Skip to content
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

Add gifs for baseline agent in benchmark scenarios #2068

Merged
merged 2 commits into from
Jun 16, 2023
Merged

Add gifs for baseline agent in benchmark scenarios #2068

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1ab4094
Add gifs for baseline agent in benchmark scenarios.
Adaickalavan Jun 16, 2023
b990919
Rectify spelling.
Adaickalavan Jun 16, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 29 additions & 2 deletions docs/benchmarks/driving_smarts_2023_1.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,27 +45,54 @@ below.
Any method such as reinforcement learning, offline reinforcement learning, behavior cloning, generative models,
predictive models, etc, may be used to develop the policy.

Several scenarios are provided for training. Their names and tasks are as follows.
The desired task execution is illustrated in a gif by a trained baseline agent.
Training scenarios
------------------

Several scenarios are provided for training as follows.
The corresponding GIF image shows the task execution by a trained baseline agent.

**Driving SMARTS 2023.1 scenarios**

+ :scenarios:`cruise_2lane_agents_1 <sumo/straight/cruise_2lane_agents_1>`

.. image:: https://raw.githubusercontent.com/smarts-project/smarts-project.github.io/master/assets/driving_smarts_2023_1/cruise_2lane_agents_1.gif

+ :scenarios:`cutin_2lane_agents_1 <sumo/straight/cutin_2lane_agents_1>`

.. image:: https://raw.githubusercontent.com/smarts-project/smarts-project.github.io/master/assets/driving_smarts_2023_1/cutin_2lane_agents_1.gif

+ :scenarios:`merge_exit_sumo_t_agents_1 <sumo/straight/merge_exit_sumo_t_agents_1>`
+ :scenarios:`overtake_2lane_agents_1 <sumo/straight/overtake_2lane_agents_1>`
+ :scenarios:`00a445fb-7293-4be6-adbc-e30c949b6cf7_agents_1 <argoverse/straight/00a445fb-7293-4be6-adbc-e30c949b6cf7_agents_1>`

.. image:: https://raw.githubusercontent.com/smarts-project/smarts-project.github.io/master/assets/driving_smarts_2023_1/00a445fb-7293-4be6-adbc-e30c949b6cf7_agents_1.gif
:width: 75%
+ :scenarios:`0a53dd99-2946-4b4d-ab66-c4d6fef97be2_agents_1 <argoverse/straight/0a53dd99-2946-4b4d-ab66-c4d6fef97be2_agents_1>`

.. image:: https://raw.githubusercontent.com/smarts-project/smarts-project.github.io/master/assets/driving_smarts_2023_1/0a53dd99-2946-4b4d-ab66-c4d6fef97be2_agents_1.gif
:width: 75%
+ :scenarios:`0a576bf1-66ae-495a-9c87-236f3fc2aa01_agents_1 <argoverse/straight/0a576bf1-66ae-495a-9c87-236f3fc2aa01_agents_1>`

**Driving SMARTS 2023.2 scenarios**

+ :scenarios:`1_to_3lane_left_turn_sumo_c_agents_1 <sumo/intersections/1_to_3lane_left_turn_sumo_c_agents_1>`

.. image:: https://raw.githubusercontent.com/smarts-project/smarts-project.github.io/master/assets/driving_smarts_2023_2/1_to_3lane_left_turn_sumo_c_agents_1.gif
:width: 75%
+ :scenarios:`1_to_3lane_left_turn_middle_lane_c_agents_1 <sumo/intersections/1_to_3lane_left_turn_middle_lane_c_agents_1>`
+ :scenarios:`00b15e74-04a8-4bd4-9a78-eb24f0c0a980_agents_1 <argoverse/turn/00b15e74-04a8-4bd4-9a78-eb24f0c0a980_agents_1>`
+ :scenarios:`0a60b442-56b0-46c3-be45-cf166a182b67_agents_1 <argoverse/turn/0a60b442-56b0-46c3-be45-cf166a182b67_agents_1>`

.. image:: https://raw.githubusercontent.com/smarts-project/smarts-project.github.io/master/assets/driving_smarts_2023_2/0a60b442-56b0-46c3-be45-cf166a182b67_agents_1.gif
:width: 75%
+ :scenarios:`0a764a82-b44e-481e-97e7-05e1f1f925f6_agents_1 <argoverse/turn/0a764a82-b44e-481e-97e7-05e1f1f925f6_agents_1>`

.. image:: https://raw.githubusercontent.com/smarts-project/smarts-project.github.io/master/assets/driving_smarts_2023_2/0a764a82-b44e-481e-97e7-05e1f1f925f6_agents_1.gif
:width: 75%
+ :scenarios:`0bf054e3-7698-4b86-9c98-626df2dee9f4_agents_1 <argoverse/turn/0bf054e3-7698-4b86-9c98-626df2dee9f4_agents_1>`

.. image:: https://raw.githubusercontent.com/smarts-project/smarts-project.github.io/master/assets/driving_smarts_2023_2/0bf054e3-7698-4b86-9c98-626df2dee9f4_agents_1.gif
:width: 75%

Observation space
-----------------
Expand Down
28 changes: 22 additions & 6 deletions docs/benchmarks/driving_smarts_2023_3.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,28 +34,44 @@ of steps per episode.
Any method such as reinforcement learning, offline reinforcement learning, behavior cloning, generative models,
predictive models, etc, may be used to develop the policy.

