Real-time on-farm yield trials powered by open-source: connecting ISOBlue, OADA, and the Trials Tracker App

The control system of a highly dynamic robot requires the ability to respond quickly to changes in the robot’s state. This type of system is needed in varying fields such as dynamic locomotion, multicopter control, and human-robot interaction. Robots in these fields require software and hardware capable of hard real-time, high frequency control. In addition, the application outlined in this paper requires modular components, remote guidance, and mobile control. The described system integrates a computer on the robot for running a control algorithm, a bus for communicating with microcontrollers connected to sensors and actuators, and a remote user interface for interacting with the robot. Current commercial solutions can be expensive, and open source solutions are often time consuming. The key innovation described in this paper is the building of a control system from existing — mostly open source — components that can provide realtime, high frequency control of the robot. This paper covers the development of such a control system based on ROS, OROCOS, and EtherCAT, its implementation on a dynamic bipedal robot, and system performance test results.

Download Full-text

A mobile sensor package for real-time greenhouse monitoring using open-source hardware

10.1002/essoar.10500273.1 ◽

2019 ◽

Author(s):

Lars Larson ◽

Elad Levintal ◽

Jose Manuel Lopez Alcala ◽

Dr. Lloyd Nackley ◽

Dr. John Selker ◽

...

Keyword(s):

Open Source ◽

Real Time ◽

Mobile Sensor ◽

Sensor Package ◽

Open Source Hardware

Download Full-text

Network-Ready, Open-Source Operating Systems for Embedded Real-Time Applications

Industrial Information Technology - Embedded Systems Handbook, Second Edition ◽

10.1201/9781439807637.ch8 ◽

2009 ◽

pp. 8-1-8-34

Author(s):

Ivan Cibrario Bertolotti

Keyword(s):

Open Source ◽

Real Time ◽

Operating Systems ◽

Real Time Applications

Download Full-text

Real Time Object Detection Canbe Embedded on Low Powered Devices

10.31219/osf.io/t3gdy ◽

2019 ◽

Author(s):

Jimut Bahan Pal

Keyword(s):

Neural Networks ◽

Object Detection ◽

Open Source ◽

Real Time ◽

Detection System ◽

Computing Power ◽

Convolution Neural Networks ◽

Real Challenge ◽

New Algorithms

It has been a real challenge for computers with low computing power and memory to detect objects in real time. After the invention of Convolution Neural Networks (CNN) it is easy for computers to detect images and recognize them. There are several technologies and models which can detect objects in real time, but most of them require high end technologies in terms of GPUs and TPUs. Though, recently many new algorithms and models have been proposed, which runs on low resources. In this paper we studied MobileNets to detect objects using webcam to successfully build a real time objectdetection system. We observed the pre trained model of the famous MS COCO dataset to achieve our purpose. Moreover, we applied Google’s open source TensorFlow as our back end. This real time object detection system may help in future to solve various complex vision problems.

Download Full-text