I just found this github from ETH Z. Not surprising that they have some of the most relevant datasets I’ve seen, pertaining to making proprioceptive autonomous systems. I came across their Autonomous Systems Labs dataset site.
One of the projects, panoptic mapping, is pretty much the panoptic segmentation from earlier research, combined with volumetric point clouds. “A flexible submap-based framework towards spatio-temporally consistent volumetric mapping and scene understanding.”
Like a SLAM part 2.1,
Some topics here for general vibes, and a robotics site’s article on them.
Of course having sensors telling you if you’ve fallen over are useful. Of course.
The IMU just gives you the relative axes on the robot, and that can feed back to a control algorithm which uses that info to influence behaviour.
Here’s a useful Q that made me realise I must get an IMU running, perhaps. https://robotics.stackexchange.com/questions/21279/do-imu-have-value-in-slam
After reading up on IMUs, you get 3 axes: accelerometer, 6 axes: + gyroscope, 9 axes: + magnetometer. And some 10 axes ones, if it’s fancy, and has a thermometer to correct inaccuracies, etc.
6 axes gives you relative positions, 9 axes gives you absolute positions.
I happen to have a 6 axis one, from Aliexpress, from years ago. Never used it, but now I have a reason. It’s labelled GY-521. Here’s a video tutorial on putting it all together, with the tutorial link for reading.
“the 6-DoF, which was used to determine the linear velocity, angular velocity, position and orientation.” – this paper, “Pose Estimation of a Mobile Robot Based on Fusion of IMU Data and Vision Data Using an Extended Kalman Filter”
You need to take these folders from the github link.
and put them in your Arduino libs folder
The github also has some code for Raspberry Pi, which I might get to next. Badabing badaboom, it actually worked first time. ( I touched the USB cable though, and needed to restart it, but that seems like something that can be prevented).
Ok so accelerometer x/y/z, temperature nice, gyroscope x/y/z
I watched these numbers as I moved it around, and at 9600 baud, it’s really slow. It’s not going to help for real time decision making.
Maybe we’ll come back to IMUs later. A bit complicated to visualise and make sense of the data, but with a visualisation, it would make odometry SLAM methods more robust.
Continuing from our early notes on SLAM algorithms (Simultaneous Localisation and Mapping), and the similar but not as map-making, DSO algorithm, I came across a good project (“From cups to consciousness“) and article that reminded me that mapping the environment or at least having some sense of depth, will be pretty crucial.
At the moment I’ve just got to the point of thinking to train a CNN on simulation data, and so there should also be some positioning of the robot as a model in it’s own virtual world. So it’s probably best to reexamine what’s already out there. Visual odometry. Optical Flow.
I found a good paper summarizing 2019 options. The author’s github has some interesting scripts that might be useful. It reminds me that I should probably be using ROS and gazebo, to some extent. The conclusion was roughly that Google Cartographer or GMapping (Open SLAM) are generally beating some other ones, Karto, Hector. Seems like SLAM code is all a few years old. Google Cartographer had some support for ‘lifelong mapping‘, which sounded interesting. The robot goes around updating its map, a bit. It reminds me I saw ‘PonderNet‘ today, fresh from DeepMind, which from a quick look is, more or less, about like scaling your workload down to your input size.
Anyway, we are mostly interested in Monocular SLAM. So none of this applies, probably. I’m mostly interested at the moment, in using some prefab scenes like the AI2Thor environment in the Cups-RL example, and making some sort of SLAM in simulation.
Also interesting is RATSLAM and the recent update: LatentSLAM – The authors of this site, The Smart Robot, got my attention because of the CCNs. Cortical column networks.
LatentSLAM: https://arxiv.org/pdf/2105.03265.pdf
“A common shortcoming of RatSLAM is its sensitivity
to perceptual aliasing, in part due to the reliance on
an engineered visual processing pipeline. We aim to reduce
the effects of perceptual aliasing by replacing the perception
module by a learned dynamics model. We create a generative
model that is able to encode sensory observations into a
latent code that can be used as a replacement to the visual
input of the RatSLAM system”
Interesting, “The robot performed 1,143 delivery tasks to 11 different locations with only one delivery failure (from which it recovered), traveled a total distance of more than 40 km over 37 hours of active operation, and recharged autonomously a total of 23 times.“
I think DSO might be a good option, or the closed loop, LDSO, look like the most straight-forward, maybe.
After a weekend away with a computer vision professional, I found out about COLMAP, a structure from movement suite.
I saw a few more recent projects too, e.g. NeuralRecon, and
ooh, here’s a recent facebook one that sounds like it might work!
Consistent Depth … eh, their google colab is totally broken.
Anyhow, LDSO. Let’s try it.
In file included from /dmc/LDSO/include/internal/OptimizationBackend/AccumulatedTopHessian.h:10:0,
from /dmc/LDSO/include/internal/OptimizationBackend/EnergyFunctional.h:9,
from /dmc/LDSO/include/frontend/FeatureMatcher.h:10,
from /dmc/LDSO/include/frontend/FullSystem.h:18,
from /dmc/LDSO/src/Map.cc:4:
/dmc/LDSO/include/internal/OptimizationBackend/MatrixAccumulators.h:8:10: fatal error: SSE2NEON.h: No such file or directory
#include "SSE2NEON.h"
^~~~
compilation terminated.
src/CMakeFiles/ldso.dir/build.make:182: recipe for target 'src/CMakeFiles/ldso.dir/Map.cc.o' failed
make[2]: *** [src/CMakeFiles/ldso.dir/Map.cc.o] Error 1
make[2]: *** Waiting for unfinished jobs….
