Skip to content

Remove vehicles with invalid positions and invalid goals from controlled vehicles #24

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.

Sign up for GitHub

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

Merged
merged 2 commits into from
Jan 20, 2024
Merged

Remove vehicles with invalid positions and invalid goals from controlled vehicles #24

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
63cdd58
Remove vehicles with invalid positions from self.controlled_vehicles.
daphne-cornelisse Jan 7, 2024
111cd0f
Merge branch 'hr_rl' into hr_rl_fix_invalid_verhicles
daphne-cornelisse Jan 20, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 8 additions & 8 deletions configs/env_config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,17 +8,17 @@ env: my_custom_multi_env_v1 # name of the env, hardcoded for now
episode_length: 80
warmup_period: 10 # In the RL setting we use a warmup of 10 steps
# How many files of the total dataset to use. -1 indicates to use all of them
num_files: 10
num_files: 1000
fix_file_order: true # If true, always select the SAME files (when creating the environent), if false, pick files at random
sample_file_method: "random" # ALTERNATIVES: "no_replacement" (SUPPORTED) / "score-based" (TODO: @Daphne)
sample_file_method: random # ALTERNATIVES: "no_replacement" (SUPPORTED) / "score-based" (TODO: @Daphne)
dt: 0.1
sims_per_step: 10
img_as_state: false
discretize_actions: true
include_head_angle: false # Whether to include the head tilt/angle as part of a vehicle's action
accel_discretization: 5
accel_lower_bound: -3
accel_upper_bound: 3
accel_upper_bound: 3
steering_lower_bound: -0.7 # steer right
steering_upper_bound: 0.7 # steer left
steering_discretization: 5
Expand Down Expand Up @@ -78,26 +78,26 @@ rew_cfg:
# sense as the episodes are 9 seconds long, i.e. we'd have to go more than 40 m/s to get there
goal_speed_scaling: 40.0

# # # # State normalization settings # # # #
# # # # State normalization settings # # # #
normalize_state: true
# Ego feature names + max values in each category
ego_state_feat_min: -30
ego_state_feat_max:
veh_len: 16
veh_width: 4
speed: 100
target_dist: 300
target_dist: 300
target_azimuth: 3.14
target_heading: 3.14
rel_target_speed_dist: 40
curr_accel: 5 # Vehicle acceleration
curr_steering: 3
curr_head_angle: 0.00001 # Not used at the moment

vis_obs_max: 100 # The maximum value across visible state elements
vis_obs_max: 500 # The maximum value across visible state elements
vis_obs_min: -10 # The minimum value across visible state elements

# # # # Agent settings # # # #
# # # # Agent settings # # # #
subscriber:
view_angle: 3.14 # the distance which the cone extends before agents are not visible; set to pi rad to correct for missing head angle
view_dist: 80
Expand All @@ -110,4 +110,4 @@ subscriber:

# Path to folder with traffic scene(s) from which to create an environment
data_path: ./data_full/train
val_data_path: ./data_full/valid
val_data_path: ./data_full/valid
Loading