The ability for robots to collaborate effectively with one another has been one of the more interesting areas of research in the past few years. I wrote last year about the thoughts of the MIT Computer Science and AI Laboratory (CSAIL) on the topic.
Central to the paper is a system whereby three robots can work successfully together to ensure items are delivered accurately in an unpredictable environment.
To put their robots through their paces, the team created a miniature bar type environment, complete with one ‘bartender’ robot and two ‘waitress’ robots.
The waitress robots would be required to take orders from customers, and also be aware if their ‘colleague’ had delivered that order to the customer whilst also efficiently navigating the bar.
The robots were capable of communicating with one another using a complex algorithm that allowed them to plan the best route and collaborate effectively having been given minimal information at the beginning.
Keeping them safe
Of course, the more robots work in conjunction with each other, the greater the risk that they might bump into one another and cause accidents. A recent paper from Georgia Tech explored some of the safety issues involved when robots start to collaborate.
Their approach involves giving each machine a kind of bubble that surrounds them and within which no other robot is allowed to invade. Whilst this is a reasonable approach, it is certainly not without issues.
“When you have too many robots together, they get so focused on not colliding with each other that they eventually just stop moving,” the authors say. “Their safety behaviors take over and the robots freeze. It’s impossible for them to go anywhere because any movement would cause their bubbles to pop.”
To overcome this, they developed a range of algorithms that shrink down that zone of no entry so that robots can move to within inches of their peers without colliding with them, whilst maintaining their confidence to perform the task required of them. It’s believed to be the first successful development of such an algorithm.
“In everyday speak, we’ve shrunk the size of each robot’s bubble to make it as small as possible,” they say. “Our system allows the robots to make the minimum amount of changes to their original behaviors in order to accomplish the task and not smack into each other.”
With robots increasingly required to work collectively alongside one another, it’s a useful advance in our thinking. Check out the video below to see the algorithm in action.