CMakeFiles/Makefile2:85: recipe for target 'src/CMakeFiles/ldso.dir/all' failed
make[1]: *** [src/CMakeFiles/ldso.dir/all] Error 2
Makefile:83: recipe for target 'all' failed
make: *** [all] Error 2
Ok maybe not.
There’s a paper here reviewing ORBSLAM3 and LDSO, and they encounter lots of issues. But it’s a good paper for an overview of how the algorithms work. We want a point cloud so we can find the closest points, and not walk into them.
Calibration is an issue, rolling shutter cameras are an issue, IMU data can’t be synced meaningfully, it’s a bit of a mess, really.
Also, reports that ORB-SLAM2 was only getting 5 fps on a raspberry pi, I got smart, and looked for something specifically for the jetson. I found a depth CNN for monocular vision on the forum, amazing.
Then this is a COLMAP structure-from-motion option, and some more depth stuff… and more making it high res…
Ok so after much fussing about, I found just what we need. I had an old copy of jetson-containers, and the slam code was added just 6 months ago. I might want to try the noetic one (ROS2) instead of ROS, good old ROS.
git clone https://github.com/dusty-nv/jetson-containers.git cd jetson-containers chicken@jetson:~/jetson-containers$ ./scripts/docker_build_ros.sh --distro melodic --with-slam Successfully built 2eb4d9c158b0 Successfully tagged ros:melodic-ros-base-l4t-r32.5.0 chicken@jetson:~/jetson-containers$ ./scripts/docker_test_ros.sh melodic reading L4T version from /etc/nv_tegra_release L4T BSP Version: L4T R32.5.0 l4t-base image: nvcr.io/nvidia/l4t-base:r32.5.0 testing container ros:melodic-ros-base-l4t-r32.5.0 => ros_version xhost: unable to open display "" xauth: file /tmp/.docker.xauth does not exist sourcing /opt/ros/melodic/setup.bash ROS_ROOT /opt/ros/melodic/share/ros ROS_DISTRO melodic getting ROS version - melodic done testing container ros:melodic-ros-base-l4t-r32.5.0 => ros_version
Well other than the X display, looking good.
Maybe I should just plug in a monitor. Ideally I wouldn’t have to, though. I used GStreamer the other time. Maybe we do that again.
This looks good too… https://github.com/dusty-nv/ros_deep_learning but let’s stay focused. I’m also thinking maybe we upgrade early, to noetic. Ugh it looks like a whole new bunch of build tools and things to relearn. I’m sure it’s amazing. Let’s do ROS1, for now.
Let’s try build that FCNN one again.
CMake Error at tx2_fcnn_node/Thirdparty/fcrn-inference/CMakeLists.txt:121 (find_package):
By not providing "FindOpenCV.cmake" in CMAKE_MODULE_PATH this project has
asked CMake to find a package configuration file provided by "OpenCV", but
CMake did not find one.
Could not find a package configuration file provided by "OpenCV" (requested
version 3.0.0) with any of the following names:
OpenCVConfig.cmake
opencv-config.cmake
Add the installation prefix of "OpenCV" to CMAKE_PREFIX_PATH or set
"OpenCV_DIR" to a directory containing one of the above files. If "OpenCV"
provides a separate development package or SDK, be sure it has been
installed.
-- Configuring incomplete, errors occurred!
Ok hold on…
Builds additional container with VSLAM packages, including ORBSLAM2, RTABMAP, ZED, and Realsense. This only applies to foxy and galactic and implies --with-pytorch as these containers use PyTorch."
Ok so not melodic then. ROS2 it is…
./scripts/docker_build_ros.sh --distro foxy --with-slam
Ok that hangs when it starts building the slam bits. Luckily, someone’s raised the bug, and though it’s not fixed, Dusty does have a docker already compiled.
sudo docker pull dustynv/ros:foxy-slam-l4t-r32.6.1
I started it up with
docker run -it --runtime nvidia --rm --network host --privileged --device /dev/video0 -v /home/chicken/:/dmc dustynv/ros:foxy-slam-l4t-r32.6.1
So, after some digging, I think we can solve the X problem (i.e. where are we going to see this alleged SLAMming occur?) with an RTSP server. Previously I used GStreamer to send RTP over UDP. But this makes more sense, to run a server on the Jetson. There’s a plugin for GStreamer, so I’m trying to get the ‘dev’ version, so I can compile the test-launch.c program.
apt-get install libgstrtspserver-1.0-dev Reading package lists... Done Building dependency tree Reading state information... Done libgstrtspserver-1.0-dev is already the newest version (1.14.5-0ubuntu1~18.04.1). ok... git clone https://github.com/GStreamer/gst-rtsp-server.git root@jetson:/opt/gst-rtsp-server/examples# gcc test-launch.c -o test-launch $(pkg-config --cflags --libs gstreamer-1.0 gstreamer-rtsp-server-1.0) test-launch.c: In function ‘main’: test-launch.c:77:3: warning: implicit declaration of function ‘gst_rtsp_media_factory_set_enable_rtcp’; did you mean ‘gst_rtsp_media_factory_set_latency’? [-Wimplicit-function-declaration] gst_rtsp_media_factory_set_enable_rtcp (factory, !disable_rtcp); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ gst_rtsp_media_factory_set_latency /tmp/ccC1QgPA.o: In function `main': test-launch.c:(.text+0x154): undefined reference to `gst_rtsp_media_factory_set_enable_rtcp' collect2: error: ld returned 1 exit status gst_rtsp_media_factory_set_enable_rtcp
Ok wait let’s reinstall gstreamer.
