AI Driving Olympics Home Challenges Submissions Jobs

Challenge "LFV 🚗🚗 - Lane following + Vehicles (robotarium 🏎, validation 🏋)"

Challenge description

(No description.)

Leaderboard

Submissions

Challenge logistics

Scoring

Scoring criteria

These are the metrics defined:

Traveled distance - driven_lanedir_consec

This is the median distance traveled, along a lane. (That is, going in circles will not make this metric increase.)

This is discretized to tiles.

Survival time - survival_time

This is the median survival time. The simulation is terminated when the car goes outside of the road or it crashes with an obstacle.

Lateral deviation - deviation-center-line

This is the median lateral deviation from the center line.

Major infractions - in-drivable-lane

This is the median of the time spent outside of the drivable zones. For example this penalizes driving in the wrong lane.

Dependencies

Dependencies

Depends on successful evaluation on LFV 🚗🚗 - Lane following + Vehicles (simulation 👾, testing 🥇)

The submission must first pass the testing.

The sum of the following tests should be at least 2.0.

Test on absolute scores:

good_enough(1.0 points)
Obtain at least 0.2 for score driven_lanedir_consec_median.

Test on relative performance:

better-than-bea-straight(1.0 points)
Do at least as good as a submission ofBea Baselines labeled straight.

Depends on successful evaluation on LF 🚗 - Lane following (robotarium 🏎, validation 🏋)

The submission must first pass the LF real.

The sum of the following tests should be at least 2.0.

Test on absolute scores:

good_enough(1.0 points)
Obtain at least 0.2 for score driven_lanedir_consec.

Test on relative performance:

better-than-bea-straight(1.0 points)
Do at least as good as a submission ofBea Baselines labeled straight.

Details

Technical details

Evaluation steps details

  • At the beginning execute step eval0.

  • If step eval0 finishes with status success, then execute step eval0-visualize.

  • If step eval0 finishes with status failed, then declare the submission FAILED.

  • If step eval0 finishes with status error, then declare the submission ERROR.

  • If step eval0 finishes with status success, then execute step eval0-videos.

  • If step eval1 finishes with status success, then execute step eval1-videos.

  • If step eval2 finishes with status success, then execute step eval2-videos.

  • If step eval0 finishes with status success, then execute step eval1.

  • If step eval0-visualize finishes with status failed, then declare the submission FAILED.

  • If step eval0-visualize finishes with status error, then declare the submission ERROR.

  • If step eval1 finishes with status success, then execute step eval1-visualize.

  • If step eval1 finishes with status failed, then declare the submission FAILED.

  • If step eval1 finishes with status error, then declare the submission ERROR.

  • If step eval1 finishes with status success, then execute step eval2.

  • If step eval1-visualize finishes with status failed, then declare the submission FAILED.

  • If step eval1-visualize finishes with status error, then declare the submission ERROR.

  • If step eval2 finishes with status success, then execute step eval2-visualize.

  • If step eval2 finishes with status failed, then declare the submission FAILED.

  • If step eval2 finishes with status error, then declare the submission ERROR.

  • If step eval2-visualize finishes with status success, then declare the submission SUCCESS.

  • If step eval2-visualize finishes with status failed, then declare the submission FAILED.

  • If step eval2-visualize finishes with status error, then declare the submission ERROR.

Evaluation step eval0

Timeout 18000.0

Evaluation in the robotarium.

This is the Docker Compose configuration skeleton:

version: '3'
services:
    evaluator:
        image: docker.io/andreacensi/aido3-off-lfv-real-validation-eval0-evaluator:2020_02_28_11_18_13@sha256:14937e5e9a768219ba7097107df82d268b8c35a5f7fe87dc71269d4d164f6e9e
        environment: {}
        ports:
        - 8005:8005

The text SUBMISSION_CONTAINER will be replaced with the user containter.

Resources required for evaluating this step

# Duckiebots2
AIDO 2 Map LFV public1

Evaluation step eval1

Timeout 18000.0

Evaluation in the robotarium.

This is the Docker Compose configuration skeleton:

version: '3'
services:
    evaluator:
        image: docker.io/andreacensi/aido3-off-lfv-real-validation-eval1-evaluator:2020_02_28_11_18_25@sha256:14937e5e9a768219ba7097107df82d268b8c35a5f7fe87dc71269d4d164f6e9e
        environment: {}
        ports:
        - 8005:8005

The text SUBMISSION_CONTAINER will be replaced with the user containter.

Resources required for evaluating this step

# Duckiebots2
AIDO 2 Map LFV public1

Evaluation step eval2

Timeout 18000.0

Evaluation in the robotarium.

