How to build Intelligent control systems using new tools from Microsoft and simulations by Mathworks

Channel:
Microsoft Research
Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=6mfUz4PDgOw


Category:
Guide
Duration: 5:18
5,814 views
108

In this video, engineers can learn how to build autonomous systems even with no previous experience in AI. Project Bonsai is Microsoft’s new service to help engineers developing intelligent control systems. In partnership with MathWorks we show how Project Bonsai can be used to control a small balancing robot called Project Moab. Project Moab enables engineers to explore classic control theory problems and go beyond a simple proportional–integral–derivative controller (PID controller or three-term controller).

Steve from MathWorks will show how you can build a simulation model of Project Moab using Simulink and Simscape that can be used with Project Bonsai. Keen, from Microsoft, will then use this simulation model to build an intelligent controller in three easy steps. (1) Integrate simulation model with the service (2) Train an AI agent to control the device that's modeled in the simulation (3) Export the brain into a device or simulation or wherever it is needed. Project Moab is available today in Project Bonsai as a simulator, implemented in both Simulink and Python. The Python simulation provides software developers the opportunity to learn how to use Project Bonsai and introduces them to simulation technology in an easy and accessible way.

Learn more here: https://www.microsoft.com/en-us/ai/autonomous-systems-platform



Other Videos By Microsoft Research


2020-06-08Microsoft Build 2020: Kevin Scott keynote with Lila Tretikov
2020-06-03Harvesting randomness, HAIbrid algorithms and safe AI with Dr. Siddhartha Sen | Podcast
2020-06-03Provably efficient reinforcement learning with Dr. Akshay Krishnamurthy | Podcast
2020-06-01What ‘bhasha’ do you want to talk in? With Kalika Bali and Dr. Monojit Choudhury | Podcast
2020-05-26Explaining Decisions from Vision Models and Correcting them via Human Feedback
2020-05-26Auditing Outsourced Services
2020-05-26MSR Distinguished Lecture Series: First-person Perception and Interaction
2020-05-26Large-scale live video analytics over 5G multi-hop camera networks
2020-05-26Kristin Lauter's TED Talk on Private AI at Congreso Futuro during Panel 11 / SOLVE
2020-05-19How an AI agent can balance a pole using a simulation
2020-05-19How to build Intelligent control systems using new tools from Microsoft and simulations by Mathworks
2020-05-13Diving into Deep InfoMax with Dr. Devon Hjelm | Podcast
2020-05-08An Introduction to Graph Neural Networks: Models and Applications
2020-05-07MSR Cambridge Lecture Series: Photonic-chip-based soliton microcombs
2020-05-07Multi-level Optimization Approaches to Computer Vision
2020-05-05How good is your classifier? Revisiting the role of evaluation metrics in machine learning
2020-05-05Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes
2020-05-05Hypergradient descent and Universal Probabilistic Programming
2020-05-04Learning over sets, subgraphs, and streams: How to accurately incorporate graph context
2020-05-04An Ethical Crisis in Computing?
2020-04-21Presentation on “Beyond the Prototype” by Rushil Khurana