apt-get install libgstreamer1.0-dev libgstreamer-plugins-base1.0-dev libgstreamer-plugins-bad1.0-dev gstreamer1.0-plugins-base gstreamer1.0-plugins-good gstreamer1.0-plugins-bad gstreamer1.0-plugins-ugly gstreamer1.0-libav gstreamer1.0-doc gstreamer1.0-tools gstreamer1.0-x gstreamer1.0-alsa gstreamer1.0-gl gstreamer1.0-gtk3 gstreamer1.0-qt5 gstreamer1.0-pulseaudio error... Unpacking libgstreamer-plugins-bad1.0-dev:arm64 (1.14.5-0ubuntu1~18.04.1) ... Errors were encountered while processing: /tmp/apt-dpkg-install-Ec7eDq/62-libopencv-dev_3.2.0+dfsg-4ubuntu0.1_arm64.deb E: Sub-process /usr/bin/dpkg returned an error code (1) Ok then leave out that one... apt --fix-broken install and that fails on Errors were encountered while processing: /var/cache/apt/archives/libopencv-dev_3.2.0+dfsg-4ubuntu0.1_arm64.deb
It’s like a sign of being a good programmer, to solve this stuff. But damn. Every time. Suggestions continue, in the forums of those who came before. Let’s reload the docker.
root@jetson:/opt/gst-rtsp-server/examples# pkg-config --cflags --libs gstreamer-1.0 -pthread -I/usr/include/gstreamer-1.0 -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include -lgstreamer-1.0 -lgobject-2.0 -lglib-2.0 root@jetson:/opt/gst-rtsp-server/examples# pkg-config --cflags --libs gstreamer-rtsp-server-1.0 -pthread -I/usr/include/gstreamer-1.0 -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include -lgstrtspserver-1.0 -lgstbase-1.0 -lgstreamer-1.0 -lgobject-2.0 -lglib-2.0
Ok I took a break and got lucky. The test-launch.c code is different from what the admin had.
Let’s diff it and see what changed…
#define DEFAULT_DISABLE_RTCP FALSE
from
static gboolean disable_rtcp = DEFAULT_DISABLE_RTCP;
{"disable-rtcp", '\0', 0, G_OPTION_ARG_NONE, &disable_rtcp,
"Whether RTCP should be disabled (default false)", NULL},
from
gst_rtsp_media_factory_set_enable_rtcp (factory, !disable_rtcp);
so now this works (to compile).
gcc test.c -o test $(pkg-config --cflags --libs gstreamer-1.0 gstreamer-rtsp-server-1.0)
ok so back to it…
root@jetson:/opt/gst-rtsp-server/examples# ./test-launch "videotestsrc ! nvvidconv ! nvv4l2h264enc ! h264parse ! rtph264pay name=pay0 pt=96"
stream ready at rtsp://127.0.0.1:8554/test
So apparently now I can run this in VLC… when I open
rtsp://<jetson-ip>:8554/test
Um is that meant to happen?…. Yes!
Ok next, we want to see SLAM stuff happening. So, ideally, a video feed of the desktop, or something like that.
So here are the links I have open. Maybe I get back to them later. Need to get back to ORBSLAM2 first, and see where we’re at, and what we need. Not quite /dev/video0 to PC client. More like, ORBSLAM2 to dev/video0 to PC client. Or full screen desktop. One way or another.
Here's a cool pdf with some instructions, from doodlelabs, and their accompanying pdf about video streaming codecs and such.
Also, gotta check out this whole related thing. and the depthnet example, whose documentation is here.
Ok, so carrying on.
I try again today, and whereas yesterday we had
libgstrtspserver-1.0-dev is already the newest version (1.14.5-0ubuntu1~18.04.1).
Today we have
E: Unable to locate package libgstrtspserver-1.0-dev
E: Couldn't find any package by glob 'libgstrtspserver-1.0-dev'
E: Couldn't find any package by regex 'libgstrtspserver-1.0-dev'
Did I maybe compile it outside of the docker? Hmm maybe. Why can’t I find it though? Let’s try the obvious… but also why does this take so long? Network is unreachable. Network is unreachable. Where have all the mirrors gone?
apt-get updateOk so long story short, I made another docker file. to get gstreamer installed. It mostly required adding a key for the kitware apt repo.
./test "videotestsrc ! nvvidconv ! nvv4l2h264enc ! h264parse ! rtph264pay name=pay0 pt=96"
Ok and on my linux box now, so I’ll connect to it.
sudo apt install vlc vlc rtsp://192.168.101.115:8554/Test
K all good… So let’s get the camera output next?
sheesh it’s not obvious.
I’m just making a note of this.
Since 1.14, the use of libv4l2 has been disabled due to major bugs in the emulation layer. To enable usage of this library, set the environment variable GST_V4L2_USE_LIBV4L2=1
but it doesn’t want to work anyway. Ok RTSP is almost a dead end.
