I’d never have guessed that consumer and industrial drone manufacturer DJI would ever consider bringing a robot vac to the dining table, but I was wrong. And when you think about, why shouldn’t they? After all, the company’s amazing squadron of drones are capable of following users through difficult terrain, even through woodland with tree branches everywhere, with breath-taking accuracy and speed.
Given that navigation and obstacle avoidance are prerequisites of any successful robot vac, it makes perfect sense to use established drone navigation tech in a robot vac, or even a robot lawn mower. And since DJI would presumably never dream of sharing its navigation technology with anyone else, they may as well make their own robot vac. And that it did.
I’ve already given the new transparent DJI Romo P a very favourable review after putting it through its paces and watching it work over the course of a week. I also spent a lot of time analyzing its cleaning power on both hard floor and carpet. However, one facet of this new upstart has truly amazed me and that’s its extremely good obstacle avoidance.
In fact, I think that the DJI Romo P’s obstacle avoidance represents one of the most technologically sophisticated navigation systems yet deployed in a consumer robot vacuum cleaner. Unlike cheap and simple robot vacuums that rely on bumper switches or basic infrared sensors, the Romo P combines dual fisheye vision sensors with three solid-state LiDAR units that, according to DJI, bring ‘millimeter-level obstacle sensing’ into the home.
When combined, this multi-sensor data allows the Romo P to identify not just large, basic obstacles like furniture legs and walls, but also extremely thin obstacles as narrow as 2mm in thickness. And this means it is also a dab hand at dodging thin phone cables of any length, a myriad of toys including Lego bricks and, if approached head on, even flat objects like train tickets and playing cards. This level of discrimination is quite significant because credit-card thin items are among the hardest for robot vacuums to detect.
Navigation and obstacle sensing hardware in itself only gathers data but making intelligent decisions from that data is equally important. Hence, DJI and, it must be said, other big players like Roborock and Dreame, also incorporate onboard machine learning algorithms — including AI-assisted learning — in their premium bots that interpret the combined sensors’ inputs. These algorithms enable the robot to recognize different types of obstacles and choose the most appropriate course of action.
Sometimes it will weave close to narrow legs of furniture to clean nearby, while other times it will give a wide berth to most smaller objects. This contextual awareness apparently helps minimize cleaning interruptions and prevents the bot from getting stuck or inadvertently spreading messes, which is something I observed when the Romo P actively avoided a large dollop of tomato ketchup in my review’s mopping test.
I’ve also noticed the logical routes the Romo P takes every time it performs a task, and I can only assume that this is also down to its spatial awareness and ability to perform almost human-like movement through a maze of obstacles.
For my review test I tried to prove this and set up an assault course using a variety of items both large and small. I was frankly amazed at the speed with which the Romo P navigated its way around the obstacles without stopping for a breath or knocking anything over. In fact, it was like watching an Olympic slalom skier in action.
Anyway, this got me thinking. So for this article I set up another two, even more extreme tests and not only focussed on the Romo P, but enlisted the help of my trusty Roborock Saros 10R, another robot vac with very decent obstacle avoidance.
By the way, the Romo P offers three levels of obstacle avoidance in the DJI Home app: Obstacle Avoidance Priority, Standard and Cleaning Priority. For the following tests I selected the Standard mode because it better balances the gap between cleaning and avoidance.
Roborock Saros 10R vs DJI Romo P obstacle tests
I’ve been using the Roborock Saros 10R since April 2025 and, along with its stablemate the Saros 10, it is one of the best bots I’ve ever had the pleasure of reviewing. So I thought I’d see how well it faired against DJI’s new Romo P when it comes to negotiating a challenging obstacle course.
For this comparison test I carefully positioned a wide range of obstacles including dog toys of various sizes, phone cables of different lengths, three titchy diffuser oil bottles, a small leaflet of stamps, a mock train ticket, a packet of cigarette papers, two thin black lids, a silver spanner, a small screwdriver and a sock.
