2021 Real Robot Challenge Phase2 attemp

Overview

Real_Robot_Challenge_Phase2_AE_attemp

We(team name:thriftysnipe) are the first place winner of Phase1 in 2021 Real Robot Challenge.
Please see this page for more details: https://real-robot-challenge.com/leaderboard
To see more details about out Phase1 works: https://github.com/wq13552463699/Real_Robot_challenge
We were granted the access to Phase 2.

I am sorry, the project is too complex with too much large files, It is too hard to upload them all on Github. I just attached a part of the core code here for you to take a quick lreview. If you think my attempts is approriate, you can go to this Google Drive to download the full project file(all codes, results, trained models, environmental files,.etc):
https://drive.google.com/file/d/14vjCrWU6vzMdXxVSR2FeskMvuQpgqWqM/view?usp=sharing

RRC phase2 task description:

Randomly place 25 dices with the size of 0.01x0.01x0.01m in the environment. Use own controller to drive the three-finger robot to rearrange the dice to a specific pattern. Unfortunately, due to the set task is too difficult, no team could complete the task on the actual robot, so all teams with record are awarded third place in this phase. But I think our attempt has a reference value, if later scholars conduct related research, our method may be useful.

Our considerations:

We consider using a reinforcement learning algorithm as the controller in this phase. However, in this phase, information that can play as observations, such as coordinates and orientation of the dices, cannot be obtained from the environment directly but they are crucial for RL to run.
The alternative observations we can use are the images of the three cameras set in 3 different angles in the environment and their segmentation masks. We picked segmentation masks rather than the raw images since the attendance of noise and redundancy in the raw images were too much. Please see the following segmentation mask example(RGB's 3 channels represent segmentation masks from 3 different angles).

The segmentation masks have the dimension of 270x270x3, if directly passing it to the RL agent, which would lead to computational explosion and hard to converge. Hence, we planned to use some means to extract the principal components that can play as observations from it. In addition, the observation value also includes readable read-robot data(joint angle of the robot arm, end effector position, end effector speed, etc.).

Segmentation mask dimensionality reduction

This is the most important part of this task. We tried different methods, such as GAN, VAE, AE, to extract the principal conponents from the images. The quality of data dimensionality reduction can be easily seem from the discripency of reconstructed and oringinal images or the loss curves. After many trials(adjusting hyperparameters, network structure, depth, etc.), we got different trained VAE, GAN and AE models. We conducted offline tests on the obtained model and compared the results, we were surprised to find that the AE performed the best. When the latent of AE is 384, the quality of the reconstructed image is the best. The result is shown in the figure below.

The loss function also converges to an acceptable range:

Build up observation and trian RL agent.

We use the best AE encoder to deal with the segmentation masks to generate the observation and stitch with the readable data. The structure of the overall obervation is shown as follow:
We fed the above observations to several current cutting-edge model based and model free reinforcement learning algorithms, including DDPG+HER, PPO, SLAC, PlaNet and Dreamer. We thought it would work and enable the agent to learn for somewhat anyway. But it is a pity that after many attempts, the model still didn't have any trend to converge. Due to time limited, our attempts were over here.

Some reasons might lead to fail

  1. We used AE as the observation model. Although the AE's dimensionality reduction capability were the best, the latent space of AE were disordered and didn't make sense to RL agent. The observations passed to the RL must be fixed and orderly. Continuous delivery of unfixed data caused a dimensional disaster. For example, the third number in the observation vector passed at t1 represents 'infos of the 1st dice', and the number on the same position at t2 represents the 'infos of the 3rd dice'. This disorderly change with time makes RL very confused.
  2. The extracted latent space from segmentation mask dominates the observations, making RL ignore the existence of robots. The latent space size is 384, but which for the robot data is 27. The two are far apart, and there is a big data bias.
  3. Robot arm blocked the dices, segmentation masks can only represent a part of the dice. This problem cannot be avoided and can only be solved by more powerful image processing technology. This is also a major challenge in the current Image-based RL industry

Contribution

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change. Please make sure to update tests as appropriate.

Owner
Qiang Wang
PhD at UCD. Research interest: Reinforcement Learning; Computer vision&Touch; Representation learning
Qiang Wang
Scapy: the Python-based interactive packet manipulation program & library. Supports Python 2 & Python 3.

Scapy Scapy is a powerful Python-based interactive packet manipulation program and library. It is able to forge or decode packets of a wide number of

SecDev 8.3k Jan 08, 2023
This repository hosts the code for Stanford Pupper and Stanford Woofer, Raspberry Pi-based quadruped robots that can trot, walk, and jump.

