8000 refactor: Task score always start at 0.0 by jmatejcz · Pull Request #444 · RobotecAI/rai · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

refactor: Task score always start at 0.0 #444

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

Jump to bottom
Merged
merged 2 commits into from
Feb 28, 2025
Merged

refactor: Task score always start at 0.0 #444

merged 2 commits into from
Feb 28, 2025

Conversation

jmatejcz
Copy link
Contributor

Purpose

Refactor tasks so that the score for scenario is always counted from 0.0

Proposed Changes

Score is now calculated only at the end of scenario
Tasks now calculate score based on how many objects that were initially incorrect are now correct. This mean when in the initial scene there are 2 objects correctly placed and 2 objects incorrectly placed, there are only 2 objects to be corrected. Every corrected object will add 0.5 to the score. Displacing initially correct object is not counted in.

Issues

Testing

  1. Setup the repository
  2. Install dependencies listed in:
    https://github.com/RobotecAI/rai/blob/main/docs/demos/manipulation.md

and:

poetry install --with openset
colcon build --symlink-install
source setup_shell.sh

  1. Download GameLauncher binary: humble or jazzy

  2. Populate src/rai_bench/rai_bench/o3de_test_bench/configs/o3de_config.yaml with:

binary_path: /path/to/your/GameLauncher
robotic_stack_command: ros2 launch examples/manipulation-demo-no-binary.launch.py
required_services:
  - /grounding_dino_classify
  - /grounded_sam_segment
  - /manipulator_move_to
  - /spawn_entity
  - /delete_entity
required_topics:
  - /color_image5
  - /depth_image5
  - /color_camera_info5
required_actions: []
  1. Run the benchmark
python src/rai_bench/rai_bench/examples/o3de_test_benchmark.py
  1. What to look for:
  • Check in logs if numbers of correct and incorrect objects match what you see in simulation
  • Check if score is calculated properly based on these numbers
    image
    image

@jmatejcz jmatejcz force-pushed the jm/feat/tasks-score-start-from-0 branch from 987dc4a to 1da35fc Compare February 28, 2025 13:39
@jmatejcz jmatejcz requested a review from maciejmajek February 28, 2025 14:04
@jmatejcz jmatejcz marked this pull request as ready for review February 28, 2025 14:04
@maciejmajek maciejmajek merged commit 84c6493 into feat/simbench Feb 28, 2025
2 checks passed
@maciejmajek maciejmajek deleted the jm/feat/tasks-score-start-from-0 branch February 28, 2025 15:07
maciejmajek pushed a commit that referenced this pull request Mar 7, 2025
@jmatejcz @maciejmajek
refactor: Task score always start at 0.0 (#444)
7cf12dd
@jmatejcz jmatejcz mentioned this pull request Mar 26, 2025
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@MagdalenaKotynia MagdalenaKotynia Awaiting requested review from MagdalenaKotynia

@maciejmajek maciejmajek Awaiting requested review from maciejmajek

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@jmatejcz @maciejmajek
0