I created two different tests because I wanted to see if either bot had learned from previous mistakes. However, I can’t categorically say if they learned anything from Test 1 because I’ve never seen any robot do exactly the same thing twice. They’re robots, after all, and they quite literally have minds of their own.
Anyway, back to the two tests which started with the Saros 10R followed by the Romo P. Both models were commanded to go from their dock positions (the Saros in the hall and Romo in the lounge) and head to the kitchen over a patterned rug. They were then commanded to return to the dock.
Although they were both coming from different areas, I made sure that both bots were given equally challenging tasks, or as close as I could get it. Setting both robots to leave from the same area would have entailed remapping the whole home on one of the bots and I simply didn’t have the time or, for that matter, the inclination. However, as the video demonstrates, both bots faced equally complex assault courses.
Test 1
Roborock Saros 10R
The Saros 10R happily jaunted into the room and simply headed straight over the cigarette papers and one phone cable but then made a very good fist of reaching its goal without causing any chaos in about one minute. Its return trip was more haphazard and it rode over a small cable and the stamps and, after having a good think with it’s camera facing the cigarette papers, it decided, what the heck, and continued onwards, carrying the packet into the hall before depositing it as it approached its base station. Its return trip took 35 seconds.
DJI Romo P
Now it was the Romo P’s turn, and for this I selected its ‘Standard’ obstacle avoidance mode which is the best option for better cleaning performance. Straight away it turned towards the spanner and, rather disappointingly, rode right over it. Typical! It also rode over the book of stamps before continuing with a weird detour around a small phone cable. However, it still completed the task in just 48 seconds.
Its return trip was also a bit wayward and took exactly one minute though it did glance the small screwdriver (understandable) and rode over the stamps. But this time it stopped at the spanner before detouring around a hair scrunch before returning to dock.
I have to say that both of them performed extremely well in this test and I was especially surprised by how adeptly the Saros 10R handled the course. However, the Romo P was clearly a lot quicker to complete the task.
Test 2
Roborock Saros 10R
The Saros 10R approached the cigarette paper packet and pushed it aside before heading over the black phone cable. It then carefully worked its way between the two diffuser bottles before noticing it had run over the short cable and reversing. It then continued, glancing a small black plastic cap before running over the second one, completing the task in 45 seconds.
Its return trip was less successful. It immediately rode over the black cap and, after some time thinking at the small bottles, ran headlong over the black cable, which it dragged most of the way home. Time: 38 seconds
DJI Romo P
A perfect gold-medal run. This time the Romo avoided everything, including the spanner, the cigarette paper packet, the stamps and both black caps. An amazing achievement in 48 seconds flat.
However, Rom(e)o got very cocky on its 50-second trip home and rode over the screwdriver, stamps and cigarette packet (twice) as if it had had enough testing for one day and just wanted to get home as quickly as possible. You’ve got to laugh.
Test 3
DJI Romo P
For this final test I used just the Romo P and selected it’s ‘Obstacle Avoidance Priority’ mode which further enhances its navigation capabilities for ultra-cluttered homes. I even added some smaller obstacles like a thin piece of cardboard, along with the black caps and stamp booklet from the previous tests. While the Romo P did a bit more thinking and a couple of detours, it nailed the run with no major issues to report other than its side brush tampering with the thin slice of cardboard. Another gold-medal result.
While these tests in no way represent the real world (at least I’d like to hope so), they just go to show how refined the navigation is on both of these models. Yet while the Saros 10R’s obstacle avoidance can be considered perfectly acceptable for everyday scenarios, I have to give the winning rosette to the Romo P for a more accurate and speedy approach when it comes to overall navigation and the perfected art of obstacle dodging.
Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds. Make sure to click the Follow button!
And of course, you can also follow TechRadar on YouTube and TikTok for news, reviews, unboxings in video form, and get regular updates from us on WhatsApp too.