This is the Docker Compose configuration skeleton:

version: '3'
services:
    evaluator:
        image: docker.io/andreacensi/aido3-off-lfv-real-validation-eval2-evaluator:2020_02_28_11_18_38@sha256:14937e5e9a768219ba7097107df82d268b8c35a5f7fe87dc71269d4d164f6e9e
        environment: {}
        ports:
        - 8005:8005

The text SUBMISSION_CONTAINER will be replaced with the user containter.

Resources required for evaluating this step

# Duckiebots2
AIDO 2 Map LFV public1

Evaluation step eval0-videos

Timeout 10800.0

This is the Docker Compose configuration skeleton:

version: '3'
services:
    evaluator:
        image: docker.io/andreacensi/aido3-off-lfv-real-validation-eval0-videos-evaluator:2020_02_28_11_19_21@sha256:3b828381f8de914eedb4ad4431e7c50cd3aa4a19be6498f6abb11dd4d9fb8c60
        environment:
            WORKER_I: '0'
            WORKER_N: '1'
            INPUT_DIR: /challenges/previous-steps/eval0/logs_raw
            OUTPUT_DIR: /challenges/challenge-evaluation-output
            DEBUG_OVERLAY: '1'
            BAG_NAME_FILTER: autobot,watchtower
            OUTPUT_FRAMERATE: '7'

The text SUBMISSION_CONTAINER will be replaced with the user containter.

Resources required for evaluating this step

Cloud simulations1

Evaluation step eval1-videos

Timeout 10800.0

This is the Docker Compose configuration skeleton:

version: '3'
services:
    evaluator:
        image: docker.io/andreacensi/aido3-off-lfv-real-validation-eval1-videos-evaluator:2020_02_28_11_19_38@sha256:3b828381f8de914eedb4ad4431e7c50cd3aa4a19be6498f6abb11dd4d9fb8c60
        environment:
            WORKER_I: '0'
            WORKER_N: '1'
            INPUT_DIR: /challenges/previous-steps/eval1/logs_raw
            OUTPUT_DIR: /challenges/challenge-evaluation-output
            DEBUG_OVERLAY: '1'
            BAG_NAME_FILTER: autobot,watchtower
            OUTPUT_FRAMERATE: '7'

The text SUBMISSION_CONTAINER will be replaced with the user containter.

Resources required for evaluating this step

Cloud simulations1

Evaluation step eval2-videos

Timeout 10800.0

This is the Docker Compose configuration skeleton:

version: '3'
services:
    evaluator:
        image: docker.io/andreacensi/aido3-off-lfv-real-validation-eval2-videos-evaluator:2020_02_28_11_19_53@sha256:3b828381f8de914eedb4ad4431e7c50cd3aa4a19be6498f6abb11dd4d9fb8c60
        environment:
            WORKER_I: '0'
            WORKER_N: '1'
            INPUT_DIR: /challenges/previous-steps/eval2/logs_raw
            OUTPUT_DIR: /challenges/challenge-evaluation-output
            DEBUG_OVERLAY: '1'
            BAG_NAME_FILTER: autobot,watchtower
            OUTPUT_FRAMERATE: '7'

The text SUBMISSION_CONTAINER will be replaced with the user containter.

Resources required for evaluating this step

Cloud simulations1

Evaluation step eval0-visualize

Timeout 1080.0

This is the Docker Compose configuration skeleton:

version: '3'
services:
    evaluator:
        image: docker.io/andreacensi/aido3-off-lfv-real-validation-eval0-visualize-evaluator:2020_02_28_11_18_49@sha256:d95babe778e197cc8f534d425915a334466289b2238c4e27bcde97c86a4a0674
        environment:
            STEP_NAME: eval0

The text SUBMISSION_CONTAINER will be replaced with the user containter.

Resources required for evaluating this step

Cloud simulations1

Evaluation step eval1-visualize

Timeout 1080.0

This is the Docker Compose configuration skeleton:

version: '3'
services:
    evaluator:
        image: docker.io/andreacensi/aido3-off-lfv-real-validation-eval1-visualize-evaluator:2020_02_28_11_19_00@sha256:d95babe778e197cc8f534d425915a334466289b2238c4e27bcde97c86a4a0674
        environment:
            STEP_NAME: eval1

The text SUBMISSION_CONTAINER will be replaced with the user containter.

Resources required for evaluating this step

Cloud simulations1

Evaluation step eval2-visualize

Timeout 1080.0

This is the Docker Compose configuration skeleton:

version: '3'
services:
    evaluator:
        image: docker.io/andreacensi/aido3-off-lfv-real-validation-eval2-visualize-evaluator:2020_02_28_11_19_10@sha256:d95babe778e197cc8f534d425915a334466289b2238c4e27bcde97c86a4a0674
        environment:
            STEP_NAME: eval2

The text SUBMISSION_CONTAINER will be replaced with the user containter.

Resources required for evaluating this step

Cloud simulations1