scholarly journals Air Learning: a deep reinforcement learning gym for autonomous aerial robot visual navigation

2021 ◽  
Author(s):  
Srivatsan Krishnan ◽  
Behzad Boroujerdian ◽  
William Fu ◽  
Aleksandra Faust ◽  
Vijay Janapa Reddi
Keyword(s):  
Reinforcement Learning ◽  
Embedded System ◽  
Broad Class ◽  
Visual Navigation ◽  
Raspberry Pi ◽  
Latency Distribution ◽  
Hardware In The Loop ◽  
Resource Constrained ◽  
Aerial Robot ◽  
Policy Optimization

AbstractWe introduce Air Learning, an open-source simulator, and a gym environment for deep reinforcement learning research on resource-constrained aerial robots. Equipped with domain randomization, Air Learning exposes a UAV agent to a diverse set of challenging scenarios. We seed the toolset with point-to-point obstacle avoidance tasks in three different environments and Deep Q Networks (DQN) and Proximal Policy Optimization (PPO) trainers. Air Learning assesses the policies’ performance under various quality-of-flight (QoF) metrics, such as the energy consumed, endurance, and the average trajectory length, on resource-constrained embedded platforms like a Raspberry Pi. We find that the trajectories on an embedded Ras-Pi are vastly different from those predicted on a high-end desktop system, resulting in up to $$40\%$$ 40 % longer trajectories in one of the environments. To understand the source of such discrepancies, we use Air Learning to artificially degrade high-end desktop performance to mimic what happens on a low-end embedded system. We then propose a mitigation technique that uses the hardware-in-the-loop to determine the latency distribution of running the policy on the target platform (onboard compute on aerial robot). A randomly sampled latency from the latency distribution is then added as an artificial delay within the training loop. Training the policy with artificial delays allows us to minimize the hardware gap (discrepancy in the flight time metric reduced from 37.73% to 0.5%). Thus, Air Learning with hardware-in-the-loop characterizes those differences and exposes how the onboard compute’s choice affects the aerial robot’s performance. We also conduct reliability studies to assess the effect of sensor failures on the learned policies. All put together, Air Learning enables a broad class of deep RL research on UAVs. The source code is available at: https://github.com/harvard-edge/AirLearning.

RANCANG BANGUN INTERNET OF THINGS SERVER DENGAN MENGGUNAKAN ACTIVEMQ ARTEMIS UNTUK MITIGASI BENCANA DI RASPBERRY PI 3

Transmisi ◽  
2020 ◽  
Vol 22 (4) ◽  
pp. 117-122
Author(s):  
Sadr Lufti Mufreni ◽  
Esi Putri Silmina
Keyword(s):  
Internet Of Things ◽  
Embedded System ◽  
Raspberry Pi

Indonesia merupakan negara kepulauan yang mempunyai lebih dari 13.000 pulau. Wilayahnya terletak di antara Samudera Hindia dan Samudera Pasifik dan dilewati oleh Pacific Ring of Fire sehingga banyak gunung berapi aktif. Berdasarkan letak geografis mempunyai potensi tsunami dan gempa bumi cukup tinggi. Diperlukan rencana penanggulangan bencana yang baik untuk menekan risiko yang bisa terjadi, salah satunya dengan mitigasi bencana. Mitigasi bencana adalah serangkaian upaya untuk mengurangi risiko bencana, baik melalui pembangunan fisik maupun penyadaran dan peningkatan kemampuan menghadapi ancaman bencana. Mitigasi bencana diperlukan untuk mengurangi dampak yang ditimbulkan terutama korban jiwa. Salah satunya dengan menggunakan sistem peringatan dini. Sistem peringatan dini terdiri dari 3 komponen utama yaitu sensor untuk mendapatkan nilai dari suatu lingkungan, controller untuk mengolah nilai yang diterima, dan aksi yang dilakukan berdasarkan hasil dari pengolahan. Untuk membuat sistem yang efektif diperlukan komunikasi yang memadai. Messaging queue digunakan oleh industri untuk komunikasi antar perangkat lunak, perangkat keras, dan embedded system. Penelitian berfokus pada penggunaan ActiveMQ Artemis sebagai messaging queue sebagai server untuk komunikasi dengan internet of things (IoT). Keunggulan ActiveMQ Artemis dapat dijalankan di Raspberry Pi 3 dengan sedikit modifikasi. Hasil penelitian membuktikan bahwa ActiveMQ Artemis dapat digunakan untuk komunikasi IoT pada simulasi sistem mitigasi bencana.

