add gif
This commit is contained in:
fxia22
parent
121aae5abe
commit
cca1b41407
30
README.md
30
README.md
|
|
@ -1,6 +1,9 @@
|
||||||
# Gibson Environment for Training Real World AI
|
# Gibson Environment for Training Real World AI
|
||||||
You shouldn't play video games all day, so shouldn't your AI. In this project we build a virtual environment that offers real world experience. You can think of it like [The Matrix](https://www.youtube.com/watch?v=3Ep_rnYweaI).
|
You shouldn't play video games all day, so shouldn't your AI. In this project we build a virtual environment that offers real world experience. You can think of it like [The Matrix](https://www.youtube.com/watch?v=3Ep_rnYweaI).
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
### Note
|
### Note
|
||||||
This is a 0.1.0 beta release, bug reports are welcome.
|
This is a 0.1.0 beta release, bug reports are welcome.
|
||||||
|
|
||||||
|
|
@ -103,29 +106,4 @@ More examples can be found in `examples/demo` and `examples/train` folder.
|
||||||
|
|
||||||
Environment Configuration
|
Environment Configuration
|
||||||
=================
|
=================
|
||||||
Each environment is configured with a `yaml` file. Examples of `yaml` files can be found in `examples/configs` folder. Parameters for the file is explained as below (take navigation environment for example):
|
Each environment is configured with a `yaml` file. Examples of `yaml` files can be found in `examples/configs` folder. Parameters for the file is explained [here](gibson/configs/README.md).
|
||||||
|
|
||||||
```
|
|
||||||
envname: AntClimbEnv # Environment name, make sure it is the same as the class name of the environment
|
|
||||||
model_id: sRj553CTHiw # Scene id
|
|
||||||
target_orn: [0, 0, 3.14] # target orientation for navigating, the reference frame is world frame
|
|
||||||
target_pos: [-7, 2.6, -1.5] # target position for navigating, the reference frame is world frame
|
|
||||||
initial_orn: [0, 0, 3.14] # initial orientation for navigating
|
|
||||||
initial_pos: [-7, 2.6, 0.5] # initial position for navigating
|
|
||||||
fov: 1.57 # field of view for the camera
|
|
||||||
use_filler: true # use neural network filler or not, it is recommended to leave this argument true
|
|
||||||
display_ui: true # show pygame ui or not, if in a production environment (training), you need to turn this off
|
|
||||||
show_dignostic: true # show dignostics overlaying on the RGB image
|
|
||||||
ui_num: 2 # how many ui components to show
|
|
||||||
ui_components: [RGB_FILLED, DEPTH] # which are the ui components, choose from [RGB_FILLED, DEPTH, NORMAL, SEMANTICS, RGB_PREFILLED]
|
|
||||||
|
|
||||||
output: [nonviz_sensor, rgb_filled, depth] # output of the environment to the robot
|
|
||||||
resolution: 512 # resolution of rgb/depth image
|
|
||||||
|
|
||||||
speed:
|
|
||||||
timestep: 0.01 # timestep of simulation in seconds
|
|
||||||
frameskip: 1 # how many frames to run simulation for one action
|
|
||||||
|
|
||||||
mode: gui # gui|headless, if in a production environment (training), you need to turn this to headless
|
|
||||||
verbose: false # show dignostics in terminal
|
|
||||||
```
|
|
||||||
|
|
@ -0,0 +1,28 @@
|
||||||
|
Environment Configuration
|
||||||
|
=================
|
||||||
|
Each environment is configured with a `yaml` file. Examples of `yaml` files can be found in `examples/configs` folder. Parameters for the file is explained as below (take navigation environment for example):
|
||||||
|
|
||||||
|
```
|
||||||
|
envname: AntClimbEnv # Environment name, make sure it is the same as the class name of the environment
|
||||||
|
model_id: sRj553CTHiw # Scene id
|
||||||
|
target_orn: [0, 0, 3.14] # target orientation for navigating, the reference frame is world frame
|
||||||
|
target_pos: [-7, 2.6, -1.5] # target position for navigating, the reference frame is world frame
