[NotInControl]

Originally Posted by yash101

And if everything works out properly, it could be literally a matter of background substraction to get all the robots. Place three color dots on the bumper of the robot and you can then calculate position, direction, velocity and acceleration!

Just a note on this, you could only calculate instantaneous velocity and acceleration, using previously stored data for the tracked object.

If you want to determine track of an object, which is where the object might go next, then you can only *Estimate* the track based on current heading, velocity, etc. using probablity theory and other aprior knowledge. An enhanced Kalman filter will help you out in this scenario, but will never be accurate.

Consider you are programming an autonomous car, you need to track the other cars around you, their position, and velocity, and lets say you want to change lanes, well how do you determine that another car is not switching into that same lane at that moment in time as well. No aprior knowledge can tell you if that car instantly changes course. There is no way to do this with 100% accuracy, unless there is communication between all the cars. If you don't have this communication, the best you can do is predict with some level of certainty less than 100%.

Regards,
Kevin