Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Driver model behaviour from ECE regulation #47

Open
tmIdiada opened this issue Jul 26, 2021 · 4 comments
Open

Driver model behaviour from ECE regulation #47

tmIdiada opened this issue Jul 26, 2021 · 4 comments

Comments

@tmIdiada
Copy link

Hi,

is it on your list to implement also the driver model from ECE regulation (including the jerk times, the lateral movement possibilities until perception, perception time, risk evaluation time, ... and also the AEB as baseline with its jerk time, delay and 0.85G deceleration, ...) as baseline for the comparison of the results?

Kind regards,

Thaddäus

@arauschert
Copy link
Collaborator

Hi,

an interesting suggestion. We haven't considered that yet. The driver model would be a specific controller for the ego vehicle, which could be used instead of the ALKS function. So this is a bit of a different focus, but I can check, if maybe esmini already provides such a controller. This would improve the demonstration, if the ego vehicle isn't driven by the default controller and does not crash into the targets all the time.

@arauschert
Copy link
Collaborator

arauschert commented Jul 27, 2021

@eknabevcc
Do you have a recommendation, which of the esmini controllers would be suitable for a human driver model that brakes as well (doesn't need to have exactly the parameters of the ALKS driver model)?

@tmIdiada
Copy link
Author

Hi, yes for sure there is the possibility to implement it as a controller. But there is also the possibility to create such scenarios with appropriate actions for the ego vehicle, then for each scenario a second xosc would be needed with this driver model (quick and dirty solution to create such a baseline).

But for sure the proper solution would be a controller.

@eknabevcc
Copy link
Contributor

Good discussion. First, esmini is unfortunately lacking a longitudinal driver model/controller. However it is planned to add a simple one, probably during September (no commitment, just prognosis :)).

I also like @tmIdiada's idea of implementing driver behavior by means of OSC maneuver (including relevant events with conditions and actions) put in a catalog which could be referred to in any scenario. Haven't tested it, but it seems conceptually feasible.
But I agree, a controller is a cleaner solution.

To conclude, unfortunately no such controller in esmini yet.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants