01.

Choose between our Starter Kit and an R&D Subscription

02.

Try it out

03.

Subscribe

1. Choose a plan

Reality AI Starter Kit using Bosch XDK

Need help collecting data?

Choose the Starter Kit plan

  • A set of Bosch XDK sensor modules, configured
    for use with Reality AI Tools™

  • SD Card with Reality AI Starter Kit software for XDK
  • USB SD card reader

Use of Reality AI Tools is restricted to accelerometer and vibration data collected with our Starter Kit.

 

Already have data?

Choose the R&D plan

  • Use your own sensors
  • All sensors are supported: works with sound, vibration, accelerometer, image, LiDAR, voltage, radio frequency, temperature, pressure data and more
  • Assistance with creation of classifiers, predicters or anomaly detectors

2. Explore Reality AI Tools

Source

Link or load new data files and manage files in persistent storage

Curate

Parse your data file. Create and manage sample lists

AI Explore™

Run Reality AI Algorithms. Explore model Complexity, Kfold accuracy, and Training Separation

Train

Expose your configured base tool to training data

Validate

Generate validation statistics, including training data separation and K-fold validation

Deploy

Prepare a trained tool for deployment and make it available in the cloud

3. Subscribe to Reality AI Tools

Starter Kit

Limited to Starter Kit Sensors

5 kper Starter Kit
  • Anomaly Detection & Clustering
    for Unlabeled Data
  • Classifier & Predictor Construction
    for Labeled Data
  • Access via Reality AI Tools™
    and Cloud API
Request a Starter Kit

  • Includes two months of subscription.
    $1,500 per additional month.

R&D Plan

All Sensors Supported

120 kYear
  • Annual Commitment Required
  • +
  • Anomaly Detection & Clustering
    for Unlabeled Data
  • Classifier & Predictor Construction
    for Labeled Data
  • Access via Reality AI Tools™
    and Cloud API
  • +
  • Complex Classifier Construction
  • +
  • Just Send Us Your Data™️ (Optional)
  • Licence to incorporate classifiers into product for resale (Optional)
  • Data labeling services (Optional)
Request a Trial

R&D Premium

All Sensors Supported

150 kYear
  • Annual Commitment Required
  • +
  • Anomaly Detection & Clustering
    for Unlabeled Data
  • Classifier & Predictor Construction
    for Labeled Data
  • Access via Reality AI Tools™
    and Cloud API
  • +
  • Complex Classifier Construction
  • Just Send Us Your Data™️
  • Embedded code export for use in firmware
  • +
  • Licence to incorporate classifiers into product for resale (Optional)
  • Data labeling services (Optional)
Contact Us

Frequently Asked Questions

Reality AI Tools™ is a cloud-based application for R&D engineers working with sensors and signals. It can be used to generate code for detecting real-world events and conditions using signal and sensor inputs.

Users can load or link to their sensor data, curate training and validation sample lists, use AI Explore™ to create optimized feature sets and generate machine learning models, then train and test those models in the field.

Reality AI Tools allows users to make trained classifiers, detectors and predictors available in the cloud, where they can be used with a simple API. Or, with a subscription upgrade, export them into a form where they can be integrated into firmware and run in real-time, at the edge, on your device.

Reality AI will work with any kind of sensor input. Customers have used a wide range of sensor and signal inputs, including accelerometry and vibrationsoundimage, LiDAR, 3D imageryelectrical signals and proprietary sensor types.

Reality AI Tools is generally more appropriate for non-image applications where the sensor data carries a sample rate of 25Hz or greater. For slower sample rates, traditional machine learning techniques geared for statistical time series are likely to give good results and should be tried first.
 
For image applications, Reality AI is generally most appropriate for problems related to identifying different surface textures and discontinuities in surface textures. For object identification and scene classification problems, a solution based on deep learning is more likely to give good results and should be tried first.

 

For sound applications, Reality AI is appropriate for a wide range of problems. However we do not have solutions for natural language processing or speech recognition. Other tools will be more appropriate for those kinds of problems.

The amount of data needed depends on the amount of variation in target classes and in the environmental background. In many cases, we can get useful results with small datasets. For some use cases, even a few dozen examples are sufficient to get started.

 

Eventually, to ensure a solution that will perform adequately in the field, it will be necessary to collect data that covers the full range of variation expected both in target and in background. For classification problems, that means examples of target classes occuring in as many different circumstances as possible, as well as counter-examples of non-target classes that could be confounded with targets.

To work with Reality AI Tools, data must be loaded or linked in one of our standard file formats. Please refer to our Standard File Format Guide.

 

Traditional signal data analysis is a “model-driven” approach based on the engineer’s understanding of the physics of the device, the physics of the sensor and a physical model of how target phenomena will be manifested in sensor output. It is typically an iterative, trial-and-error approach. Often, the engineer will use a fast-fourier transform (FFT), filter banks, or a linear systems analysis to discover the amount of energy in the signal’s frequency and time domain and use these outputs with statistical methods.

Reality AI uses a “data-driven” approach that makes no assumptions about the underlying physics, and instead employs advanced mathematics and machine learning to identify relevant features (which can be very different than frequency domain features found by an FFT), and then learn to classify on the basis of those features. Data-driven approaches to signal analysis are relatively new, and can be a powerful complement to traditional model-driven approaches.

You can find more information in our Technical Whitepaper.
Reality AI uses a proprietary method for generating features from sensor data that is grounded in the fundamental mathematics behind signal processing. This method creates optimized features that enable highly accurate detection / prediction in an extremely computationally efficient form. Reality AI Tools typically does not use neural networks at all (although it will for certain types of problems).
 
Deep Learning is an approach to machine learning that typically uses layers of convolutional neural networks to discover features and learn to accomplish a detection or prediction. It has been highly effective in many use cases, including object recognition in images and natural language processing in sound. But Deep Learning requires a great deal of training data, requires significant expertise to configure, and is not very computationally efficient -- deep learning solutions often require expensive, specialized hardware based on GPUs to run in the field.
 
Reality AI's approach, on the other hand, is usually much faster to configure, requires much less training data, and delivers results that are highly computationally efficient -- often fitting into inexpensive, commodity hardware when running at the edge.