Drone transportation has literally been the buzz world since last few years and companies are striving to develop automated drone mobility ecosystem. Microsoft has always been on the forefront when it comes to new technology and Drone mobility is no different. Microsoft has built a simulator which will let researchers use it as a safe, reliable and cheap way to test autonomous systems.
If you really want to do this high-fidelity perception work, you have to render the scene in very realistic detail – you have sun shining in your eyes, water on the street,” said Shital Shah, a principal research software development engineer who has been a key developer of the simulator
The advantages can be numerous the very evident one is that the company will not have to crash a costly drone during testing and also doesn’t need to invest thousands of Dollars and purchase the testing equipment. Also, the chances of hurting someone or damaging a property is also greatly reduced due to the simulator.
Microsoft has designed the simulator such that it helps the researchers do better AI research in a smaller time frame also it facilitates a ready platform for users to use advanced AI methods like reinforcement testing. The bonus, however, comes in the form of a library of software in the Aerial and Robotics Platform. This library allows developers to quickly write the code to control drones which are built on DJI and mavLink platforms. Traditionally developers had to learn both the API’s separately and then write code for each platform. Needless to say, the researchers will add more tool as they keep on improvising the platform.
We had earlier covered how Microsoft wants to Democratizing AI and the simulator is a part of their strategy. In fact, the developers claim that the same software can be even used to drive a car or even ride a glider.
In the near future Technology will become much simpler for the developers since they can start working on ready-made platforms instead of coding from the scratch also this helps in creating a unified ecosystem.
- Tags: AI