{"id":45932,"date":"2023-10-30T22:57:31","date_gmt":"2023-10-30T22:57:31","guid":{"rendered":"https:\/\/www.bravent.net\/news\/experimento-204-brazo-robotico-autonomo-con-ensenanza-automatica\/"},"modified":"2024-10-21T15:17:21","modified_gmt":"2024-10-21T15:17:21","slug":"experiment-204-autonomous-robotic-arm-with-machine-teaching-cognitive-services-and-iot","status":"publish","type":"post","link":"https:\/\/www.bravent.net\/en\/innovation-lab\/experiment-204-autonomous-robotic-arm-with-machine-teaching-cognitive-services-and-iot","title":{"rendered":"Experiment 204: Autonomous Robotic Arm with Machine Teaching, Cognitive Services and IoT"},"content":{"rendered":"

[vc_section full_width=”stretch_row” css=”.vc_custom_1698706318476{margin-top: 0px !important;margin-right: 0px !important;margin-bottom: 0px !important;margin-left: 0px !important;padding-top: 0px !important;padding-right: 0px !important;padding-bottom: 0px !important;padding-left: 0px !important;background-image: url(\/wp-content\/uploads\/2023\/10\/Group-22-4.png?id=45261) !important;background-position: center !important;background-repeat: no-repeat !important;background-size: cover !important;}” el_class=”casos-fold”]

[vc_empty_space height=”200px”]

Experiment #204<\/span><\/strong><\/p>\n<\/div>

Autonomous Robotic Arm with Machine Teaching, Cognitive Services and IoT<\/h1><\/div><\/div><\/div><\/section>[\/vc_section][vc_section full_width=”stretch_row” css=”.vc_custom_1635928545333{margin-top: 0px !important;margin-right: 0px !important;margin-bottom: 0px !important;margin-left: 0px !important;padding-top: 0px !important;padding-right: 0px !important;padding-bottom: 0px !important;padding-left: 0px !important;background-color: #020726 !important;background-position: center !important;background-repeat: no-repeat !important;background-size: cover !important;}”]
The Experiment #204 researches about the possibilities of using Custom Vision Object Detection and Reinforcement Learning in a Machine Teaching approach to building an autonomous robotic system.<\/span><\/div><\/div><\/div>

Project Date: <\/span>January-March 2020<\/span><\/p>\n

Services: <\/span> Azure Custom Vision, Reinforcement Learning, OpenAI Gym, Windows 10 IoT Core<\/span><\/p>\n

Technology used: <\/span>Machine Teaching – Cognitive Services
\n– IoT<\/span><\/p>\n<\/div><\/div><\/div><\/div><\/section>[\/vc_section]

[vc_empty_space height=”480px”]<\/div><\/div><\/div><\/section>
<\/div>[vc_section full_width=”stretch_row” css=”.vc_custom_1635929310178{margin-top: 0px !important;margin-right: 0px !important;margin-bottom: 0px !important;margin-left: 0px !important;padding-top: 0px !important;padding-right: 0px !important;padding-bottom: 0px !important;padding-left: 0px !important;background-color: #dadd02 !important;}”]
Challenge<\/span>[vc_separator color=”custom” border_width=”2″ accent_color=”#020726″ el_class=”reto-solucion” css=”.vc_custom_1698699630990{margin-bottom: 0px !important;}”]Automatic teaching<\/span><\/div><\/div><\/div><\/section>[\/vc_section]
Idea &
process<\/span><\/div><\/div><\/div>

For this Proof of Concept, we will try to build a robotic arm. The main purpose of the project is to create an Artificial Intelligence capable of detecting objects automatically and manipulating the arm autonomously.<\/p>\n

First, we will print some 3D pieces and assemble the servo motors and electronics on them.<\/p>\n<\/div><\/div><\/div><\/div>

Then, we will create an Azure Custom Vision project to build and train an Object Detection model. After that, we will use Machine Teaching and Reinforcement Learning to build and train a model to manage the autonomous system. Finally, we will put all things together in a Windows IoT Core application and deploy it on a Raspberry Pi device attached to the robotic arm.<\/p>\n<\/div><\/div><\/div><\/div><\/div><\/div><\/div><\/div><\/section>

[vc_empty_space height=”480px”]<\/div><\/div><\/div><\/section>
<\/div>[vc_section full_width=”stretch_row” css=”.vc_custom_1635929310178{margin-top: 0px !important;margin-right: 0px !important;margin-bottom: 0px !important;margin-left: 0px !important;padding-top: 0px !important;padding-right: 0px !important;padding-bottom: 0px !important;padding-left: 0px !important;background-color: #dadd02 !important;}”]
Utility<\/span>[vc_separator color=”custom” border_width=”2″ accent_color=”#020726″ el_class=”reto-solucion” css=”.vc_custom_1698699557120{margin-bottom: 0px !important;}”]Calculate the best path with the fewest number of instructions<\/span><\/div><\/div><\/div><\/section>[\/vc_section]
Utility<\/span><\/div><\/div><\/div>

The system optimizes the movements with the consequent energy saving and speed increase. Also, a well-calibrated robotic arm is more accurate than humans in manual and repetitive tasks.<\/p>\n<\/div><\/div><\/div><\/div><\/div><\/div><\/div><\/div><\/section>

Do you have a project in mind?<\/span><\/div><\/div><\/div><\/section>
<\/div>
<\/div><\/div><\/div>
\n
\n

<\/p>