Caspar AI enables you to build intelligent smart home applications such as fall detection, activity detection, personalization and adaptation for your residents.
Caspar runs on the edge — does not send sensitive data to the cloud, ensuring privacy.
Edge Computing ensures reliability. The AI modules are compiled on your devices for low-latency.
Caspar’s API easily integrates with your smart home IoT platform to help you build innovative applications.
Caspar learns residents’ preferences and activities using CasparAdapt and CasparSense technology.
Our compiler produces local and computationally-efficient AI inference models for your IoT platform to power intelligent applications. It preserves privacy by design and keeps the users’ sensitive data within the home.
CasparSense uses multi-modal sensors within the home to predict complex user activities and intents such as cooking, falling and taking medicine.
CasparAdapt is a library of Deep Co-Reinforcement Learning tools that are designed to intelligently adapt and personalize the home to the residents.
The Home Notifies You If An Appliance Is Left On By Changing The Color Of The Lights.
In Case Of Inactivity Detected Due To Fall, Caspar Can Send An Alert.
Our Smart Clips Feature Notifies Residents When Their Pet Is On The Couch.
Residents Receive An Intelligent Reminder When They Forget To Take Their Medicine.
Don’t Want To Get Up From Couch? Don’t Worry, You Can Now Control The Home With Gestures.
CasparAdapt Intelligently Adjusts The Lighting To The Right Color So Residents Can Exercise, Watch A Movie Or Relax.
This paper proposes a scalable and principled approach for casting an arbitrary spatio-temporal graph as a rich Recurrent Neural Network (RNN).Learn more
In embodied AI applications such as smart homes, deep learning still suffers from generalization issues under the presence of a domain shift between the training and the test data distribution.Learn more
An average adult forgets three key facts, chores or events every day in a home. To detect the action structure in the complex activities, we propose a compact yet expressive representationLearn more
If you have a question, you can ask Google or Bing or any number of online databases. Now robots have their own knowledge database.Learn more
Anticipating human actions beforehand can provide alerts that could avoid incidents from happening. We reason with the contextual information from the surrounding context, which is obtained from multiple data sources.Learn more
Human behavior has an underlying structure. In this paper, we propose a supervised learning method for parsing a video into a semantic “storyline” composed of objective steps.Learn more
A system operating in a real-world environment such as homes needs to perform reasoning with a variety of sensing modalities.Learn more
Distributed AI (D-AI) is enabling rapid progress on smart IoT systems, homes, and cities. D-AI refers to any AI system with discrete AI subsystems that can be combined to create ensemble-intelligences. We introduce a Privacy-Preserving IoT Cloud (PPIC) optimized to host D-AI applications on the edge.Learn more
Covid has exposed just how vulnerable seniors are who live in nursing homes and assisted living facilities. Caspar.AI’s vision is to fundamentally change how seniors are in their homes and how assisted living facilities are run.Learn more
The question we’ve been talking about centers on the proper way to create a privacy-preserving IoT infrastructure.Learn more
“The network is the computer.”
That’s the old Sun Microsystems slogan coined by Sun computer scientist and researcher John Gage. The slogan predated cloud computing, but it’s a great way to envision the cloud idea.Learn more