I might attach a CSI camera instead of V4L2 (USB camera) maybe. Seems less troublesome. But yeah let’s take a break. Let’s get back to depthnet and ROS2 and ORB-SLAM2, etc.
depthnet: error while loading shared libraries: /usr/lib/aarch64-linux-gnu/libnvinfer.so.8: file too short
Ok, let’s try ROS2.
(Sorry, this was supposed to be about SLAM, right?)
As a follow-up for this post…
I asked about mapping two argus (NVIDIA’s CSI camera driver) node topics, in order to fool their stereo_proc, on the github issues. No replies, cause they probably want to sell expensive stereo cameras, and I am asking how to do it with $15 Chinese cameras.
I looked at DustyNV’s Mono depth. Probably not going to work. It seems like you can get a good depth estimate for things in the scene, but everything around the edges reads as ‘close’. Not sure that’s practical enough for depth.
I looked at the NVIDIA DNN depth. Needs proper stereo cameras.
I looked at NVIDIA VPI Stereo Disparity pipeline It is the most promising yet, but the input either needs to come from calibrated cameras, or needs to be rectified on-the-fly using OpenCV. This seems like it might be possible in python, but it is not obvious yet how to do it in C++, which the rest of the code is in.
I tried calibration.
I removed the USB cameras.
I attached two RPi 2.1 CSI cameras, from older projects. Deep dived into ISAAC_ROS suite. Left ROS2 alone for a bit because it is just getting in the way. The one camera sensor had fuzzy lines going across, horizontally, occasionally, and calibration results were poor, fuzzy. Decided I needed new cameras.
IMX-219 was used by the github author, and I even printed out half of the holder, to hold the cameras 8cm apart.
I tried calibration using the ROS2 cameracalibrator, which is a wrapper for a opencv call, after starting up the camera driver node, inside the isaac ros docker.
ros2 run isaac_ros_argus_camera_mono isaac_ros_argus_camera_mono --ros-args -p device:=0 -p sensor:=4 -p output_encoding:="mono8"
(This publishes mono camera feed to topic /image_raw)
ros2 run camera_calibration cameracalibrator \
--size=8x6 \
--square=0.063 \
--approximate=0.3 \
--no-service-check \
--ros-args --remap /image:=/image_raw
(Because of bug, also sometimes need to remove –ros-args –remap )
OpenCV was able to calibrate, via the ROS2 application, in both cases. So maybe I should just grab the outputs from that. We’ll do that again, now. But I think I need to print out a chessboard and just see how that goes first.
I couldn’t get more than a couple of matches using pictures of the chessboard on the screen, even with binary thresholding, in the author’s calibration notebooks.
Here’s what the NVIDIA VPI 1.2’s samples drew, for my chess boards:
Camera calibration seems to be a serious problem, in the IOT camera world. I want something approximating depth, and it is turning out that there’s some math involved.
Learning about epipolar geometry was not something I planned to do for this.
But this is like a major showstopper, so either, I must rectify, in real time, or I must calibrate.
We’re not going to SLAM without it.
The pertinent forum post is here.
“The reason for the noisy result is that the VPI algorithm expects the rectified image pairs as input. Please do the rectification first and then feed the rectified images into the stereo disparity estimator.”
So can we use this info? The nvidia post references this code below as the solution, perhaps, within the context of the code below. Let’s run it on the chessboard?
p1fNew = p1f.reshape((p1f.shape[0] * 2, 1))
p2fNew = p2f.reshape((p2f.shape[0] * 2, 1))
retBool ,rectmat1, rectmat2 = cv2.stereoRectifyUncalibrated(p1fNew,p2fNew,fundmat,imgsize)import numpy as np
import cv2
import vpi
left = cv2.imread('left.png')
right = cv2.imread('right.png')
left_gray = cv2.cvtColor(left, cv2.COLOR_BGR2GRAY)
right_gray = cv2.cvtColor(right, cv2.COLOR_BGR2GRAY)
detector = cv2.xfeatures2d.SIFT_create()
kp1, desc1 = detector.detectAndCompute(left_gray, None)
kp2, desc2 = detector.detectAndCompute(right_gray, None)
bf = cv2.BFMatcher()
matches = bf.knnMatch(desc1, desc2, k=2)
ratio = 0.75
good, mkp1, mkp2 = [], [], []
for m in matches:
if m[0].distance < m[1].distance * ratio:
m = m[0]
good.append(m)
mkp1.append( kp1[m.queryIdx] )
mkp2.append( kp2[m.trainIdx] )
p1 = np.float32([kp.pt for kp in mkp1])
p2 = np.float32([kp.pt for kp in mkp2])
H, status = cv2.findHomography(p1, p2, cv2.RANSAC, 20)
print('%d / %d inliers/matched' % (np.sum(status), len(status)))
status = np.array(status, dtype=bool)
p1f = p1[status.view(np.ndarray).ravel()==1,:] #Remove Outliers
p2f = p2[status.view(np.ndarray).ravel()==1,:] #Remove Outliers
goodf = [good[i] for i in range(len(status)) if status.view(np.ndarray).ravel()[i]==1]
fundmat, mask = cv2.findFundamentalMat(p1f, p2f, cv2.RANSAC, 3, 0.99,)
#img = cv2.drawMatches(left_gray, kp1, right_gray, kp2, good, None, None, flags=2)
#cv2.imshow('Default Matches', img)
#img = cv2.drawMatches(left_gray, kp1, right_gray, kp2, goodf, None, None, flags=2)
#cv2.imshow('Filtered Matches', img)
#cv2.waitKey(0)
retBool, H1, H2 = cv2.stereoRectifyUncalibrated(p1f, p2f, fundmat, (left.shape[1],left.shape[0]))
with vpi.Backend.CUDA:
left = vpi.asimage(left).convert(vpi.Format.NV12_ER)
left = left.perspwarp(H1)
left = left.convert(vpi.Format.RGB8)
right = vpi.asimage(right).convert(vpi.Format.NV12_ER)
right = right.perspwarp(H2)
right = right.convert(vpi.Format.RGB8)
#cv2.imshow('Left', left.cpu())
#cv2.imshow('Right', right.cpu())
#cv2.waitKey(0)
cv2.imwrite('rectified_left.png', left.cpu())
cv2.imwrite('rectified_right.png', right.cpu())
This post follows the ‘Finding where we left off’ post, focused on locomotion sim2real. In that post I tried to generalise and smooth the leg angle servo movements in their -PI/2 to PI/2 range.
