Smart Home —
Distributed AI at the Edge

Caspar AI enables you to build intelligent smart home applications such as fall detection, activity detection, personalization and adaptation for your residents.

Privacy

Caspar runs on the edge — does not send sensitive data to the cloud, ensuring privacy.

Reliable & Low-latency

Edge Computing ensures reliability. The AI modules are compiled on your devices for low-latency.

Easy-to-use API

Caspar’s API easily integrates with your smart home IoT platform to help you build innovative applications.

Deep Context Al

Caspar learns residents’ preferences and activities using CasparAdapt and CasparSense technology.

Caspar Edge Al 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

CasparSense uses multi-modal sensors within the home to predict complex user activities and intents such as cooking, falling and taking medicine.

CasparAdapt

CasparAdapt is a library of Deep Co-Reinforcement Learning tools that are designed to intelligently adapt and personalize the home to the residents.

Sample Applications

Build Applications with Caspar Al

Caspar API includes the tools, libraries, and components you need to add cutting-edge smart home Al technology to your loT platform.

Fall detection for seniors

Setup IoT
platform

import casparSense
import iotPlatform
platform = iotPlatform(room="bathroom”)
sensor = ["thermal", "sound", "vision"])
User fall

sense = casparSense(room="bathroom")
prob = sense.fall()
Alert sent

if prob > 0.5:
   platform.alert(method="text")

Personalization and Adaptation
for a more helpful home

Week 1

User goes
to sleep
User controls
home

import casparSense
import iotPlatform
platform = iotPlatform(room="bedroom”)
sensor = ["thermal", "sound", "vision"])

Closes
shades
Turn off
lights

sense = casparSense(room="bedroom")
sense.run()

CasparAdapt learns
preferences

adapt = casparAdapt(room="bedroom")

Week 2

User goes
to sleep
CasparSense
understands
activity

@callback (userAction)
def userActionUpdate():
adapt.learnPrefs(sense.activity, userAction)

Closes
shades
Turn off
lights

@callback (sense.activity)
def automatedBehavior():
platform.takeAction(adapt.getLearnedPrefs(sense.activity))

IoT partners