diff --git a/docs/courses/capstone/overview.md b/docs/courses/capstone/overview.md index c8580b9..b065c5a 100644 --- a/docs/courses/capstone/overview.md +++ b/docs/courses/capstone/overview.md @@ -1,3 +1,6 @@ + + # 🏢 AC Training Lab Design Project Turn your self-driving lab expertise into a real-world project. During this course, you will propose, design, and build a self-driving laboratory at the AC training lab equipped with education- and research-grade equipment including liquid handlers, solid dispensers, Cartesian-axis systems, and mobile robotic arms. Prior to arrival, you'll create schematic figures, write white papers, and present your proposals to a team of scientists. During a week-long in-person experience, you'll implement your proposal and document your progress. After the visit, you will share your designs, data, and documentation to contribute to the public knowledge base. @@ -31,6 +34,8 @@ Turn your self-driving lab expertise into a real-world project. During this cour ## 🧩 Modules +This course is expected to take approximately 40 hours to complete. + ```{list-table} :header-rows: 1 diff --git a/docs/courses/data-science/overview.md b/docs/courses/data-science/overview.md index 6a96c1f..ab97352 100644 --- a/docs/courses/data-science/overview.md +++ b/docs/courses/data-science/overview.md @@ -1,3 +1,6 @@ + + # 📊 AI and Materials Databases for Self-Driving Labs Unleash the power of data science in the realm of self-driving laboratories. This remote, asynchronous course empowers you to apply data science concepts to materials discovery tasks. You'll create Bayesian optimization scripts using the Ax Platform, explore advanced optimization topics, and use the Honegumi template generator to create an advanced optimization setup for a materials discovery task. Additionally, you'll learn to share your findings by uploading datasets to FigShare, creating benchmark models with scikit-learn, and hosting models on HuggingFace. @@ -30,6 +33,8 @@ The **recommended prerequisite** for this course is Introduction to AI for Disco ## 🧩 Modules +Each module is intended to take approximately 2-3 hours, assuming that the recommended prerequisites have been met. + ```{list-table} :header-rows: 1 diff --git a/docs/courses/hello-world/overview.md b/docs/courses/hello-world/overview.md index 9bb3235..da62f6a 100644 --- a/docs/courses/hello-world/overview.md +++ b/docs/courses/hello-world/overview.md @@ -1,6 +1,9 @@ + + # 💡 Introduction to AI for Discovery using Self-driving Labs -Discover the essential principles of self-driving laboratories (SDLs) by building a 'Hello World' SDL from scratch. In this asynchronous, remote course, you will build a self-driving color matcher using dimmable LEDs and a light sensor. This introduction will help you implement hardware/software communication via MQTT, database integration via MongoDB, microcontroller programming with a Raspberry Pi Pico W, and optimization via the Adaptive Experimentation (Ax) Platform. The course will conclude with an expansion of the demo to the research-relevant task of continuously logging temperature, humidity, pressure, light, and accelerometer data. +Self-driving laboratories (SDLs) incorporate AI and automation into scientific laboratories to speed up the discovery of new materials for applications such as clean energy and cancer drugs. Discover the essential principles of SDLs by building a 'Hello World' SDL from scratch. In this asynchronous, remote course, you will build a self-driving color matcher using dimmable LEDs and a light sensor. This introduction will help you implement hardware/software communication, database integration, microcontroller programming, and Bayesian optimization. Each of these are important components of an SDL, and you will get a taste of these in the course modules. The course will conclude with an expansion of the demo to the research-relevant task of continuously logging temperature, humidity, pressure, light, and accelerometer data. ![](./images/clslab-light.gif) Animated schematic diagram of the 'Hello World' demo: A microcontroller controls the LEDs and reads sensor data. The difference between the target color and the measured color is fed into an adaptive experimentation algorithm, and the process repeats itself. @@ -16,10 +19,11 @@ For participants to complete this course within the expected timeframe (approx. - Describe key terms and principles of self-driving labs - Send commands and receive sensor data over WiFi using standard frameworks such as MQTT -- Store experiment configurations and results in a MongoDB database -- Implement software on a microcontroller to adjust device power and read sensor data +- Store experiment configurations and results in databases such as MongoDB +- Implement software on a microcontroller such as Raspberry Pi Pico W to adjust device power and read sensor data - Adapt a Bayesian optimization script from packages such as the Ax Platform to iteratively suggest new colors to try - Implement workflow orchestration for a color experiment using packages such as Covalent +- Integrate the individual SDL components to finalize the 'Hello World' demo - Modify the system to record temperature, humidity, barometric pressure, and accelerometer measurements ## 🛠️ Competencies/Skills @@ -34,6 +38,13 @@ For participants to complete this course within the expected timeframe (approx. ## 🧩 Modules +Each module is intended to take approximately 2-3 hours, assuming that the recommended prerequisites have been met. ABC + +``` +{include} ./hardware-note.md +``` + + ```{list-table} :header-rows: 1 @@ -79,8 +90,10 @@ For participants to complete this course within the expected timeframe (approx. * - Bayesian optimization - * Design of experiments + * Bayesian optimization * Data visualization - - * Compare grid and random search vs. Bayesian optimization + - * Adapt a Bayesian optimization script to perform color-matching + * Compare Bayesian optimization with other search methods * Visualize optimization efficiency * - Device communication diff --git a/docs/courses/robotics/overview.md b/docs/courses/robotics/overview.md index d6635a9..d42c5ee 100644 --- a/docs/courses/robotics/overview.md +++ b/docs/courses/robotics/overview.md @@ -1,3 +1,6 @@ + + # 🦾 Autonomous Systems for Self-Driving Labs Embark on a journey into the world of robotics and automation for self-driving laboratories. This asynchronous, remote course equips you with the skills to control peristaltic pumps, linear actuators, automated liquid handlers, and solid dispensers using a Pico W microcontroller, a motor driver, and the Covalent workflow orchestration package. You'll also learn to control mobile cobots using the Robot Operating System (ROS) framework and to perform spatial referencing and ID recognition via AprilTags and OpenCV. The course will conclude with a solid sample transfer workflow using Covalent, ROS, AprilTags, OpenCV, and a multi-axis robot. @@ -32,6 +35,8 @@ The **recommended prerequisite** for this course is Introduction to AI for Disco ## 🧩 Modules +Each module is intended to take approximately 2-3 hours, assuming that the recommended prerequisites have been met. + ```{list-table} :header-rows: 1 diff --git a/docs/courses/software-dev/overview.md b/docs/courses/software-dev/overview.md index ace8611..adb5473 100644 --- a/docs/courses/software-dev/overview.md +++ b/docs/courses/software-dev/overview.md @@ -1,3 +1,6 @@ + + # 👩‍💻 Software development for self-driving labs Elevate your software development skills in the context of self-driving laboratories. This asynchronous, remote course introduces software development concepts and best practices and productivity tools such as integrated development environments (IDEs) with VS Code, unit testing with pytest, continuous integration via GitHub actions, and documentation creation using Sphinx and Read the Docs. You'll also learn to deploy materials discovery campaigns on cloud servers or dedicated hardware and run offline simulations using cloud hosting. @@ -34,6 +37,8 @@ The **recommended prerequisite** for this course is Introduction to AI for Disco ## 🧩 Modules +Each module is intended to take approximately 2-3 hours, assuming that the recommended prerequisites have been met. + ```{list-table} :header-rows: 1