Enhanced Home Appliances
with AI

Unlock Smarter Hardware

Consumers want smarter, better appliances. So, whether it’s a security camera identifying a known person versus a stranger at the front door or a robotic vacuum cleaner recognizing obstacles in its path, Artificial Intelligence (AI) inference processing is becoming an integral part of home appliances. AI enables these domestic devices to learn from the behavior and activities of home users to provide a better experience through more targeted, more intelligent actions.

Televisions, smart locks, HVAC, vacuum cleaners, kitchen appliances, fitness mirrors, washing machines, and dryers all benefit from the addition of edge AI, allowing critical user experience-enhancing decisions to be made quickly with a minimum of latency and power consumption.

Ideal AI Implementations in Home Appliances
Compared to other markets, home appliance AI requirements are not particularly performance intensive. However, cost pressures dictate that Neural Processing Unit (NPU) engines use the least amount of silicon area possible while meeting specific performance targets. Additionally, power consumption must be minimal, especially for battery-powered devices. Home appliances generally run a single or small group of Neural Networks (NNs)—an ideal home appliance NPU should be specifically designed to require the smallest silicon area (thus, cost) and lowest power consumption.

AI in Home Appliances - Use Cases
AI in home appliances can bring a host of new capabilities, including:

• Refrigerators that automatically create shopping lists based on contents and expiration dates
• Coffee machines that brew at specific times and quantities based on user behaviors learned over time
• Door locks and deadbolts that detect and resist tampering
• Washing machines that determine the ideal cycle choice for every load and automatically order detergent as needed
• Heating, ventilation, and air conditioning (HVAC) systems that request preventive maintenance as needed

Best AI for Home Appliances
Future home appliances will process ever larger data sets and higher-resolution imagery. As a result, processing at the edge will require highly efficient hardware solutions. Adding Expedera Origin™ E1 or E2 Neural Processing Units (NPUs) to your silicon solution can improve system performance without increasing system costs. With Expedera, a home appliance can run one or more real-time AI inference models simultaneously with minimal power consumption and the smallest area (often 50% or less than other solutions), saving system cost.

Learn More About Expedera Products