|
||||||
|
initial_orn: [0, 0, 3.14] # initial orientation for navigating
|
||||||
|
initial_pos: [-7, 2.6, 0.5] # initial position for navigating
|
||||||
|
fov: 1.57 # field of view for the camera
|
||||||
|
use_filler: true # use neural network filler or not, it is recommended to leave this argument true
|
||||||
|
display_ui: true # show pygame ui or not, if in a production environment (training), you need to turn this off
|
||||||
|
show_dignostic: true # show dignostics overlaying on the RGB image
|
||||||
|
ui_num: 2 # how many ui components to show
|
||||||
|
ui_components: [RGB_FILLED, DEPTH] # which are the ui components, choose from [RGB_FILLED, DEPTH, NORMAL, SEMANTICS, RGB_PREFILLED]
|
||||||
|
|
||||||
|
output: [nonviz_sensor, rgb_filled, depth] # output of the environment to the robot
|
||||||
|
resolution: 512 # resolution of rgb/depth image
|
||||||
|
|
||||||
|
speed:
|
||||||
|
timestep: 0.01 # timestep of simulation in seconds
|
||||||
|
frameskip: 1 # how many frames to run simulation for one action
|
||||||
|
|
||||||
|
mode: gui # gui|headless, if in a production environment (training), you need to turn this to headless
|
||||||
|
verbose: false # show dignostics in terminal
|
||||||
|
```
|
||||||
|
|
@ -1,21 +0,0 @@
|
||||||
## Gibson Core Environment
|
|
||||||
|
|
||||||
This folder contains the code base for running universe engine, as well as instructions needed for implementing custom environment and agent
|
|
||||||
### File Structure
|
|
||||||
- Client: client side code for running remote environment
|
|
||||||
- Core: realenv engine
|
|
||||||
- Data: realenv dataset
|
|
||||||
- Envs: repository of current environments, each can be thought of as a "challenge"
|
|
||||||
- Spaces: Envs dependencies
|
|
||||||
|
|
||||||
### Implementing Agent
|
|
||||||
|
|
||||||
```python
|
|
||||||
observation, reward, done, info = env._step({})
|
|
||||||
```
|
|
||||||
|
|
||||||
- *observation* (object): agent's observation of the current environment
|
|
||||||
- *reward* (float) : amount of reward returned after previous action
|
|
||||||
- *done* (boolean): whether the episode has ended. The agent is responsible for taking care of this, by calling `env.restart()`
|
|
||||||
- *info* (dict): auxiliary diagnostic information (helpful for debugging, and sometimes learning)
|
|
||||||
|
|
||||||
|
|
@ -1,61 +0,0 @@
|
||||||
## Scratch ubuntu:16.04 image with NVIDIA GPU
|
|
||||||
FROM nvidia/cuda
|
|
||||||
|
|
||||||
## Skip keyboard settings
|
|
||||||
ENV DEBIAN_FRONTEND noninteractive
|
|
||||||
|
|
||||||
RUN apt-get update \
|
|
||||||
&& apt-get install -y libav-tools \
|
|
||||||
libpq-dev \
|
|
||||||
libjpeg-dev \
|
|
||||||
cmake \
|
|
||||||
wget \
|
|
||||||
unzip \
|
|
||||||
git \
|
|
||||||
xpra \
|
|
||||||
golang-go \
|
|
||||||
libboost-all-dev \
|
|
||||||
make \
|
|
||||||
&& apt-get clean \
|
|
||||||
&& rm -rf /var/lib/apt/lists/* \
|
|
||||||
|
|
||||||
## Install conda, opencv
|
|
||||||
|
|
||||||
RUN echo 'export PATH=/opt/conda/bin:$PATH' > /etc/profile.d/conda.sh && \
|
|
||||||
wget --quiet https://repo.continuum.io/miniconda/Miniconda2-4.3.14-Linux-x86_64.sh -O ~/miniconda.sh && \
|
|
||||||
/bin/bash ~/miniconda.sh -b -p /opt/conda && \
|
|
||||||
rm ~/miniconda.sh
|
|
||||||
|
|
||||||
ENV PATH /opt/conda/bin:$PATH
|
|
||||||
|
|
||||||
RUN conda install -c menpo opencv -y
|
|
||||||
#RUN conda install -y \
|
|
||||||
# scikit-image \
|
|
||||||
# flask \
|
|
||||||
# pillow
|
|
||||||
|
|
||||||
RUN conda install pytorch torchvision cuda80 -c soumith
|
|
||||||
|
|
||||||
## Install Universe
|
|
||||||
WORKDIR /usr/local/realenv
|
|
||||||
RUN git clone https://github.com/openai/universe.git
|
|
||||||
WORKDIR /usr/local/realenv/universe
|
|
||||||
RUN pip install -e .
