Send the link below via email or IMCopy
Present to your audienceStart remote presentation
- Invited audience members will follow you as you navigate and present
- People invited to a presentation do not need a Prezi account
- This link expires 10 minutes after you close the presentation
- A maximum of 30 users can follow your presentation
- Learn more about this feature in our knowledge base article
Robotic Applications Platform
Transcript of Robotic Applications Platform
Why rely on robot CPU, when we can use a powerful cloud CPU and GPU?
Why use one robot controller, when we can have many on-demand controllers downloaded from the cloud?
Freeing up resources
Asynchronous API promotes parallelism & threading.
Ergo, More crucial tasks are performed on the robot, in a non-blocking manner.
Knowledge is shared across - no robot is a
. Thus, less space and processing needed on the robot.
The Robot APP
Similarly to the Smartphone APP, Robot controllers (as FSM, or Biologically-inspired ANN) can execute specific tasks by downloading a RAPP.
The RAPP CLOUD
We run computationally heavy requests on the "cloud": Computer-Vision, Speech Recognition, pattern detection, Artificial Neural Networks.
Also, we share knowledge across Robots!
ASIO cloud API
Object tracking (streamed)
Speech Recognition (streamed)
Ontology & Knowledge DB
e.g., "Find Keys"
Robot requests a RAPP that can perform task "Find Keys".
RAPP is downloaded, executed and an object is passed back to the caller.
e.g., "Open Door"
Robot detects a door, and asks the cloud for a RAPP that can handle this door.
Provided the robot hardware is compatible, a RAPP that opens that door, is downloaded and executed.
Is a Linux-based ROS node cluster using ASIO sockets.
It can be on the Internet, your local Intranet, or within your physical reach (e.g., the same facility) using a low-latency high-bandwidth LAN/WAN.
It may be private, public or protected