Position detection system of mobile robot in the warehouse enviroment

Overview
MainwindowGUI  

Autonomous-Forklift-System

Top language Status Repository size

About   |   GUI   |   Tests   |   Starting   |   License   |   Author   |  


🎯 About

An application that run the autonomous forklift paletization aglorithms. Projekt was created for Engineering Thesis. It was fully completed. The last release of this application is available in this repository. Alication uses image processing (OpenCV library) to detect the position of Acuco markers. Based on the calculated positions of the forklift, pallets and the storage place, the trajectories for the truck are generated (mainly using Voronoi graph and Dijsktra algorithm). Then the module responsible for communication with the robot controls it, so the robot collects choosed pallets and puts them one on top of the other in the designated warehouse.

🖥️ GUI

The interface was created using the PyQt5 and pyqtgraph libraries.The following elements are shown in the figure:

  1. Menu bar - user can change the FPTV coefficient, communication port and baudrate.
  2. Image transmission - user can choose between three views. The first view displays the real image from the camera. View 2 displays marked tags with their identifiers. The third view displays the trajectories for a robot and updates it with each move robot (fig. 3.22).
  3. Entering identifiers - to start system, the user has to enter the robot ID and the pallet that the robot has deliver to the storage area.
  4. Parameters - In the Module statuses table you can observe camera, communication and navigation module status. The Warehouse table shows the status graphically storage place. The Parameters table shows in sequence: camera number (by default 1), COM port (COM14 by default), baud rate (9600 by default), ratio FPTV (25 by default), fault information, phase one status, phase two status, and the number of steps remaining to complete the phase.
  5. Start and progress button that starts the palletization process (Start). It is available only after the correct robot and pallette identifiers are entered

🔬 Tests

  1. Correctness of generated paths - The correct route is considered to be a safe route to the destination. In the first phase the palette is the goal. The robot has to reach the pallet and then pick it up. In the second phase the goal is the storage area (warehouse). Result: Correct

  1. Correctness of completing the route - A correctly covered route is characterized by a minimal error between generated route and the route taken by the robot. This is equivalent to maintenance safety assumptions for every traffic. Result: Correct

  1. Correctness of multi-level storage - This test checks whether the palletiser is correctly stacking the pallets. It is necessary to consider the created system as a multi-level palletizing system. Result: Correct

🏁 Starting

# Clone this project
$ git clone https://github.com/KamilGos/Autonomous_Forklift_System

# Access
$ cd Autonomous_Forklift_System

# Run the project
$ sudo python3 main.py

📝 License

This project is under license from MIT. For more details, see the LICENSE file.

🧑‍💻 Author

Made with ❤️ by Kamil Goś

 

Back to top

You might also like...
MOT-Tracking-by-Detection-Pipeline - For Tracking-by-Detection format MOT (Multi Object Tracking), is it a framework that separates Detection and Tracking processes? Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

Apache MXNet (incubating) for Deep Learning Apache MXNet is a deep learning framework designed for both efficiency and flexibility. It allows you to m

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

Apache MXNet (incubating) for Deep Learning Apache MXNet is a deep learning framework designed for both efficiency and flexibility. It allows you to m

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

Apache MXNet (incubating) for Deep Learning Apache MXNet is a deep learning framework designed for both efficiency and flexibility. It allows you to m

MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.
MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.

Documentation | FAQ | Release Notes | Roadmap | MACE Model Zoo | Demo | Join Us | 中文 Mobile AI Compute Engine (or MACE for short) is a deep learning i

The UI as a mobile display for OP25
The UI as a mobile display for OP25

OP25 Mobile Control Head A 'remote' control head that interfaces with an OP25 instance. We take advantage of some data end-points left exposed for the

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

Apache MXNet (incubating) for Deep Learning Master Docs License Apache MXNet (incubating) is a deep learning framework designed for both efficiency an

Spatial Intention Maps for Multi-Agent Mobile Manipulation (ICRA 2021)
Spatial Intention Maps for Multi-Agent Mobile Manipulation (ICRA 2021)

spatial-intention-maps This code release accompanies the following paper: Spatial Intention Maps for Multi-Agent Mobile Manipulation Jimmy Wu, Xingyua

Spatial Action Maps for Mobile Manipulation (RSS 2020)
Spatial Action Maps for Mobile Manipulation (RSS 2020)

spatial-action-maps Update: Please see our new spatial-intention-maps repository, which extends this work to multi-agent settings. It contains many ne

Releases(v1.0.0)
Owner
Kamil Goś
Make my code with :heart:
Kamil Goś
Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator

DRL-robot-navigation Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin Delayed Deep Deterministic Policy Gra

null 87 Jan 7, 2023
Guiding evolutionary strategies by (inaccurate) differentiable robot simulators @ NeurIPS, 4th Robot Learning Workshop

Guiding Evolutionary Strategies by Differentiable Robot Simulators In recent years, Evolutionary Strategies were actively explored in robotic tasks fo

Vladislav Kurenkov 4 Dec 14, 2021
MohammadReza Sharifi 27 Dec 13, 2022
Space robot - (Course Project) Using the space robot to capture the target satellite that is disabled and spinning, then stabilize and fix it up

Space robot - (Course Project) Using the space robot to capture the target satellite that is disabled and spinning, then stabilize and fix it up

Mingrui Yu 3 Jan 7, 2022
(CVPR 2021) PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds

PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds by Mutian Xu*, Runyu Ding*, Hengshuang Zhao, and Xiaojuan Qi. Int

CVMI Lab 228 Dec 25, 2022
3D position tracking for soccer players with multi-camera videos

This repo contains a full pipeline to support 3D position tracking of soccer players, with multi-view calibrated moving/fixed video sequences as inputs.

Yuchang Jiang 72 Dec 27, 2022
ShuttleNet: Position-aware Fusion of Rally Progress and Player Styles for Stroke Forecasting in Badminton (AAAI 2022)

ShuttleNet: Position-aware Rally Progress and Player Styles Fusion for Stroke Forecasting in Badminton (AAAI 2022) Official code of the paper ShuttleN

Wei-Yao Wang 11 Nov 30, 2022
Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+

Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+

null 567 Dec 26, 2022
Implementing yolov4 target detection and tracking based on nao robot

Implementing yolov4 target detection and tracking based on nao robot

null 6 Apr 19, 2022