|
|
||||||
|
|
||||||
## Install Realenv
|
|
||||||
WORKDIR /usr/local/realenv
|
|
||||||
RUN wget https://www.dropbox.com/s/xmhgkmhgp9dfw52/realenv.tar.gz && tar -xvzf realenv.tar.gz && rm realenv.tar.gz
|
|
||||||
WORKDIR /usr/local/realenv/realenv
|
|
||||||
RUN pip install -e .
|
|
||||||
|
|
||||||
## Set up data & model for view synthesizer
|
|
||||||
#nvidia-docker run -it -v realenv-data:/usr/local/realenv/data realenv bash
|
|
||||||
|
|
||||||
## Start VNC server
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
## Entry point
|
|
||||||
WORKDIR /usr/local/realenv/
|
|
||||||
ENTRYPOINT [ "/bin/bash", "-c" ]
|
|
||||||
|
|
||||||
|
|
@ -1,66 +0,0 @@
|
||||||
## Real Universe Environment
|
|
||||||
|
|
||||||
This folder has the source code for environment bundle, which includes view renderer, multichannel renderer and physics simulation engine
|
|
||||||
|
|
||||||
### Requirement
|
|
||||||
You need CUDA 8.0 in order to run the environment.
|
|
||||||
|
|
||||||
### Run everything in a bundle
|
|
||||||
Current trainin environment in implemented in `simple_env.py`. It is a dead simple room exploration game with negative delta distance as reward. It's default to ru with model `11HB6XZSh1Q`. We provide a sample agent `random_husky.py` to interact with this environment. To start, run the following command
|
|
||||||
```shell
|
|
||||||
source activate (py2_universe_env)
|
|
||||||
python random_husky.py
|
|
||||||
```
|
|
||||||
You can switch between agent/human mode by setting `human=True/False` when initializing environment object. You can also set `debug=True/False` to run with or without graphical interface.
|
|
||||||
|
|
||||||
### Components
|
|
||||||
The above environment has three components: view renderer, multichannel renderer and physics simulation engine. A built-in add on is a scoreboard implemented with matplotlib.
|
|
||||||
|
|
||||||
#### Test each component individually
|
|
||||||
Multichannel renderer currently only supports depth rendering. In the future we will provide surface normal, semantics and arbitrary meta information.
|
|
||||||
```shell
|
|
||||||
## Shell One
|
|
||||||
cd depth/depth_render
|
|
||||||
./depth_render --datapath ../../data -m 11HB6XZSh1Q
|
|
||||||
```
|
|
||||||
|
|
||||||
View renderer.
|
|
||||||
```shell
|
|
||||||
## Shell Two
|
|
||||||
cd render
|
|
||||||
source activate (py2_universe_env)
|
|
||||||
python show_3d2.py --datapath ../data/ --idx 10
|
|
||||||
```
|
|
||||||
|
|
||||||
Physics engine
|
|
||||||
```shell
|
|
||||||
## Shell Three
|
|
||||||
cd physics
|
|
||||||
source activate (py2_universe_env)
|
|
||||||
python render_physics.py --datapath ../data --model 11HB6XZSh1Q
|
|
||||||
```
|
|
||||||
|
|
||||||
If you want to test out how they work together in a combined way, you don't have to open up three separate terminals. Run
|
|
||||||
```shell
|
|
||||||
source acitvate (py2_universe_env)
|
|
||||||
python simple_env.py
|
|
||||||
```
|
|
||||||
|
|
||||||
You should see OpenCV windows, as well as pybullet panel pop up.
|
|
||||||
|
|
||||||
To control the object, click on pybullet panel, then use the following keys. Pybullet sends its movement to
|
|
||||||
Opengl & OpenCV for rendering.
