Closed mattuntergassmair closed 4 years ago
It may be difficult to implement this change - IDM does not have access to the timestep and propagate(... LaneFollowingAccel ...)
applies the action without knowledge about what model produced it.
@MaximeBouton
It seems like this could be solve by having a different action type that would prevent negative velocities in the propagate
, something like ForwardAccel
.
One would then wrap the IDM model to output such action, or we could make it the default action for IDM but I am not sure if this is a good idea.
Would it be reasonable to introduce proportional braking, with -d_max
as the bound to which deceleration is maximized?
I think that's already the case, but depending on how long you apply your deceleration d_max
for, the resulting velocity could be negative
Currently, in the case where the distance to the lead vehicle is smaller than s_min a full break with maximum deceleration is returned. At this maximum deceleration, the resulting velocity may become negative (e.g. at dt=1s, initial state with v=2m/s, deceleration=9m/s -> v_new=-7m/s). It is probably safe to say that negative velocities (i.e. backward driving, against the flow of traffic) are usually not desired. I suggest changing the model such that it does not reach negative velocities, as this seems out of the scope of an IDM.