Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
N
nuplan-devkit
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package Registry
Container Registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Eli Henry Dykhne
nuplan-devkit
Commits
8c9cb0f5
Commit
8c9cb0f5
authored
1 year ago
by
sacardoz
Browse files
Options
Downloads
Patches
Plain Diff
oops
parent
a07e30e6
No related branches found
Branches containing commit
No related tags found
2 merge requests
!21
Major changes. convert nuplan devkit to handle occlusions for project
,
!8
Shea multiagent rules
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
nuplan/planning/simulation/observation/ml_planner_agents.py
+3
-3
3 additions, 3 deletions
nuplan/planning/simulation/observation/ml_planner_agents.py
with
3 additions
and
3 deletions
nuplan/planning/simulation/observation/ml_planner_agents.py
+
3
−
3
View file @
8c9cb0f5
...
...
@@ -197,7 +197,7 @@ class MLPlannerAgents(AbstractObservation):
history_input
=
self
.
_build_history_input
(
agent_token
,
agent_data
[
'
ego_state
'
],
history
)
if
agent_data
[
'
occlusion
'
]
is
not
None
:
planner
_input
=
agent_data
[
'
occlusion
'
].
occlude_input
(
history_input
)
history
_input
=
agent_data
[
'
occlusion
'
].
occlude_input
(
history_input
)
planner_input
=
PlannerInput
(
iteration
=
iteration
,
history
=
history_input
,
traffic_light_data
=
traffic_light_data
)
trajectory
=
agent_data
[
'
planner
'
].
compute_trajectory
(
planner_input
)
...
...
@@ -292,9 +292,9 @@ class MLPlannerAgents(AbstractObservation):
# Convert agent state to a corresponding "ego state" object, or pull it from cache if already computed.
if
matched_agent
is
None
:
faux_ego_observation
=
deepcopy
(
current_state
)
faux_ego_observation
.
_time_point
=
ego_state
.
time_point
faux_ego_observation
.
_time_point
=
deepcopy
(
ego_state
.
time_point
)
else
:
faux_ego_observation
=
self
.
_build_ego_state_from_agent
(
matched_agent
,
ego_state
.
time_point
)
faux_ego_observation
=
self
.
_build_ego_state_from_agent
(
matched_agent
,
deepcopy
(
ego_state
.
time_point
)
)
# Rebuild timestep and buffer - creating a new observations object with old ego appended.
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment