examples VS ROS

TensorFlow, developed by Google, and PyTorch, developed by Facebook, are two of the most popular frameworks for building and training complex machine learning models. TensorFlow is known for its flexibility and robust scalability, making it suitable for both research prototypes and production deployments. PyTorch is praised for its ease of use, simplicity, and dynamic computational graph that allows for more intuitive coding of complex AI models. Both frameworks support a wide range of AI models, from simple linear regression to complex deep neural networks.

AI's Open Embrace Artificial intelligence (AI) and machine learning (ML) are increasingly leveraging open-source frameworks like TensorFlow [https://www.tensorflow.org/] and PyTorch [https://pytorch.org/]. This democratization of AI tools is driving innovation and lowering entry barriers across industries.

Which label applies to a tool sometimes depends on what you do with it. For example, PyTorch or TensorFlow can be called a library, a toolkit, or a machine-learning framework.

TensorFlow: An open-source machine learning framework for high-performance numerical computations, especially well-suited for deep learning.

The tool used to build the model per se was TensorFlow, a very powerful and end-to-end open source platform for machine learning with a rich ecosystem of tools. And in order to to create the needed script using TensorFlow Jupyter Notebook was used, which is a web-based interactive computing platform.

10. TensorFlow - Make Machine Learning Work for You 🤖

AI models, particularly those built on deep learning frameworks like TensorFlow, exhibit a high degree of parallelism. Neural network training involves numerous matrix operations, and GPUs, with their expansive core count, excel in parallelizing these operations. TensorFlow, along with other popular deep learning frameworks, optimizes to leverage GPU power for accelerating model training and inference.

#2 TensorFlow

I am on a new ftc team trying to get vision to work. I used the ftc machine learning tool chain but I have yet to get a good result with at best a 10% accuracy rate. I have changed everything possible in the tool chain with little luck. To fix this, I have tried making my own .tflite model using the google colab from https://www.tensorflow.org/. When ever I try to run the same code with my own .tflite model, it gives me the error "User code threw an uncaught exception: IllegalStateException - Error getting native address of native library: task_vision_jni". It gives me the same error with official tensor flow tflite test models, and when I put them on a raspberry pi, both worked just fine. Does anyone have a fix to this error or even just tips for the machine learning toolchain?

I wonder if this could be related to M1/2/3 Macs being worse for x86 system software development than the old Intel Macs. I work on ROS[1] which runs on x86 Linux platforms, but usually develop on a Mac. I may have to move to a Linux laptop soon because there's not an easy path (that I'm aware of) to running x86 ROS code on an M3: compiling the entire system for arm would be a huge headache while running x86 code in a Linux VM under Rosetta has a lot of unknowns.

Obviously my case is a bit of an outlier, but once you add up enough outliers you might see a real impact.

[1] https://www.ros.org

Robotics is a broad field and is a confluence of many specialties: mechanical engineering, hardware engineering, software engineering, control, machine learning, computer vision, anything in between is a good entrance.

Coming from software, if you are interested, I would suggest either:

- Backend platform development (Python, C++ as main programming languages with a strong focus on ROS[1]).

- Frontend development (nothing too different from what's out there).

As small projects I would suggest playing with ROS to learn it and getting a running simulation with a simple robot that you can teleoperate, most of the stack already exists, it's just connecting everything together [2].

Another venue is open source contribution [1] to get known within the community and potentially attract interest from companies. ROS has multiple packages, from cloud infrastructure to drivers and simulation, if you see anything there you could contribute to, they will gladly take contributions.

In general robotics greatly benefits of good technologies from other areas, if there is a tool we use you believe could be better or a lack of good tooling in a specific area, it will get noticed.

So this would be my suggested path: learn C++/Python if you're not familiar with, learn ROS and watch which specialties appear more often in robot related jos posts [3]. If you are really invested, maybe go to a robotics conference as ROSCon to meet other enthusiasts, which companies are engaged with the community, etc.

Good luck!

Note: not everything robot related is done in ROS, but it's almost a standard within the field save for a few exceptions.

[1]: https://www.ros.org/

ROS is an operating system designed for robotics (it can be run many different ways) it includes simulations for many robots (including sensors etc) and you can even design your own fully inside the software. https://www.ros.org/

Robotics with ROS https://www.ros.org/ (You can do a lot with simulators and don't require actual HW)

Hardware experience is useful, but not needed to get started working with robotics. With your software background, I recommend you look into learning ROS (Robot Operating System) fundamentals on a personal computer, you can simulate a robot using Gazebo. Good luck!

In Robotics, the Open Motion Planning Library (OMPL) is a popular library for multi-dimensional motion planning, and is used by ROS and other robotics-related software. There are no Rust bindings to OMPL (though there is Rust support for software like ROS), and the library is written almost exclusively in C++. There are Python bindings, but those are generated using Py++. The header files throughout OMPL are C++ header files, not C, as they contain namespaces, classes, etc.

[3] https://www.ros.org/

ALSO - learn ROS. If you are interested in robotics as a career, this is one of the better things to have good experience for on your resume. There are also good tutorials on using ROS with simulated robots, so if you just want to focus on the software that's a good option :)

Roboticist here, have you heard of ROS?