Views:0 Author:Site Editor Publish Time: 2021-07-20 Origin:Site
The earliest robotic vacuums did one thing passably well: they danced randomly over a smooth or flat surface, sucking up some dirt and debris until their battery charge got low and they had to return to their docks. They could more or less clean a space without the ability to understand it.
Today’s robotic cleaners have made huge strides over the past few years. They are now delivering more consistent and sustained performance as well as more cleaning features, and are starting to understand their spaces in order to clean them more efficiently. However, there are still design challenges that need to be addressed. This review of the top cleaners for 2018 shows that two of the four top challenges cleaners now face are related to navigation and the terrain of the home.
Let’s take a look at some of the big challenges–and opportunities–for robotic manufacturers today:
Room Mapping & Efficient Route Planning
Several of today’s navigation challenges–missed areas, long cleaning cycles, and insufficient battery charge–can be addressed through efficient route planning. Mapping an entire level of a house–or better yet, the entire house–and “remembering” which room is the goal worth attaining.
Room mapping requires AI and location awareness gained from a blend of inputs, including motion sensors, cameras, bump detectors and more. The smartest robots use this data to stay on course when they encounter corners, furniture and other typical obstacles. They’re starting to understand the topography of the rooms they’re cleaning in order to map the most efficient routes.
A robotic vacuum that can map a room can also take location-specific commands. Because it knows where a pet’s food and water bowls are, it will be able to skillfully avoid them. Or, you will know the location of the baby’s high chair and be able to go right to it to clean up after a particularly fun snacktime.
Clearing Multiple Floor Types & Identifying Obstacles
Today’s robots might stay on course perfectly well when the route is flat, but most can be stopped in their tracks by a slight tilt on the surface, such as a transition from wood to carpet or when trying to pass over a cord or wire. They may encounter a slight incline and attempt to power over it, only to wind up drowning in a dog’s water bowl or worse, spreading an even bigger mess….
To keep up with today’s consumer expectations and deliver a robot that can intelligently react to its surroundings, multi-axis motion sensors are a must. Multi-axis sensors are an advanced technology delivering an increased amount of real-world data to enhance AI decision making.
By adding “soft sensors” (bump detector, tilt/stuck detection) that leverages multi-axis IMUs with specialized algorithms and software, manufacturers can unlock even more features.
Smarter navigation is enhanced with multi-axis sensors by enabling robots to conquer obstacles and uneven or transitioning surfaces without losing accuracy. This all leads to a better end-user experience: more efficient navigation leads to lower power consumption, shorter cleaning time, fewer interruptions and, most importantly — happier end-users.
Moving Outside (and Into New Markets)
Robotic cleaners aren’t just for floors anymore: Robotic lawn mowers have gained in popularity and market share in recent years. But, robotic lawn mowers face very similar challenges to their indoor cousins: although many can power up a 45° slope, errant sticks and uneven ground can cause major interruptions. The outdoors may be a different environment, but the same challenges exist. Multi-axis motion sensors and their properly calibrated sensor fusion software can take automated lawn care to the next (high-accuracy) level.
Today’s leading robotic vacuums are able to map rooms and make more intelligent decisions about their environments to reduce service interruptions and perform better than older generations. Tomorrow’s robots will need to be even smarter. Multi-axis motion sensors with powerful sensor fusion can enable the next phase of product enhancements, allowing better AI decision making with real-world orientation information. All of this will improve end-user satisfaction and help to drive adoption in a market that’s poised for growth (reaching over $7B by 2022).