Several scenarios are provided for training. Their names and tasks are as follows.
The desired task execution is illustrated in a gif by a trained baseline agent.
Training scenarios
------------------

+ straight_2lane_agents_1
A single ego must follow a specified leader, with no background traffic.

.. image:: /_static/driving_smarts_2023/platoon_straight_2lane_agents_1.gif
Several scenarios are provided for training as follows.
The corresponding GIF image shows the task execution by a trained baseline agent.

+ :scenarios:`straight_2lane_sumo_agents_1 <sumo/vehicle_following/straight_2lane_sumo_agents_1>`
+ :scenarios:`straight_2lane_sumo_t_agents_1 <sumo/vehicle_following/straight_2lane_sumo_t_agents_1>`
+ :scenarios:`straight_3lanes_sumo_agents_1 <sumo/vehicle_following/straight_3lanes_sumo_agents_1>`
+ :scenarios:`straight_3lanes_sumo_t_agents_1 <sumo/vehicle_following/straight_3lanes_sumo_t_agents_1>`

.. image:: https://raw.githubusercontent.com/smarts-project/smarts-project.github.io/master/assets/driving_smarts_2023_3/straight_3lanes_sumo_t_agents_1.gif

+ :scenarios:`straight_3lanes_sumo_t_agents_2 <sumo/vehicle_following/straight_3lanes_sumo_t_agents_2>`
+ :scenarios:`merge_exit_sumo_agents_1 <sumo/vehicle_following/merge_exit_sumo_agents_1>`
+ :scenarios:`merge_exit_sumo_t_agents_1 <sumo/vehicle_following/merge_exit_sumo_t_agents_1>`

.. image:: https://raw.githubusercontent.com/smarts-project/smarts-project.github.io/master/assets/driving_smarts_2023_3/merge_exit_sumo_t_agents_1.gif

+ :scenarios:`merge_exit_sumo_t_agents_2 <sumo/vehicle_following/merge_exit_sumo_t_agents_2>`
+ :scenarios:`ff239c9d-e4ff-4acc-bad5-bd55648c212e_0_agents_1 <argoverse/vehicle_following/ff239c9d-e4ff-4acc-bad5-bd55648c212e_0_agents_1>`

.. image:: https://raw.githubusercontent.com/smarts-project/smarts-project.github.io/master/assets/driving_smarts_2023_3/ff239c9d-e4ff-4acc-bad5-bd55648c212e_0_agents_1.gif

+ :scenarios:`ff239c9d-e4ff-4acc-bad5-bd55648c212e_agents_1 <argoverse/vehicle_following/ff239c9d-e4ff-4acc-bad5-bd55648c212e_agents_1>`
+ :scenarios:`ff6dc43b-dd27-4fe4-94b6-5c1b3940daed_agents_1 <argoverse/vehicle_following/ff6dc43b-dd27-4fe4-94b6-5c1b3940daed_agents_1>`

.. image:: https://raw.githubusercontent.com/smarts-project/smarts-project.github.io/master/assets/driving_smarts_2023_3/ff6dc43b-dd27-4fe4-94b6-5c1b3940daed_agents_1.gif
:width: 75%
+ :scenarios:`ff9619b5-b0c0-4942-b5d8-df6a5814f8a2_agents_1 <argoverse/vehicle_following/ff9619b5-b0c0-4942-b5d8-df6a5814f8a2_agents_1>`

.. image:: https://raw.githubusercontent.com/smarts-project/smarts-project.github.io/master/assets/driving_smarts_2023_3/ff9619b5-b0c0-4942-b5d8-df6a5814f8a2_agents_1.gif
:width: 75%
+ :scenarios:`ffd10ec2-715b-48af-a89d-b11f79927f63_agents_1 <argoverse/vehicle_following/ffd10ec2-715b-48af-a89d-b11f79927f63_agents_1>`

.. image:: https://raw.githubusercontent.com/smarts-project/smarts-project.github.io/master/assets/driving_smarts_2023_3/ffd10ec2-715b-48af-a89d-b11f79927f63_agents_1.gif
:width: 75%

Observation space
-----------------

Expand Down