Behavior optimizations

[Flova]

Summary

Bring peak behavior CPU load from 99% to ~40% with an avg. of ~25%

Proposed changes

• Cache frequently computed values during each tick
• Use the events executor
• Reduce usage of tf for simple transformations

Checklist

• Run colcon build
• Write documentation
• Test on your machine
• Test on the robot
• Create issues for future work
• Triage this PR and label it

[Copilot]

Pull Request Overview

This PR optimizes CPU usage by caching repeated computations, standardizing TF buffer initialization, switching to a lighter weight executor, and replacing costly TF transforms with direct numpy operations.

• Standardized tf_buffer initialization across nodes with the new Buffer signature
• Swapped MultiThreadedExecutor for EventsExecutor and added cache clearing
• Introduced a @cached_capsule_function decorator and applied it to expensive capsule methods

Reviewed Changes

Copilot reviewed 9 out of 9 changed files in this pull request and generated 4 comments.

Show a summary per file

File	Description
bitbots_world_model/bitbots_robot_filter/bitbots_robot_filter/filter.py	Reordered Buffer arguments for tf_buffer
bitbots_world_model/bitbots_ball_filter/bitbots_ball_filter/ball_filter.py	Reordered Buffer arguments for tf_buffer
bitbots_team_communication/bitbots_team_communication/bitbots_team_communication/bitbots_team_communication.py	Changed tf_buffer to use named argument
bitbots_navigation/bitbots_path_planning/bitbots_path_planning/path_planning.py	Reordered Buffer arguments for tf_buffer
bitbots_behavior/bitbots_body_behavior/bitbots_body_behavior/bitbots_body_behavior.py	Replaced MultiThreadedExecutor with EventsExecutor
bitbots_behavior/bitbots_blackboard/bitbots_blackboard/capsules/world_model_capsule.py	Added caching decorator and replaced TF-based transform with numpy
bitbots_behavior/bitbots_blackboard/bitbots_blackboard/capsules/team_data_capsule.py	Applied @cached_capsule_function to team data methods
bitbots_behavior/bitbots_blackboard/bitbots_blackboard/capsules/init.py	Defined cached_capsule_function and added per-capsule cache
bitbots_behavior/bitbots_blackboard/bitbots_blackboard/body_blackboard.py	Added clear_cache to flush all capsule caches

Comments suppressed due to low confidence (2)

bitbots_behavior/bitbots_blackboard/bitbots_blackboard/capsules/init.py:11

• The new caching decorator introduces stateful behavior; consider adding unit tests to verify that caching and clear_cache correctly store and invalidate results.

def cached_capsule_function(method):

bitbots_behavior/bitbots_blackboard/bitbots_blackboard/capsules/team_data_capsule.py:72

• [nitpick] The method name time may be ambiguous or collide with modules; consider renaming it to current_time or now for clarity.

def time(self) -> Time:

[Copilot]

Other TF buffers in this project specify a cache duration; relying on the default may lead to inconsistency. Consider passing the intended Duration explicitly.

[Copilot]

[nitpick] Using positional parameters for the new Buffer signature can be less clear. Consider switching to named arguments (e.g., Buffer(cache_time=Duration(...), node=self)) for readability.

Suggested change

	self.tf_buffer = Buffer(Duration(seconds=10.0), self)
	self.tf_buffer = Buffer(cache_time=Duration(seconds=10.0), node=self)