From 1c59ee042114927a28ec53d375aedf027a2bc11a Mon Sep 17 00:00:00 2001 From: QuanyiLi Date: Sun, 27 Aug 2023 16:26:00 +0100 Subject: [PATCH] add PG --- documentation/PG.rst | 17 ++++++++++++++++- documentation/example.rst | 2 +- documentation/lyft.rst | 5 +++-- documentation/nuplan.rst | 6 ++++-- documentation/nuscenes.rst | 6 ++++-- documentation/waymo.rst | 10 +++++----- 6 files changed, 33 insertions(+), 13 deletions(-) diff --git a/documentation/PG.rst b/documentation/PG.rst index e3b0170..35c9471 100644 --- a/documentation/PG.rst +++ b/documentation/PG.rst @@ -2,5 +2,20 @@ PG ############ -Known Issues +The PG scenarios are collected by running simulation and record the episodes in MetaDrive simulator. +The name PG refers to Procedural Generation, which is a technique used to generate maps. +When a map is determined, the vehicles and objects will be spawned and actuated according to a hand-crafted rules. + +Build PG Database +=================== + +If MetaDrive is installed, there is no any further steps required to build the database. Just run the following +command to generate, i.e. 1000 scenarios:: + + python -m scenarionet.convert_pg -d /path/to/pg_database --num_scenarios 1000 + + +Known Issues: PG ================== + +N/A diff --git a/documentation/example.rst b/documentation/example.rst index 8f6ec96..e877ab9 100644 --- a/documentation/example.rst +++ b/documentation/example.rst @@ -42,7 +42,7 @@ And place the downloaded tfrecord file to a folder. Let's call it ``exp_waymo`` Likewise, place all downloaded tfrecord files to the same folder. -3. Build Database +3. Build Mini Database ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Run the following command to extract scenarios in ``exp_waymo`` to ``exp_converted``:: diff --git a/documentation/lyft.rst b/documentation/lyft.rst index 3cd59a2..3ea23f8 100644 --- a/documentation/lyft.rst +++ b/documentation/lyft.rst @@ -24,7 +24,8 @@ The dataset includes: using new Lyft data. +Known Issues: Lyft +=================== -Known Issues -############# +N/A diff --git a/documentation/nuplan.rst b/documentation/nuplan.rst index a322523..b500947 100644 --- a/documentation/nuplan.rst +++ b/documentation/nuplan.rst @@ -2,5 +2,7 @@ nuPlan ############################# -Known Issues -================== +Known Issues: nuPlan +====================== + +N/A diff --git a/documentation/nuscenes.rst b/documentation/nuscenes.rst index 0db3901..9f900bf 100644 --- a/documentation/nuscenes.rst +++ b/documentation/nuscenes.rst @@ -2,5 +2,7 @@ nuScenes ############################# -Known Issues -================== +Known Issues: nuScenes +======================= + +N/A diff --git a/documentation/waymo.rst b/documentation/waymo.rst index 9c26fac..f32afa6 100644 --- a/documentation/waymo.rst +++ b/documentation/waymo.rst @@ -26,7 +26,7 @@ The dataset includes: - Adjusted some road edge boundary height estimates -1. Install requirements +1. Install Waymo Toolkit ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ First of all, we have to install the waymo toolkit and tensorflow:: @@ -40,7 +40,7 @@ First of all, we have to install the waymo toolkit and tensorflow:: .. note:: This package is only supported on Linux platform. -2. Download Raw Data +2. Download TFRecord ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Waymo motion dataset is at `Google Cloud `_. @@ -72,7 +72,7 @@ The downloaded data should be stored in a directory like this:: └── ... -3. Build Database +3. Build Waymo Database ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Run the following command to extract scenarios in any directory containing ``tfrecord``. @@ -82,7 +82,7 @@ Here we take converting raw data in ``training_20s`` as an example:: Now all converted scenarios will be placed at ``/path/to/your/database`` and are ready to be used in your work. -Known Issues -================== +Known Issues: Waymo +===================== N/A