CHRIS will address the fundamental issues which would enable safe Human Robot Interaction (HRI). Specifically this project addresses the problem of a human and a robot performing co-operative tasks in a co-located space, such as in the kitchen where your service robot stirs the soup as you add the cream. These issues include communication of a shared goal (verbally and through gesture), perception and understanding of intention (from dextrous and gross movements), cognition necessary for interaction, and active and passive compliance."
The middle picture shows the lead researcher, Professor Chris Melhuish, director of the Bristol Robotics Laboratory (BRL), with one of the BRL robots. (Credit: BRL)
The bottom one shows how robots could help in the kitchen. This picture probably comes from BRL, but has been picked from a Sky News article, "Robot Chef Which Stirs Soup To Be Tested By Bristol Scientists" (May 14, 2008).
Now, let's look at the Bristol University news release for some more details given by Melhuish. "When we interact with other humans we are interpreting facial expression, body position, gestures, tone of voice as well as sharing a goal and understanding and following verbal instructions. For example in the soup situation, not only does the robot need to know what the goal is (making the soup) but he also needs to know how hard to stir the soup, what it means when you hold up your hand to say enough, to interpret the look of pain on your face if you accidentally get splashed with hot soup, and to stop stirring when told."
And here what he says about the interaction between humans and robots. "Enabling robots to interact safely with humans is a key need for the future development of robotics. A key premise of this project is that it will be beneficial to our society and our economy to generate service robots capable of safe co-operative physical interaction with humans. If we can provide the ‘thinking’ (cognition) necessary for safe robot human cooperation in the same physical space then this will enable significant advancement in this area, and we will be a step closer to having service robots in society."
The news release adds that the University of the West of England (UWE Bristol) share is valued at €1,342,898. However, a EU document named "Cognitive Systems, Interaction, Robotics" (PDF format, 28 pages, 160 KB, January 2008) provides different numbers about the total funding of the CHRIS project, saying on page 4 that the EU funds for the project will reach €3,650,000.
Of course, the CHRIS project involves more institutions than the two Bristol universities. The other European partners include the Centre National de la Recherche Scientifique at Toulouse, France, the Université Lyon 2 Louis Lumière, also in France, the Italian Institute of Technology Genoa, Italy, and the Max Planck Institute at Leipzig, Germany.
Here is a description of the project taken from the page 4 of the EU document mentioned above. "CHRIS addresses fundamental issues related to the design of safe human robot interaction. Robots and humans are assumed to share a given environment and to cooperate on tasks. The primary research question is: How can interaction between a human and an intelligent autonomous agent be safe without being pre-scripted and still achieve the desired goal? The key hypothesis is that safe interaction between humans and robots can be engineered physically and cognitively for joint physical tasks requiring co-operative manipulation of real world objects. Engineering principles for safe movement and dexterity will be explored on three robot platforms, and developed with regard to language, communication and decisional action planning where the robot reasons explicitly with its human partner. Integration of cognition for safe co-operation in the same physical space will spawn significant advances in the area, and be a step towards genuine service robotics."
Rendez-vous in 2012 to discover the results of this project.
Sources: Bristol University news release, May 14, 2008; and various websites
You'll find related stories by following the links below.