I will likely try extracting kMPs, before this is all over, which from a skim read, and look at the pictures, are like, just taking a single slice of the wave data, and repeating that. Or, taking consecutive periodic waves, and extracting the average / normalized movement from them.
https://becominghuman.ai/introduction-to-timeseries-analysis-using-python-numpy-only-3a7c980231af
It’s now December 6th 2021, as I continue here…
This paper is very relevant, “Realizing Learned Quadruped Locomotion Behaviors through Kinematic Motion Primitives”
Some Indian PhDs have summed up the process. Unfortunately I’m not quite on the exact same page. I understand the pictures, haha.
Here’s where this picture comes from, which is useful for explaining what I need to do: (Short paper)
In 2014, also, same thing, Kinematic primitives for walking and trotting gaits of a quadruped robot with compliant legs
They just used PCA. (Principal Component Analysis). That’s like a common ML toolkit thing.
See now this is where they lose me: “The covariance matrix of the normalized dataset”. Come on guys. Throw us a bone.
I found this picture, which is worth 1000 words, in the discussion on stackexchange about PCA and SVD:
So, I’m not quite ready for PCA. That is two dimensions, anyway. Oh right, so I need to add a ‘time’ dimension. numpy’s expand_dims?
I played around with Codex, to assist with finding the peaks, and to find the period length.
And I separated them out to different plots… and got the peaks matching once I passed in ( , distance=80).
I had to install these, and restart the Jupyter kernel (and I think close and restart the Chrome tab.) in order to get some matplotlib widgets.
Error message: Jupyter Lab: Error displaying widget: model not found !pip3 install --upgrade jupyterlab ipympl %matplotlib widget
I started on a slider widget to draw a vertical line on top of the leg data, but I need to fix the refresh issue. Anyhow, it’s not quite what i want. What do I want?
So, I want the kMPs. The kMPs are like, a gif of a basic action, e.g. robot taking a full step forward, on all legs, which we can run once, twice, etc.
We can ‘average’ or ‘normalise’ or ‘phase’ the waves, and assume that gives us a decent average step forward.
I think there’s enough variation in this silly simulation walk that we should start with just the simplest, best single wave.
But since they ran PCA, let’s run it to see what it does for the data. We have a single integer value, which is 1D. To make it 2D, so we can run PCA on it… we add a time dimension?
But also, so I measured the period a few programs up, to be
67 steps (front right),
40 steps (front left),
59 steps (back right),
42 steps (back left).
So, as a starting point, it would be nice to be as close to servos at 90 degrees as possible. If I iterate the values, and track the lowest sum diff, yeah… is that it? I’m looking at this link at SO.
Ideally I could visualise the options..
Repeating a slice. Averaging the slices.
Ok, so I need a start index, end index, to index a range.
After some investigation, the index where the legs are closest to 90 degrees, is at 1739
Computer Enhance
So that’s kinda close to our ideal kMPs, from about 1739 to about 1870 maybe, but clearly the data is messy. Could be tweaked. Wavetable editor, basically.
Alright, let’s make an app. We can try run a Flask server on the Pi, with Javascript front end using chart.js.
pip3 install flask
Save the test web app, kmpapp.py
from flask import Flask
app = Flask(__name__)
@app.route('/')
def index():
return 'Hello world'
if __name__ == '__main__':
app.run(debug=True, host='0.0.0.0')
python3 kmpapp.py
Ok good start. We need to get the x and y data into JSON so Javascript can plot it, in chart.js
That’s looking good. Maybe too many points. Ok, so I want to edit, save, and run the KMPs on the robot.
Well it took a day but it’s working, and is pretty cool. Used smooth.js to allow smoother transitions. Took another day to add save and load features.
I’ll upload this to the project repo.
Many improvements added. Will update repo again closer to MFRU.
We’ve got an egg in the gym environment now, so we need to collect some data for training the robot to go pick up an egg.
I’m going to have it save the rgba, depth and segmentation images to disk for Unet training. I left out the depth image for now. The pictures don’t look useful. But some papers are using the depth, so I might reconsider. Some weed bot paper uses 14-channel images with all sorts of extra domain specific data relevant to plants.