scholarly journals PEMODELAN SISTEM DETEKSI WAJAH SEBAGAI PENGHITUNG JUMLAH PENUMPANG TRANSPORTASI PUBLIK

2021 ◽  
Vol 4 (1) ◽  
pp. 67-77
Author(s):  
Fransiska Sisilia Mukti ◽  
Lia Farokhah ◽  
Nur Lailatul Aqromi
Keyword(s):  
Embedded System ◽  
System Design ◽  
Face Detection ◽  
Public Transportation ◽  
Detection System ◽  
Raspberry Pi ◽  
The Internet ◽  
Detection Mechanism ◽  
Information System Design ◽  
The Face

Bus is one of public transportation and as the most preferable by Indonesian to support their mobility. The high number of bus traffics then demands the bus management to provide the maximum service for their passenger, in order to gain public trust. Unfortunately, in the reality passenger list’s fraud is often faced by the bus management, there is a mismatch list between the amount of deposits made by bus driver and the number of passengers carried by the bus, and as the result it caused big loss for the Bus management. Automatic Passenger Counting (APC) then as an artificial intelligence program that is considered to cope with the bus management problems. This research carried out an APC technology based on passenger face detection using the Viola-Jones method, which is integrated with an embedded system based on the Internet of Things in the processing and data transmission. To detect passenger images, a webcam is provided that is connected to the Raspberry pi which is then sent to the server via the Internet to be displayed on the website provided. The system database will be updated within a certain period of time, or according to the stop of the bus (the system can be adjusted according to management needs). The system will calculate the number of passengers automatically; the bus management can export passenger data whenever as they want. There are 3 main points in the architecture of modeling system, they are information system design, device architecture design, and face detection mechanism design to calculate the number of passengers. A system design test is carried out to assess the suitability of the system being built with company needs. Then, based on the questionnaire distributed to the respondent, averagely 85.12 % claim that the Face detection system is suitability. The score attained from 4 main aspects including interactivity, aesthetics, layout and personalization

scholarly journals Proposal for an Embedded System Architecture Using a GNDVI Algorithm to Support UAV-Based Agrochemical Spraying

Sensors ◽  
2019 ◽  
Vol 19 (24) ◽  
pp. 5397 ◽  
Author(s):  
Maik Basso ◽  
Diego Stocchero ◽  
Renato Ventura Bayan Henriques ◽  
André Luis Vian ◽  
Christian Bredemeier ◽  
...  
Keyword(s):  
Control System ◽  
Embedded System ◽  
Precision Agriculture ◽  
System Architecture ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Raspberry Pi ◽  
Research Station ◽  
High Definition ◽  
Cpu Usage

