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

Integrations/vbd #283

Draft
wants to merge 92 commits into
base: main
Choose a base branch
from
Draft

Integrations/vbd #283

wants to merge 92 commits into from

Conversation

daphne-cornelisse
Copy link
Contributor

@daphne-cornelisse daphne-cornelisse commented Oct 27, 2024

Description

This PR integrates a pre-trained VBD model with the simulator.

Todo (debugging)

Inputs

  • agents_history & agents_future: Ensure yaw is aligned (@nadarenator, @daphnecor)
  • agents_history & agents_future: Ensure velocities (x,y) are aligned (@nadarenator, @daphnecor)
  • agents_id: Ensure the same vehicles are controlled and the order is the same (@daphnecor)
  • Is the velocity used in the dynamics model? Does the physics matter? (@nadarenator)
  • polylines Check construction and alignment (@nadarenator, @daphnecor)
  • agent_futures: why is only the first timestep added?

Outputs

  • Check outputs (@daphnecor)

Done (archive)

  • Add support for a "warmup period"
  • Construct a sample (main input to the model) with the following pieces of info in global coordinates:
dict_keys(['agents_history', 'agents_interested', 'agents_type', 'agents_future', 'traffic_light_points', 'polylines', 'polylines_valid', 'relations', 'agents_id', 'anchors'])
  • Integrate StateDynamics model for the actions
  • Use StateDynamics model to step the vehicles for the init_steps (warmup period)
  • Feed predicted action back into simulator
  • Make videos to test VBD model
  • Align waymax with GPUDrive sim; specifically in terms of:
  • 1) Road id grouping;
  • 2) Road object types

daphne-cornelisse and others added 12 commits December 28, 2024 11:30
* Add support for resample_limit

* Add option to draw the log replay trajectories in visualizer

* WIP

* minimal set maps script

* minimal set maps script

* Data processing utils

* Rendering improvements and ppo

* Make dataset to resample from configurable

* Bug fix: resampling

* Agent observation figures

* Cleanup

* Prep experiments

* Prep experiments
* Make collision behavior transient

* Simpler way to reset collision state for collision behavior ignore

* Reset info on collision ignore

---------

Co-authored-by: Aarav Pandya <[email protected]>
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

Successfully merging this pull request may close these issues.

2 participants