When we talk about improving collaboration within our organisations, we’re usually talking about improving it between our human employees. Some new research from MIT is attempting to go a bit beyond that however, and investigate how human and robot collaboration can be improved.
“In general, everything around us is getting smarter,” says Brian Williams, a professor of aeronautics and astronautics and leader of the Model-Based Embedded and Robotic Systems group within MIT’s Computer Science and Artificial Intelligence Laboratory. “So we’re trying to allow people to interact with these increasingly autonomous systems in the same way that they would interact with another human.”
The ultimate aim for these kind of collaborative systems is to provide better control over driverless vehicles. In the shorter term though, the researchers are developing systems that allow driver and vehicle to work together on planning routes etc.
The researchers paint a picture of their technology at use in companies such as Zipcar.
“The dilemma for Zipcar users is that they don’t want to pay a lot of money, so they only want to reserve the car for as long as they need it,” they say. “But they then run the risk of not reserving it for long enough and so having to pay a penalty.”
The alternative would see the algorithm working out the best way to fit everything into the time you’ve booked. It’d be a real world version of the traveling salesman problem.
The system begins by asking drivers what they want to achieve in the time they have booked. It will then analyse digital maps to determine the best way to achieve that in the time allowed.
What’s more, it will also inform the driver of the parts of their plan that add problems to the overall ambition, so for instance if a particular stop is too far from a Zipcar pickup point.
“Our technology views the process of collaboration as a diagnostic problem,” they say. “So the algorithm figures out why the travel plan failed, what were the important things that caused it to fail, and explains this back to the user.”
The system will then offer up a few alternative options to try and eliminate the problem, which the user can select from. Alternatively they can provide the system with more information about what they want to achieve. The outcome of this back and forth is an improved system that hopefully can make smarter choices.
There are of course other potential uses for such a system, but it provides a nice insight into how humans and computers can work together to create smart outcomes.
You can find out a bit more about the project in the video below.