This repository hosts the code for Stanford Pupper and Stanford Woofer, Raspberry Pi-based quadruped robots that can trot, walk, and jump.

Stanford Student Robotics 1.2k Dec 25, 2022
Transform a Raspberry Pi into a network diagnostic machine.

EtherView Last updated jan 30, 2022. Welcome to the EtherView project! This is a project to transform a RaspberryPi into a portable network diagnostic

1 Jan 30, 2022
Christmasvillage-rpi - Raspberry Pi relay controller for ChristmasVillage.io

ChristmasVillage.io Relay Controller Links ChristmasVillage.io - Live Stream & Controls Youtube Instagram About This repository controls the light rel

Grant Windes 2 Feb 15, 2022
Used python functional programming to make this Ai assistant

Python-based-AI-Assistant I have used python functional programming to make this Ai assistant. Inspiration of project : we have seen in our daily life

Durgesh Kumar 2 Dec 26, 2021
🔆 A Python module for controlling power and brightness of the official Raspberry Pi 7

rpi-backlight A Python module for controlling power and brightness of the official Raspberry Pi 7" touch display. Note: This GIF was created using the

Linus Groh 238 Jan 08, 2023
hardware design of the 250mm drone

hardware design of the 250mm drone

ZJU FAST Lab 645 Dec 25, 2022
Raspberry Pi Pico as a Rubber Ducky

Raspberry-Pi-Pico-as-a-Rubber-Ducky Kurulum Raspberry Pi Pico cihazınız için CircuitPython'u indirin. Boot düğmesine basılı tutarken cihazı bir USB ba

Furkan Enes POLATOĞLU 6 Dec 13, 2022
The PicoEMP is a low-cost Electromagnetic Fault Injection (EMFI) tool,

ChipSHOUTER-PicoEMP The PicoEMP is a low-cost Electromagnetic Fault Injection (EMFI) tool, designed specifically for self-study and hobbiest research.

NewAE Technology Inc. 312 Jan 07, 2023
Home Assistant custom integration to fetch data from Powerpal

Powerpal custom component for Home Assistant Component to integrate with powerpal. This repository and integration is not affiliated with Powerpal. Th

Lawrence 32 Jan 07, 2023
Example code to sending USB Gadget multimedia keys via Python

Send Multimedia USB HID Keys via Python As an USB Gadget in Linux This gives a simple script with zero dependencies that can easily run on any Linux d

DevOps Nirvana 2 Jan 02, 2023
What if home automation was homoiconic? Just transformations of data? No more YAML!

radiale what if home-automation was also homoiconic? The upper or proximal row contains three bones, to which Gegenbaur has applied the terms radiale,

Felix Barbalet 21 Mar 26, 2022
Red Light Green Light Robot

Red Light Green Light Robot The primary problem addressed by our project is robotic follower behavior i.e. maintaining distance from a moving target.

Will Romano 2 Nov 20, 2021
PyTorch implementation of paper "MT-ORL: Multi-Task Occlusion Relationship Learning" (ICCV 2021)

MT-ORL: Multi-Task Occlusion Relationship Learning Official implementation of paper "MT-ORL: Multi-Task Occlusion Relationship Learning" (ICCV 2021) P

Panhe Feng 12 Oct 11, 2022
The software that powers the sPot: a 4th generation

This code is meant to accompany this project in which a Spotify client is built into an iPod "Classic" from 2004. Everything is meant to run on a Raspberry Pi Zero W.

Guy Dupont 683 Dec 28, 2022
Skykettle ha - Redmond SkyKettle integration for Home Assistant

Redmond SkyKettle integration for Home Assistant This integration allows to cont

Alexey 'Cluster' Avdyukhin 48 Jan 06, 2023
Custom component for interacting with Octopus Energy

Home Assistant Octopus Energy ** WARNING: This component is currently a work in progress ** Custom component built from the ground up to bring your Oc

David Kendall 116 Jan 02, 2023
Lego Mindstorms EV3 and Lego Spike Prime

Lego Mindstorms EV3 and Lego Spike Prime What is FLL? The FIRST LEGO League Challenge Robotics Tournament challenges students from 9 to 16 years old t

Danimar Campos da Costa 1 Nov 14, 2021
🐱 Petkit feeder components for HomeAssistant

Petkit for HomeAssistant Installing Download and copy custom_components/xiaomi_miot folder to custom_components folder in your HomeAssistant config fo

62 Dec 29, 2022
LifeSaver automatically, periodically saves USB flash drive data into the PC

LifeSaver automatically, periodically saves USB flash drive data into the PC. Theoriticaly it will work with any any connected drive ex - Hard Disk ,SSD ... But, can't handle Backing up multipatition

siddharth dhaka 4 Sep 26, 2021