An important area in precision agriculture is related to the efficient use of chemicals applied onto fields. Efforts have been made to diminish their use, aiming at cost reduction and fewer chemical residues in the final agricultural products. The use of unmanned aerial vehicles (UAVs) presents itself as an attractive and cheap alternative for spraying pesticides and fertilizers compared to conventional mass spraying performed by ordinary manned aircraft. Besides being cheaper than manned aircraft, small UAVs are capable of performing fine-grained instead of the mass spraying. Observing this improved method, this paper reports the design of an embedded real-time UAV spraying control system supported by onboard image processing. The proposal uses a normalized difference vegetation index (NDVI) algorithm to detect the exact locations in which the chemicals are needed. Using this information, the automated spraying control system performs punctual applications while the UAV navigates over the crops. The system architecture is designed to run on low-cost hardware, which demands an efficient NDVI algorithm. The experiments were conducted using Raspberry Pi 3 as the embedded hardware. First, experiments in a laboratory were conducted in which the algorithm was proved to be correct and efficient. Then, field tests in real conditions were conducted for validation purposes. These validation tests were performed in an agronomic research station with the Raspberry hardware integrated into a UAV flying over a field of crops. The average CPU usage was about 20% while memory consumption was about 70 MB for high definition images, with 4% CPU usage and 20.3 MB RAM being observed for low-resolution images. The average current measured to execute the proposed algorithm was 0.11 A. The obtained results prove that the proposed solution is efficient in terms of processing and energy consumption when used in embedded hardware and provides measurements which are coherent with the commercial GreenSeeker equipment.

scholarly journals Artificial vision system for object classification in real time using Raspberry Pi and a Web camera

2021 ◽  
pp. 20-25
Author(s):  
Tomás Serrano-Ramírez ◽  
Ninfa del Carmen Lozano-Rincón ◽  
Arturo Mandujano-Nava ◽  
Yosafat Jetsemaní Sámano-Flores
Keyword(s):  
Embedded System ◽  
Real Time ◽  
Vision System ◽  
Low Cost ◽  
Artificial Vision ◽  
Maintenance Cost ◽  
Raspberry Pi ◽  
Smart Cameras ◽  
Suggested Technique ◽  
Web Camera

Computer vision systems are an essential part in industrial automation tasks such as: identification, selection, measurement, defect detection and quality control in parts and components. There are smart cameras used to perform tasks, however, their high acquisition and maintenance cost is restrictive. In this work, a novel low-cost artificial vision system is proposed for classifying objects in real time, using the Raspberry Pi 3B + embedded system, a Web camera and the Open CV artificial vision library. The suggested technique comprises the training of a supervised classification system of the Haar Cascade type, with image banks of the object to be recognized, subsequently generating a predictive model which is put to the test with real-time detection, as well as the calculation for the prediction error. This seeks to build a powerful vision system, affordable and also developed using free software.

scholarly journals Raspberry Pi based Embedded System for Vehicle Automation over Internet

IJARCCE ◽  
2016 ◽  
Vol 5 (12) ◽  
pp. 255-259
Author(s):  
Nagalaskhmi T S ◽  
Nirmala L ◽  
Akash Soragaon
Keyword(s):  
Embedded System ◽  
Raspberry Pi ◽  
Vehicle Automation

scholarly journals Cloud-based people counter

2020 ◽  
Vol 9 (1) ◽  
pp. 284-291 ◽  
Author(s):  
Abd Kadir Mahamad ◽  
Sharifah Saon ◽  
Hamimi Hashim ◽  
Mohd Anuaruddin Ahmadon ◽  
Shingo Yamaguchi
Keyword(s):  
Embedded System ◽  
Economic Trend ◽  
Raspberry Pi ◽  
People Counting ◽  
Video Footage ◽  
Iot Platform ◽  
The People ◽  
Initial Stage ◽  
Actual Environment ◽  
People Movement

Emergence of Industry 4.0 in current economic trend promotes the usage of Internet of Things (IoT) in product development. Counting people on streets or at entrances of places is indeed beneficial for security, tracking and marketing purposes. The usage of cameras or closed-circuit television (CCTV) for surveillance purposes has emerged the need of tools for the digital imagery content analysis to improve the system. The purpose of this project is to design a cloud-based people counter using Raspberry Pi embedded system and send the received data to ThingSpeak, IoT platform. The initial stage of the project is simulation and coding development using OpenCV and Python. For the hardware development, a Pi camera is used to capture the video footage and monitor the people movement. Raspberry Pi acts as the microcontroller for the system and process the video to perform people counting. Experiment have been conducted to measure the performance of the system in the actual environment, people counting on saved video footage and visualized the data on ThingSpeak platform.

