Duckietown Challenges | Home | Challenges | Submissions |
In this variation of the lane following challenge, your agent is embodied in multiple robots. Avoid the crashes with different versions of yourself.
See the documentation for more details.
These are the metrics defined:
driven_lanedir_consec_median
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_median
This is the median survival time. The simulation is terminated when the car goes outside of the road or it crashes with an obstacle.
deviation-center-line_median
This is the median lateral deviation from the center line.
in-drivable-lane_median
This is the median of the time spent outside of the drivable zones. For example this penalizes driving in the wrong lane.
Depends on successful evaluation on LFV_multi 🚗🚗🚗 - Lane following multibody (simulation 👾, validation 🏋)
The submission must first pass the validation step.
The sum of the following tests should be at least 2.0.
Test on absolute scores:
good_enough
(1.0 points) driven_lanedir_consec_median
.Test on relative performance:
better-than-bea-straight
(1.0 points) straight
.At the beginning execute step LFVmultibodyv-sim
.
If step LFVmultibodyv-sim
has result success, then declare the submission SUCCESS
.
If step LFVmultibodyv-sim
has result failed, then declare the submission FAILED
.
If step LFVmultibodyv-sim
has result error, then declare the submission ERROR
.
LFVmultibodyv-sim
Timeout 10000.0
This is the Docker Compose configuration skeleton:
version: '3' services: evaluator: image: docker.io/andreacensi/aido5-lfv_multi-sim-testing-lfvmultibodyv-sim-evaluator:2020_12_02_19_27_49@sha256:f08ab286cf978c49237eecf5ac016b79a4916f6b7aa2ef7093ac7c7157977d58 environment: experiment_manager_parameters: 'episodes_per_scenario: 3 episode_length_s: 60.0 min_episode_length_s: 0.0 seed: 20200922 physics_dt: 0.05 max_failures: 2 fifo_dir: /fifos sim_in: /fifos/simulator-in sim_out: /fifos/simulator-out sm_in: /fifos/scenario_maker-in sm_out: /fifos/scenario_maker-out timeout_initialization: 120 timeout_regular: 120 scenarios: - /scenarios port: 10123 ' ports: - '10123' simulator: image: docker.io/duckietown/challenge-aido_lf-simulator-gym@sha256:c0096866077db3574e425d40603d8f5fc8ebbd164da7c0578df94ff4ede58d95 environment: AIDONODE_CONFIG: "env_constructor: Simulator\nenv_parameters:\n max_steps:\ \ 500001 # we don't want the gym to reset itself\n domain_rand: 0\n\ \ camera_width: 640\n camera_height: 480\n distortion: true\n \ \ num_tris_distractors: 0\n color_ground: [0, 0.3, 0] # green\n \ \ enable_leds: true\ntopdown_resolution: 600\ndebug_no_video: false\n" AIDONODE_DATA_IN: /fifos/simulator-in AIDONODE_DATA_OUT: fifo:/fifos/simulator-out solution-ego0: image: SUBMISSION_CONTAINER environment: AIDONODE_NAME: ego0 AIDONODE_DATA_IN: /fifos/ego0-in AIDO_REQUIRE_GPU: '1' AIDONODE_DATA_OUT: fifo:/fifos/ego0-out solution-ego1: image: SUBMISSION_CONTAINER environment: AIDONODE_NAME: ego1 AIDONODE_DATA_IN: /fifos/ego1-in AIDO_REQUIRE_GPU: '1' AIDONODE_DATA_OUT: fifo:/fifos/ego1-out solution-ego2: image: SUBMISSION_CONTAINER environment: AIDONODE_NAME: ego2 AIDONODE_DATA_IN: /fifos/ego2-in AIDO_REQUIRE_GPU: '1' AIDONODE_DATA_OUT: fifo:/fifos/ego2-out solution-ego3: image: SUBMISSION_CONTAINER environment: AIDONODE_NAME: ego3 AIDONODE_DATA_IN: /fifos/ego3-in AIDO_REQUIRE_GPU: '1' AIDONODE_DATA_OUT: fifo:/fifos/ego3-out
The text SUBMISSION_CONTAINER
will be replaced with the user containter.
Cloud simulations | 1 |