Last year, a car which followed the athlete instead of the path began to emerge as the best solution, but a car in front doesn't know where you're heading, only which way to turn to keep you in frame. This causes it to drive in circles.
Setting the car to follow a desired magnetic heading won't work on its own, because the magnetic heading isn't precise enough. The latest theory is if the car senses both a desired magnetic heading & the direction towards the human, it can stay on the path. This works only if the human is directly behind the car, with decreasing accuracy as the human moves alongside the car.
The car maneuvers so the angle from the human to the car to the desired magnetic heading is 180. The desired magnetic heading is changed from the stick controller to steer the car.
If the desired magnetic heading is off, following it leads the car off the path, but the human stays on the path. As the car heads off the path, the human-car-magnetic heading shrinks & the car turns back towards the path to make it approach 180 again. Wherever the human goes on the path, the car maneuvers to stay in front.
The 2nd case is the human alongside the car. This requires a different algorithm that maintains a fixed distance to the human. If the human gets farther away, the car steers to reduce the distance. This would be much less accurate than following behind the car.
The 3rd case is the human in front of the car. It just needs the direction to the human. No single algorithm can handle all 3 cases. The human needs to configure what algorithm to use, 2 desired angles & a distance from the car. It's impractical for most applications, but the 180' case is still an intriguing method of remote control.
Cases in between would entail both maintaining a fixed perpendicular distance from the human & a fixed human-car-magnetic heading. The human-car-magnetic heading & perpendicular distance would have to be set on the phone with a one-time recording of the current positions.
Key to anything is the object recognition for the car to find the human & measure distance. Previous experience showed chroma keying was hopeless, so instead the target is black & white with all colored objects removed. The target has to be as unreflective as possible, probably made of felt. This would be sensitive to shadows & all the usual problems.
So there isn't a foolproof solution in either athlete following or path following. The problem still seems dead.