|
|
||||||
|
|
||||||
| key | action |
|
|
||||||
| ------------- | ------------- |
|
|
||||||
| w/q | go forward |
|
|
||||||
| a | go left |
|
|
||||||
| s | go backward |
|
|
||||||
| d | go right |
|
|
||||||
| z | go upward |
|
|
||||||
| c | go downward |
|
|
||||||
| u/j | add/subtract roll |
|
|
||||||
| i/k | add/subtract pitch |
|
|
||||||
| o/l | add/subtract yaw |
|
|
||||||
|
|
||||||
Note that key w has conflict with pybullet hotkey.
|
|
||||||
|
|
@ -1,30 +0,0 @@
|
||||||
## Real Universe Viewer Renderer
|
|
||||||
|
|
||||||
Renderer for real-time visual input. Currently neural network filler is not included, rendering framerate: 30fps in single view, 12fps with five views.
|
|
||||||
|
|
||||||
Beta version renderer is implemented using OpenCV-Python. In the future we might completely switch to OpenGL to avoid the speed overhead, and reduce setup cost.
|
|
||||||
|
|
||||||
Install opencv, pytorch and others
|
|
||||||
```shell
|
|
||||||
conda install -c menpo opencv -y
|
|
||||||
conda install pytorch torchvision cuda80 -c soumith
|
|
||||||
conda install pillow
|
|
||||||
pip install zmq
|
|
||||||
```
|
|
||||||
|
|
||||||
Build cpp, cython dependencies
|
|
||||||
```shell
|
|
||||||
bash build.sh
|
|
||||||
bash build_cuda.sh
|
|
||||||
python setup.py build_ext --inplace
|
|
||||||
```
|
|
||||||
|
|
||||||
Download the necessary helper files
|
|
||||||
```shell
|
|
||||||
wget https://www.dropbox.com/s/a4tb959bbue0hap/coord.npy
|
|
||||||
```
|
|
||||||
|
|
||||||
```
|
|
||||||
source activate (py2_universe_env)
|
|
||||||
python show_3d2.py --datapath ../data/ --idx 10
|
|
||||||
```
|
|
||||||
|
|
@ -1,198 +0,0 @@
|
||||||
import time, random
|
|
||||||
import math
|
|
||||||
import collections
|
|
||||||
from collections import deque
|
|
||||||
from matplotlib.font_manager import FontProperties
|
|
||||||
import matplotlib.gridspec as gridspec
|
|
||||||
import matplotlib.patches as mpatches
|
|
||||||
from matplotlib import pyplot as plt
|
|
||||||
from multiprocessing import Process, Pipe
|
|
||||||
#import gobject
|
|
||||||
|
|
||||||
class SmoothList(collections.MutableSequence):
|
|
||||||
max_entries = 200
|
|
||||||
def __init__(self):
|
|
||||||
self.list = []
|
|
||||||
|
|
||||||
def __getitem__(self, idx):
|
|
||||||
scale = 1
|
|
||||||
if len(self.list) > SmoothList.max_entries:
|
|
||||||
scale = len(self.list) / float(SmoothList.max_entries)
|
|
||||||
return self.list[int((idx + 1) * scale) - 1]
|
|
||||||
|
|
||||||
def __len__(self):
|
|
||||||
return min(len(self.list), SmoothList.max_entries)
|
|
||||||
|
|
||||||
def append(self, elem):
|
|
||||||
'''
|
|
||||||
if len(self.list) >= SmoothList.max_entries:
|
|
||||||
newlist = []
|
|
||||||
i = 0
|
|
||||||
while i < len(self.list):
|
|
||||||
newlist.append((self.list[i] + self.list[i + 1]) / 2.0)
|
|
||||||
i = i + 2
|
|
||||||
self.list = newlist
|
|
||||||
'''
|
|
||||||
self.list.append(elem)
|
|
||||||
|
|
||||||
def __delitem__(self, i): del self.list[i]
|
|
||||||
|
|
||||||
def __setitem__(self, i, v):
|
|
||||||
