While you don't always have to spend big to get the best tech, when it comes to robot mowers, the pricey Husqvarna Automower 450X EPOS proved to be a cut above the competition (technically, I tested the Husqvarna 410XE Nera (9/10, WIRED Recommends), which is the closest model in the UK and Europe). It employs Husqvarna's EPOS (Exact Positioning Operating System) tech and relies on a satellite connection to navigate your chosen virtual boundaries (no wire required). But you do need to install the receiver in an area with an open line of sight to the sky and, ideally, no tall trees or buildings nearby. Setup involves remote control driving the Husqvarna around your garden to map the virtual boundaries. You can have multiple separate areas and potentially cover an area up to 2.5 acres. I marked out my front and back lawns and simply carried the mower between them.

The Ultenic T10 is the latest in a small but growing pool of self-emptying robot vacuums. It can vacuum and mop simultaneously, map your home for more efficient cleaning, and customize cleaning schedules based on your habits. Aside from its less-common white finish, the T10 design is pretty standard with a pair of buttons--power and "home"--on the top, adjacent to a turret housing the vacuum's 360-degree laser scanner. On the underside are a rolling brush and a single spinning edge brush, along with various wheels and sensors. The T10's dust collector doubles as its charging dock.

As companies welcome more autonomous robots and other heavy equipment into the workplace, we need to ensure equipment can operate safely around human teammates. In this post, we will show you how to build a virtual boundary with computer vision and AWS DeepLens, the AWS deep learning-enabled video camera designed for developers to learn machine learning (ML). Using the machine learning techniques in this post, you can build virtual boundaries for restricted areas that automatically shut down equipment or sound an alert when humans come close. For this project, you will train a custom object detection model with Amazon SageMaker and deploy the model to an AWS DeepLens device. Object detection is an ML algorithm that takes an image as input and identifies objects and their location within the image.

Self-emptying robot vacuums allow you almost fully automate your floor cleaning. But until recently, they'd only been an option for those with very generous appliance budgets. The iRobot Roomba i7, for example, will cost you nearly $800, and the Roomba S9 a whopping $1,099. More recently, Proscenic's M7 Pro and iRobot's own Roomba i3 attempted to bring the self-emptying vacuum to more people with less scary price tags, but each sacrificed some functionality to do it. Ecovac's Deebot Ozmo N8 stands apart, managing to deliver most of the advanced features while keeping the cost moderate.

The M7 Pro is the first Proscenic robot vacuum we've reviewed, and if it's indicative of the rest of the company's vacuums, it bodes well indeed. The M7 Pro performs both vacuuming and mopping duties, employs laser navigation and mapping, and offers plenty of cleaning customization for a solidly mid-tier price. The M7 Pro doesn't break any molds with its design, sticking to a standard circular shape in a black finish. It measures just over 13 inches across and its above-average 3.8-inch height reflects the laser turret--which allows it to map your floor plan--sitting on top. Underneath are two spinning edge brushes and a main rolling brush.

Vacuums are the most successful consumer home robots ever, and they're likely to remain so for quite a while, simply because they do quite a good job at keeping your floors clean in a reliable and affordable way. For robot vacuum manufacturers, this is a bit of a problem: As we very often point out in our reviews, lower-end models clean just about as effectively as more expensive ones, often making it difficult to justify an upgrade. Today, Neato Robotics is introducing a new flagship robot vacuum that we think offers one of the most significant advances we've seen in years: persistent, actionable maps. Like its predecessors, the D7 uses a lidar sensor to create a map of your house as it goes, but now, the robot will remember that map and allow you to interact with it. Neato is starting off simple with what you'll be able to do (like defining no-go zones), but it's an incredibly powerful feature that's necessary for the future of all home robots.