I wrote some code to take pics if the egg was in the viewport, and it took 1000 rgb and segmentation pictures or so. I need to change the colour of the egg for sure, and probably randomize all the textures a bit. But main thing is probably to make the segmentation layers with pixel colours 0,1,2, etc. so that it detects the egg and not so much the link in the foreground.
So sigmoid to softmax and so on. Switching to multi-class also begs the question whether to switch to Pytorch & COCO panoptic segmentation based training. It will have to happen eventually, as I think all of the fastest implementations are currently in Pytorch and COCO based. Keras might work fine for multiclass or multiple binary classification, but it’s sort of the beginning attempt. Something that works. More proof of concept than final implementation. But I think Keras will be good enough for these in-simulation 256×256 images.
Regarding multi-class segmentation, karolzak says “it’s just a matter of changing num_classes argument and you would need to shape your mask in a different way (layer per class??), so for multiclass segmentation you would need a mask of shape (width, height, num_classes)“
I’ll keep logging my debugging though, if you’re reading this.
So I ran segmask_linkindex.py to see what it does, and how to get more useful data. The code is not running because the segmentation image actually has an array of arrays. I presume it’s a numpy array. I think it must be the rows and columns. So anyway I added a second layer to the loop, and output the pixel values, and when I ran it in the one mode:
-1 -1 -1 83886081 obUid= 1 linkIndex= 4 83886081 obUid= 1 linkIndex= 4 1 obUid= 1 linkIndex= -1 1 obUid= 1 linkIndex= -1 16777217 obUid= 1 linkIndex= 0 16777217 obUid= 1 linkIndex= 0 -1 -1 -1 And in the other mode -1 -1 -1 1 obUid= 1 linkIndex= -1 1 obUid= 1 linkIndex= -1 1 obUid= 1 linkIndex= -1 -1 -1 -1
Ok I see. Hmm. Well the important thing is that this code is indeed for extracting the pixel information. I think it’s going to be best for the segmentation to use the simpler segmentation mask that doesn’t track the link info. Ok so I used that code from the guy’s thesis project, and that was interpolating the numbers. When I look at the unique elements of the mask without interpolation, I’ve got…
[ 0 2 255] [ 0 2 255] [ 0 2 255] [ 0 2 255] [ 0 2 255] [ 0 1 2 255] [ 0 1 2 255] [ 0 2 255] [ 0 2 255] Ok, so I think: 255 is the sky 0 is the plane 2 is the robotable 1 is the egg
So yeah, I was just confused because the segmentation masks were all black and white. But if you look closely with a pixel picker tool, the pixel values are (0,0,0), (1,1,1), (2,2,2), (255,255,255), so I just couldn’t see it.
The interpolation kinda helps, to be honest.
As per OpenAI’s domain randomization helping with Sim2Real, we want to randomize some textures and some other things like that. I also want to throw in some random chickens. Maybe some cats and dogs. I’m afraid of transfer learning, at this stage, because a lot of it has to do with changing the structure of the final layer of the neural network, and that might be tough. Let’s just do chickens and eggs.
An excerpt from OpenAI:
Both techniques increase the computational requirements: dynamics randomization slows training down by a factor of 3x, while learning from images rather than states is about 5-10x slower.
Ok that’s a bit more complex than I was thinking. I want to randomize textures and colours, first
I’ve downloaded and unzipped the ‘Describable Textures Dataset’
And ok it’s loading a random texture for the plane
and random colour for the egg and chicken
Ok, next thing is the Simulation CNN.
Interpolation doesn’t work though, for this, cause it interpolates from what’s available in the image:
[ 0 85 170 255] [ 0 63 127 191 255] [ 0 63 127 191 255] I kind of need the basic UID segmentation. [ 0 1 2 3 255] Ok, pity about the mask colours, but anyway.
Let’s train the UNet on the new dataset.
We’ll need to make karolzak’s changes.
I’ve saved 2000+ rgb.jpg and seg.png files and we’ve got [0,1,2,3,255] [plane, egg, robot, chicken, sky]
So num_classes=5
And
“for multiclass segmentation you would need a mask of shape (width, height, num_classes) “
What is y.shape?
(2001, 256, 256, 1)
which is 2001 files, of 256 x 256 pixels, and one class. So if I change that to 5…? ValueError: cannot reshape array of size 131137536 into shape (2001,256,256,5)
Um… Ok I need to do more research. Brb.
So the keras_unet library is set up to input binary masks per class, and output binary masks per class.
I would rather use the ‘integer’ class output, and have it output a single array, with the class id per pixel. Similar to this question. In preparation for karolzak probably not knowing how to do this with his library, I’ve asked on stackoverflow for an elegant way to make the binary masks from a multi-class mask, in the meantime.
I coded it up using the library author’s suggested method, as he pointed out that the gains of the integer encoding method are minimal. I’ll check it out another time. I think it might still make sense for certain cases.
Ok that’s pretty awesome. We have 4 masks. Human, chicken, egg, robot. I left out plane and sky for now. That was just 2000 images of training, and I have 20000. I trained on another 2000 images, and it’s down to 0.008 validation loss, which is good enough!
So now I want to load the CNN model in the locomotion code, and feed it the images from the camera, and then have a reward function related to maximizing the egg pixels.
