{"id":9780,"date":"2026-04-06T23:59:46","date_gmt":"2026-04-07T06:59:46","guid":{"rendered":"https:\/\/osorobotics.ai\/?page_id=9780"},"modified":"2026-08-25T06:33:44","modified_gmt":"2026-08-25T13:33:44","slug":"technology","status":"publish","type":"page","link":"https:\/\/osorobotics.ai\/es_ar\/technology\/","title":{"rendered":"Tecnolog\u00eda"},"content":{"rendered":"
\"\"<\/span>
\n

The Technology<\/h1>\n\n\n\n

AI That Learns From the Field<\/h2>\n<\/div><\/div>\n\n\n\n
\n

Most autonomous equipment follows a predefined map, but Oso’s equipment thinks on the fly.<\/p>\n<\/div>\n\n\n\n

\n
\n

How it works<\/p>\n\n\n\n

The AI brain built for the physical world<\/h2>\n\n\n\n

Our Large World Model (LWM) is an AI system built from the ground up for outdoor environments. It learns from experience, adapts to new conditions, and gets smarter with every hour it operates. No rigid programming. No starting over on a new property.<\/p>\n\n\n\n

So what exactly is it? You’ve probably heard of large language models (LLM) \u2014 the AI behind tools like ChatGPT. Those systems are trained to predict the next word in a sentence. Our LWM is trained to predict the next action <\/em>in the physical world.<\/p>\n\n\n\n

That distinction matters. Our equipment can observe its environment, make decisions in real time, and navigate complex outdoor spaces \u2014 uneven terrain, obstacles, irregular property boundaries \u2014 the same way an experienced operator would. Except it never gets tired, never calls out sick, and gets better the more it works.<\/p>\n\n\n\n

The hardware that makes it possible: RTK GPS for centimeter-level positioning, LiDAR for real-time obstacle detection, and vision cameras for person and object recognition. All data is processed by an on-board computer making navigation decisions continuously throughout every cut.<\/p>\n<\/div>

\"\"<\/figure><\/div>\n\n\n\n
\n

Setup<\/h3>\n\n\n\n
\n
\n

Operator walks perimeter<\/h4>\n\n\n\n

Record Mode active<\/p>\n<\/div>\n\n\n\n

\n

GPS + sensor data captured<\/h4>\n\n\n\n

Boundary locked in<\/p>\n<\/div>\n\n\n\n

\n

Mower operates autonomously<\/h4>\n\n\n\n

Within boundary<\/p>\n<\/div>\n<\/div>\n<\/div>\n\n\n\n

\n

Continuous Learning<\/h3>\n\n\n\n
\n
\n

01<\/p>\n\n\n\n

Mower cuts the site<\/h4>\n\n\n\n

Real-world operation<\/p>\n<\/div>\n\n\n\n

\n

02<\/p>\n\n\n\n

Operational data collected<\/h4>\n\n\n\n

Every run, every property<\/p>\n<\/div>\n\n\n\n

\n

04<\/p>\n\n\n\n

Every unit benefits<\/h4>\n\n\n\n

Updates deploy fleet-wide<\/p>\n<\/div>\n\n\n\n

\n

03<\/p>\n\n\n\n

LWM model improves<\/h4>\n\n\n\n

Across entire fleet<\/p>\n<\/div>\n<\/div>\n\n\n\n

Equipment sold today performs better six months from now.No hardware change required \u2014 the intelligence lives in the software.<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n

What it means<\/p>\n\n\n\n

Less setup, more uptime. Lower cost per cut.<\/h2>\n\n\n\n

Simple site setup, then full autonomy<\/strong> \u2014 Getting a new property ready takes one walk. Operators trace the perimeter in Record Mode, which uses RTK GPS to lock in the site boundary with centimeter-level accuracy. That boundary is stored on the mower. From that point forward, every visit to that property starts with full autonomous operation \u2014 no reprogramming, no technician, no babysitting.<\/p>\n\n\n\n

Adapts to what it finds<\/strong> \u2014 LiDAR sensors stop the mower immediately when anything enters its safety field. Vision cameras handle person and obstacle detection throughout the cut. The mower doesn’t need the property to be perfect, it handles what it finds.<\/p>\n\n\n\n

Continuously improving<\/strong> \u2014 Every hour of operation feeds back into the model. Equipment sold today performs better six months from now. No hardware change required. The intelligence lives in the software.<\/p>\n\n\n\n

Reduced dependency on skilled labor<\/strong> \u2014 The AI handles navigation and decision-making. Operators don’t need technical training to run it. If they can walk a perimeter, they can set up the mower.<\/p>\n<\/div>\n\n\n\n

\n

In-Depth Look<\/p>\n\n\n\n

How the Large World Model Works<\/h2>\n\n\n\n

Traditional autonomous outdoor equipment relies on one or more of the following: GPS boundary mapping, LiDAR or sensor-based obstacle avoidance, and hard-coded rule sets that define how the machine should behave in any given scenario. These systems are expensive to set up, brittle when conditions change, and incapable of handling situations they weren’t explicitly programmed for.<\/p>\n\n\n\n

The LWM takes a fundamentally different approach. Rather than programming rules, we train a deep learning model on real-world operational data. This teaches it to interpret its environment and select the best action at each moment, the same way a human brain processes sensory input and makes decisions.<\/p>\n\n\n\n

The sensor suite feeding the LWM is purpose-built for outdoor autonomy:<\/p>\n\n\n\n

\n
\n
\"\"<\/figure>\n\n\n\n

RTK GPS<\/h3>\n\n\n\n

Real-Time Kinematic positioning delivers centimeter-level accuracy, enabling precise boundary enforcement and consistent mowing patterns across every visit.<\/p>\n<\/div>\n\n\n\n

\n
\"\"<\/figure>\n\n\n\n

LiDAR <\/h3>\n\n\n\n

Continuous scanning of the safety field directly in front of and beside the mower, with immediate motor stop if anything enters the unsafe zone.<\/p>\n<\/div>\n\n\n\n

\n
\"\"<\/figure>\n\n\n\n

Vision cameras<\/h3>\n\n\n\n

Active obstacle and person detection throughout autonomous operation, providing a layer of awareness that GPS and LiDAR alone can’t deliver.<\/p>\n<\/div>\n\n\n\n

\n
\"\"<\/figure>\n\n\n\n

On-board computer<\/h3>\n\n\n\n

Fuses all sensor inputs in real time, making navigation and safety decisions continuously throughout every cut.<\/p>\n<\/div>\n<\/div>\n\n\n\n

The result is an algorithm that:<\/p>\n\n\n\n