self.check(v)
|
|
||||||
self.list[i] = v
|
|
||||||
|
|
||||||
def insert(self, i, v):
|
|
||||||
self.check(v)
|
|
||||||
self.list.insert(i, v)
|
|
||||||
|
|
||||||
|
|
||||||
class RealtimePlot:
|
|
||||||
def __init__(self, axes, max_entries = 100, full = False):
|
|
||||||
self.axes = axes
|
|
||||||
self.max_entries = max_entries
|
|
||||||
if not full:
|
|
||||||
self.axis_x = deque(maxlen=max_entries)
|
|
||||||
self.axis_y = deque(maxlen=max_entries)
|
|
||||||
self.lineplot, = axes.plot([], [], "bo-")
|
|
||||||
else:
|
|
||||||
self.axis_x = SmoothList()
|
|
||||||
self.axis_y = SmoothList()
|
|
||||||
self.lineplot, = axes.plot([], [], "ro-")
|
|
||||||
|
|
||||||
self.axes.set_autoscaley_on(True)
|
|
||||||
|
|
||||||
def add(self, x, y):
|
|
||||||
self.axis_x.append(x)
|
|
||||||
self.axis_y.append(y)
|
|
||||||
self.lineplot.set_data(self.axis_x, self.axis_y)
|
|
||||||
self.axes.set_xlim(self.axis_x[0], self.axis_x[-1] + 1e-15)
|
|
||||||
self.axes.relim(); self.axes.autoscale_view() # rescale the y-axis
|
|
||||||
|
|
||||||
def animate(self, figure, callback, interval = 50):
|
|
||||||
import matplotlib.animation as animation
|
|
||||||
def wrapper(frame_index):
|
|
||||||
self.add(*callback(frame_index))
|
|
||||||
self.axes.relim(); self.axes.autoscale_view() # rescale the y-axis
|
|
||||||
return self.lineplot
|
|
||||||
animation.FuncAnimation(figure, wrapper, interval=interval)
|
|
||||||
|
|
||||||
|
|
||||||
class RewardDisplayer:
|
|
||||||
def __init__(self):
|
|
||||||
self.all_rewards = []
|
|
||||||
self.factor = 3
|
|
||||||
font0 = FontProperties()
|
|
||||||
gs = gridspec.GridSpec(12, 3)
|
|
||||||
|
|
||||||
fig = plt.figure(figsize=(10.25, 8))
|
|
||||||
|
|
||||||
self.axes_text = plt.subplot(gs[:2, :], facecolor='gainsboro')
|
|
||||||
self.axes_full = plt.subplot(gs[2:9, :], facecolor='gainsboro')
|
|
||||||
self.axes_real = plt.subplot(gs[9:12, :], facecolor='gainsboro')
|
|
||||||
|
|
||||||
self.axes_text.set_xlim(0, 10)
|
|
||||||
self.axes_text.set_ylim(0, 10)
|
|
||||||
|
|
||||||
#ax1.set_title('title1', color='c', rotation='vertical',x=-0.1,y=0.5)
|
|
||||||
self.axes_full.legend(loc='upper left', handles=[mpatches.Patch(color='red', label='Score - Time Plot')], prop={'size': 13})
|
|
||||||
self.axes_real.legend(loc='upper left', handles=[mpatches.Patch(color='blue', label='Reward - Time Plot')], prop={'size': 13})
|
|
||||||
|
|
||||||
self.font = font0.copy()
|
|
||||||
self.font.set_family('sans caption')
|
|
||||||
self.font.set_weight('semibold')
|
|
||||||
self.alignment = {'horizontalalignment': 'left', 'verticalalignment': 'baseline'}
|
|
||||||
self.axes_text.axis('off')
|
|
||||||
|
|
||||||
self.display_full = RealtimePlot(self.axes_full, full = True)
|
|
||||||
self.display_real = RealtimePlot(self.axes_real)
|
|
||||||
|
|
||||||
self.txt_reward = None
|
|
||||||
self.txt_totalr = None
|
|
||||||
self.txt_time = None
|
|
||||||
|
|
||||||
self.axes_text.text(0, 9, 'Reward:', fontproperties=self.font, size = 15, **self.alignment)
|
|
||||||