I also need to look at the pybullet-planning project and see what it consists of, as I imagine they’ve made some progress on the next steps. “built-in implementations of standard motion planners, including PRM, RRT, biRRT, A* etc.” – I haven’t even come across these acronyms yet! Ok, they are motion planning. Solvers of some sort. Hmm.
I’ve been scouring for existing code to help with developing the gripper in simulation. I was looking for a way to implement ‘eye-in-hand’ visual servoing, and came across a good resource, created for a masters thesis, which shows a ‘robot vision’ window, and he compares depth sensing algorithms. My approach was going to be, essentially, segmentation, in order to detect and localise chickens and eggs, in the field of vision, and then just try get their shape into an X-Y coordinate position, and over a certain size, to initiate interaction.
This one uses an SDF model of a KUKA industrial 6 DOF robot with a two finger gripper, but that has specific rotational movement, that seems maybe different from a simpler robot arm. So it’s maybe a bit overkill, and I might just want to see his camera code.
Miranda’s gripper prototype isn’t a $50k KUKA industrial robot arm. It’s just v.0.1 and got an 11kg/cm MG945, some 5kg/cm MG5010s, and an 1.3kg/cm SG90, and a sucker contraption I found on DFRobot, that can suck eggs.
So, regarding the simulation,this will be on top of the robot, as its head.
So we need an URDF file. Or an SDF file. There’s a couple ways to go with this.
The other resource I’ve found that looks like just what I need, is ur5pybullet
Regarding the ‘visual servoing’, the state of the art appears to be QT-Opt, perhaps. Or maybe RCAN, built on top of it. But we’re not there just yet. Another project specifically uses pybullet. Some extra notes here, from Sergey Levine, and co., associated with most of these projects.
Another good one is Retina-GAN, where they convert both simulation and reality into a canonical format. I’ve also come across Dex-Net before, from UCB.
Everything is very complicated though.
I’ve managed to make an URDF that looks good enough to start with, though. I’ll put everything in a github. We want to put two servos on the ‘head’ for animatronic emotional aesthetics, but there’s a sucker contraption there for the egg, so I think this is good enough for simulation, for now, anyway. I just need to put a camera on its head, put some eggs in the scene, and maybe reward stable contact with the tip. Of course it’s going to be a lot of work.
We also want to add extra leg parts, but I don’t want to use 4 more motors on it.
So I’m playing around with some aluminium and timing belts and pulleys to get 8 leg parts on 4 motors. Something like this, with springs if we can find some.
So, simulator camera vision. I can enable the GUI. Turns out I just need to press ‘g’ to toggle.
self._pybullet_client.configureDebugVisualizer(self._pybullet_client.COV_ENABLE_RENDERING, 1)
self._pybullet_client.configureDebugVisualizer(self._pybullet_client.COV_ENABLE_GUI, 1)
self._pybullet_client.configureDebugVisualizer(self._pybullet_client.COV_ENABLE_SEGMENTATION_MARK_PREVIEW, 1)
self._pybullet_client.configureDebugVisualizer(self._pybullet_client.COV_ENABLE_DEPTH_BUFFER_PREVIEW, 1)
self._pybullet_client.configureDebugVisualizer(self._pybullet_client.COV_ENABLE_RGB_BUFFER_PREVIEW, 1)I’ve added the gripper, and now I’m printing out the _control_observation, because I need to work out what is in an observation.
self.GetTrueMotorAngles() 0.18136442583543283, 0.4339093246887722, -0.25269494256467184, 0.32002873424829736, -0.6635045784503064, 1.5700002984158676, -1.5700000606174402, -0.2723645141027962, self.GetTrueMotorVelocities() 0.451696256678765, 0.48232988947216504, -4.0981980703534395, 0.4652986924553241, 0.3592921211587608, -6.978131098967118e-06, 1.5237597481713495e-06, -10.810712328063294, self.GetTrueMotorTorques() -3.5000000000000004, -3.5000000000000004, 3.5000000000000004, -3.5000000000000004, 3.5000000000000004, -3.5000000000000004, 3.5000000000000004, 3.5000000000000004, self.GetTrueBaseOrientation() -0.008942336195953221, -0.015395612988274186, 0.00639837318132646, 0.9998210192552996, self.GetTrueBaseRollPitchYawRate() -0.01937158793669886, -0.05133982438770338, 0.001050170752804882]
Ok so I need the link state of the end effector (8th link), to get its position and orientation.
