refactor: Task score always start at 0.0

[jmatejcz]

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

3. Download GameLauncher binary: humble or jazzy

4. 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: []

5. Run the benchmark

python src/rai_bench/rai_bench/examples/o3de_test_benchmark.py

6. 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