self.axes_text.text(4.5, 9, 'Score:', fontproperties=self.font, size = 15, **self.alignment)
|
|
||||||
self.axes_text.text(0, 3, 'Time:', fontproperties=self.font, size = 15, **self.alignment)
|
|
||||||
self.score = 0
|
|
||||||
|
|
||||||
self.start = time.time()
|
|
||||||
|
|
||||||
def _smooth(self):
|
|
||||||
return self.all_rewards
|
|
||||||
|
|
||||||
def reset(self):
|
|
||||||
self.score = 0
|
|
||||||
|
|
||||||
def add_reward(self, reward):
|
|
||||||
self.score = self.score + reward
|
|
||||||
cur_time = time.time() - self.start
|
|
||||||
self.display_real.add(cur_time, reward)
|
|
||||||
self.display_full.add(cur_time, self.score)
|
|
||||||
if self.txt_reward:
|
|
||||||
self.txt_reward.remove()
|
|
||||||
if self.txt_totalr:
|
|
||||||
self.txt_totalr.remove()
|
|
||||||
if self.txt_time:
|
|
||||||
self.txt_time.remove()
|
|
||||||
self.txt_reward = self.axes_text.text(2, 9, '%.2f' % reward, fontproperties=self.font, size = 30, **self.alignment)
|
|
||||||
self.txt_totalr = self.axes_text.text(6.5, 9, '%.2f' % self.score, fontproperties=self.font, size = 30, **self.alignment)
|
|
||||||
self.txt_time = self.axes_text.text(2, 3, '%.2f' % cur_time, fontproperties=self.font, size = 30, **self.alignment)
|
|
||||||
plt.pause(0.0001)
|
|
||||||
|
|
||||||
def terminate(self):
|
|
||||||
plt.close('all')
|
|
||||||
|
|
||||||
def poll_draw(self):
|
|
||||||
while 1:
|
|
||||||
#print("polling")
|
|
||||||
if not self.pipe.poll():
|
|
||||||
break
|
|
||||||
command = self.pipe.recv()
|
|
||||||
#print("received reward", command)
|
|
||||||
if command is None:
|
|
||||||
self.terminate()
|
|
||||||
return False
|
|
||||||
else:
|
|
||||||
self.add_reward(command)
|
|
||||||
time.sleep(0.01)
|
|
||||||
#self.fig.canvas.draw()
|
|
||||||
return True
|
|
||||||
|
|
||||||
def __call__(self, pipe):
|
|
||||||
print('Starting plotter...')
|
|
||||||
|
|
||||||
self.pipe = pipe
|
|
||||||
#self.fig, self.ax = plt.subplots()
|
|
||||||
#self.gid = gobject.timeout_add(1000, )
|
|
||||||
self.poll_draw()
|
|
||||||
print('...done')
|
|
||||||
#plt.show()
|
|
||||||
|
|
||||||
class MPRewardDisplayer(object):
|
|
||||||
def __init__(self):
|
|
||||||
self.plot_pipe, plotter_pipe = Pipe()
|
|
||||||
self.plotter = RewardDisplayer()
|
|
||||||
self.plot_process = Process(target=self.plotter,
|
|
||||||
args=(plotter_pipe,))
|
|
||||||
self.plot_process.daemon = True
|
|
||||||
self.plot_process.start()
|
|
||||||
|
|
||||||
def add_reward(self, reward, finished=False):
|
|
||||||
send = self.plot_pipe.send
|
|
||||||
if finished:
|
|
||||||
send(None)
|
|
||||||
else:
|
|
||||||
send(reward)
|
|
||||||
|
|
||||||
def reset(self):
|
|
||||||
return
|
|
||||||
|
|
||||||
def main():
|
|
||||||
r_displayer = MPRewardDisplayer()
|
|
||||||
for i in range(10000):
|
|
||||||
num = random.random() * 100 - 30
|
|
||||||
r_displayer.add_reward(num)
|
|
||||||
if i % 40 == 0:
|
|
||||||
r_displayer.reset()
|
|
||||||
|
|
||||||
if __name__ == "__main__": main()
|
|
||||||
Binary file not shown.
|
After Width: | Height: | Size: 3.5 MiB |
Loading…
Reference in New Issue