state = self._pybullet_client.getLinkState(self.quadruped, self._end_effector_index)
pos = state[0]
orn = state[1]
print(pos)
print(orn)
(0.8863188372297804, -0.4008813832608453, 3.1189486984341848)
(0.9217446940545668, 0.3504950513334899, -0.059006227834041206, -0.1551070696318658)
Since the orientation is 4 dimensions, it’s a quaternion,
def gripper_camera(self, state):
pos = state[0]
ori = state[1]
rot_matrix = self._pybullet_client.getMatrixFromQuaternion(ori)
rot_matrix = np.array(rot_matrix).reshape(3, 3)
# Initial vectors
init_camera_vector = (1, 0, 0) # z-axis
init_up_vector = (0, 1, 0) # y-axis
# Rotated vectors
camera_vector = rot_matrix.dot(init_camera_vector)
up_vector = rot_matrix.dot(init_up_vector)
self.view_matrix_gripper = self._pybullet_client.computeViewMatrix(pos, pos + 0.1 * camera_vector, up_vector)
img = self._pybullet_client.getCameraImage(256, 256, self.view_matrix_gripper, self.projectionMatrix, shadow=0, flags = self._pybullet_client.ER_SEGMENTATION_MASK_OBJECT_AND_LINKINDEX, renderer=self._pybullet_client.ER_BULLET_HARDWARE_OPENGL)
Ok I’ve got the visuals now, but I shouldn’t be seeing that shadow
The camera is like 90 degrees off maybe. Could be an issue with the camera setup, or maybe the URDF setup? Ok…
Changing the initial camera vector fixed the view somewhat:
init_camera_vector = (0, 0, 1) # x-axis
Except that we’re looking backwards now.
init_camera_vector = (0, 0, -1) # x-axis
Ok well it’s correct now, but heh, hmm. Might need to translate the camera just a bit higher.
I found a cool free chicken obj file with Creative commons usage. And an egg.
Heh need to resize obj files. Collision physics is fun.
Ok I worked out how to move the camera a bit higher.
pos = list(pos)
pos[2] += 0.3
pos = tuple(pos)
Alright! Getting somewhere.
So, next, I add resized eggs and some chickens for good measure, to the scene.
Then we need to train it to stick its shnoz on the eggs.
Ok… gonna have to train this sucker now.
First, the table is falling from the sky, so I might need to stabilize it first. I also need to randomize the egg location a bit.
And I want to minimize the distance between the gripper attachment and the egg.
The smart way is probably to have it walk until some condition and then grasp, but in the spirit of letting the robot learn things by itself, I will probably ignore heuristics. If I do decide to use heuristics, it will probably be a finite state machine with ‘walking’ mode and ‘gripping’ mode. But we’ll come back to this when it’s necessary. Most of the time there won’t be any eggs in sight. So it will just need to walk around until it is sure there is an egg somewhere in sight.
Ok I’ve added a random egg to the scene
self.rng = default_rng()
egg_position = np.r_[self.rng.uniform(-20, 20, 2), 0.1]
egg_orientation = transformations.random_quaternion(self.rng.random(3))
self._egg_mesh = self._pybullet_client.loadURDF("%s/egg.urdf" % self._urdf_root, egg_position, egg_orientation, globalScaling=0.1)
And the end effector’s position should be something like the original camera position before we moved it up a bit, plus length of the end effector in the URDF (0.618). I ended up doing this:
pos = [pos[0] + 0.5*camera_vector[0],
pos[1] + 0.5*camera_vector[1],
pos[2] + 0.5*camera_vector[2]]
pos = tuple(pos)
And it’s closer to the tip now. But yeah. I will start a new post, Simulation Vision.
The chicken bone robot prototype I made turned out pretty well, mostly because bones have kind of gone through millions of years of evolution to be as strong and light as possible. Sounds like an ideal limb material. It’s also really nice to work with. Would be nice to do some composites too, for molding and 3D printing etc. from egg shells and feathers (2.3 million tonnes of EU feather waste from slaughterhouses a year) and whatever else.
egg shells + calcium carbonate a la Little Pink Maker
Giuseppe Abate‘s material experiments with chicken waste
Ylem Lab‘s Chicken Feather material “Pluminaire”
“Ecce” Robot pics from taken at the “making robots human ” exhibition in Stockholm Dan and I went to. The exhibition was kinda out of date British nationalist techno-utopian propaganda, but whatever, still got some cool hardware inspiration.
This https://github.com/facebookresearch/meshrcnn is maybe getting closer to holy grail in my mind. I like the idea of bridging the gap between simulation and reality in the other direction too. By converting the world into object meshes. Real2Sim.
The OpenAI Rubik’s cube hand policy transfer was done with camera in simulation and camera in real world. This could allow a sort of dreaming, i.e., running simulations on new 3d obj data.)
It could acquire data that it could mull over, when chickens are asleep.
PyTorch3d: https://arxiv.org/pdf/2007.08501.pdf
Pixel2Mesh: Generating 3D Mesh Models
from Single RGB Images https://arxiv.org/pdf/1804.01654.pdf
Remember Hinton’s dark knowledge. The trick is having a few models distill into one.
In trying to get Mesh R-CNN working, I had to add DEVICE=CPU to the config.
python3 demo/demo.py --config-file configs/pix3d/meshrcnn_R50_FPN.yaml --input /home/chrx/Downloads/chickenegg.jpg --output output_demo --onlyhighest MODEL.WEIGHTS meshrcnn://meshrcnn_R50.pth
Success! It’s a chair.
There’s no chicken category in Pix3d. But getting closer. Just need a chicken and egg dataset.
Downloading blender again, to check out the obj file that was generated. Ok Blender doesn’t want to show it, but here’s a handy site https://3dviewer.net/ to view OBJ files. The issue in blender required selecting the obj, then View > Frame Selected to make it zoom in. Switching to orthographic from perspective view also helps.
Chair is a pretty adaptable class.
https://github.com/facebookresearch/habitat-sim
A flexible, high-performance 3D simulator with configurable agents, multiple sensors, and generic 3D dataset handling (with built-in support for MatterPort3D, Gibson, Replica, and other datasets