scholarly journals GPS Data Correction Based on Fuzzy Logic for Tracking Land Vehicles

Mathematics ◽  
2021 ◽  
Vol 9 (21) ◽  
pp. 2818
Author(s):  
Pedro J. Correa-Caicedo ◽  
Horacio Rostro-González ◽  
Martin A. Rodriguez-Licea ◽  
Óscar Octavio Gutiérrez-Frías ◽  
Carlos Alonso Herrera-Ramírez ◽  
...  
Keyword(s):  
Fuzzy Logic ◽  
Embedded System ◽  
Fuzzy Systems ◽  
Intelligent System ◽  
Unscented Kalman Filter ◽  
The Other ◽  
Linear Functions ◽  
Sensor Technology ◽  
Raspberry Pi ◽  
Land Vehicles

GPS sensors are widely used to know a vehicle’s location and to track its route. Although GPS sensor technology is advancing, they present systematic failures depending on the environmental conditions to which they are subjected. To tackle this problem, we propose an intelligent system based on fuzzy logic, which takes the information from the sensors and correct the vehicle’s absolute position according to its latitude and longitude. This correction is performed by two fuzzy systems, one to correct the latitude and the other to correct the longitude, which are trained using the MATLAB ANFIS tool. The positioning correction system is trained and tested with two different datasets. One of them collected with a Pmod GPS sensor and the other a public dataset, which was taken from routes in Brazil. To compare our proposal, an unscented Kalman filter (UKF) was implemented. The main finding is that the proposed fuzzy systems achieve a performance of 69.2% higher than the UKF. Furthermore, fuzzy systems are suitable to implement in an embedded system such as the Raspberry Pi 4. Another finding is that the logical operations facilitate the creation of non-linear functions because of the ‘if else’ structure. Finally, the existence justification of each fuzzy system section is easy to understand.

scholarly journals UAV Object Tracking Application Based on Patch Color Group Feature on Embedded System

Electronics ◽  
2021 ◽  
Vol 10 (15) ◽  
pp. 1864
Author(s):  
Ming-Hwa Sheu ◽  
Yu-Syuan Jhang ◽  
S M Salahuddin Morsalin ◽  
Yao-Fong Huang ◽  
Chi-Chia Sun ◽  
...  
Keyword(s):  
Computational Complexity ◽  
Embedded System ◽  
Object Tracking ◽  
Tracking System ◽  
Computational Cost ◽  
Gaussian Mixture ◽  
Raspberry Pi ◽  
Color Group ◽  
Current Frame ◽  
Low Computational Complexity

The discriminative object tracking system for unmanned aerial vehicles (UAVs) is widely used in numerous applications. While an ample amount of research has been carried out in this domain, implementing a low computational cost algorithm on a UAV onboard embedded system is still challenging. To address this issue, we propose a low computational complexity discriminative object tracking system for UAVs approach using the patch color group feature (PCGF) framework in this work. The tracking object is separated into several non-overlapping local image patches then the features are extracted into the PCGFs, which consist of the Gaussian mixture model (GMM). The object location is calculated by the similar PCGFs comparison from the previous frame and current frame. The background PCGFs of the object are removed by four directions feature scanning and dynamic threshold comparison, which improve the performance accuracy. In the terms of speed execution, the proposed algorithm accomplished 32.5 frames per second (FPS) on the x64 CPU platform without a GPU accelerator and 17 FPS in Raspberry Pi 4. Therefore, this work could be considered as a good solution for achieving a low computational complexity PCGF algorithm on a UAV onboard embedded system to improve flight times.

Sign in / Sign up

Export Citation Format

Share Document