Boffins teach football bots how to fall
RonaldoBots apply lessons from martial arts
Boffins are teaching football-playing robots how to fall properly.
Traditional approaches to robotics have focused on keeping mechanical machines upright and balanced. But in the context of playing football on an uneven surface and with interaction with other robot players, that's an unrealistic goal.
Robotic experts in Chile have begun teaching their bots to fall down without damaging themselves and recover quickly, taking lessons from the world of martial arts. An article in New Scientist explains that the researchers aim to further evolve the technique so that bots who play in goal can dive to save shots.
Javier Ruiz-del-Solar, something like the Raphael Benitez of RoboSoccer, and his team from the University of Chile in Santiago are developing the technique for bots due to take part in the annual world RoboCup in Austria next month. New Scientist reports that the Chilean boffins hope to outshine the opposition by researching and later integrating superior falling capabilities into their metal men.
To find out the optimum ways for a robot to fall, the team used a computer simulation based on a humanoid robot called Nao, the player used by all teams competing in the RoboCup's Standard Platform League. Nao has 22 simple joints, each with a single degree of freedom, and is typical of the bipedal soccer robots being built today.
Ruiz-del-Solar and colleagues put their simulated soccerbot through a series of different fall sequences. The simulation computes the stresses on each joint, which can then be plugged into the team's equations to work out the total damage factor.
They found that one of the main ways to minimise damage is for the robot to fold its legs underneath it. Among other things, that means the robot is much less likely to hit its head on the ground. Another good strategy is to use a fall sequence consisting of several movements, so the falling body has several points of contact with the ground, spreading the energy of the impact over a large number of joints, rather than taking it all in one disastrous crunch.
The eventual goal of the RoboCup competition is to develop a team of robots capable of beating the best humanity has to offer by 2050.
By that point presumably, future Drogba-model bots will have learned to to fall down in the area as if they had been tripped, make inflated salary demands, and disgrace themselves after a night on the last just before a crucial game. ®
Sponsored: Hyper-scale data management