AGRICULTURE
Autonomous Navigation
Autonomous Navigation. What it takes to run it.
Visual SLAM and obstacle avoidance in unstructured terrain.
// 01 · The question
“Where can this machine safely drive?”
// 02 · Why it is hard
The terrain is unstructured and has no lane markings, no kerbs and no consistent geometry. Dust, ruts and glare change the surface appearance faster than the surface itself changes.
// 03 · What the labels have to be
Semantic segmentation
Decided before the first frame
Drivable and not-drivable is a property of every pixel, not of a countable object. There is no instance to box: the road, the headland and the crop row are surfaces, and the planner consumes a map rather than a list.
This is the decision that is expensive to reverse. The geometry has to match what the answer contains, and finding out it does not means labelling the set a second time.
// 04 · How we run it
Three parts of one loop, on this job.
LexAnnotate
Field Precision
Annotate crops, equipment, obstacles, and pathways with polygons, polylines, and semantic segmentation. Tag environmental factors like dust, shadows, and occlusions. 80k+ image annotations in production deployments.
LexInsight
Yield Intelligence
Transform plant-level detections into field-level intelligence. Map disease patterns across zones, track crop health progression over time, estimate yield from visual data.
LexAlert
Navigation Alerts
Monitor autonomous navigation models against seasonal drift. Retrain as fields change to keep navigation reliable through the seasons.
// 05 · What breaks it after launch
The same headland is bare soil, then stubble, then a metre of standing crop. Drivable ground looks entirely different in each, and the machine has to be right in all three.
It is not the only one that can get this use case, it is the one that usually gets it first. All ten conditions.
// 06 · In agriculture
GPS-Denied Autonomy
The Challenge
Unreliable GPS under tree canopies and low visibility. Models failed in unstructured, obstacle-heavy terrains.
Our Execution
Annotated thousands of images with polygons and polylines. Tagged diverse environmental factors like dust, shadows, and occlusions.
The Result
Enhanced autonomy in GPS-denied environments. Faster deployment of AI-powered navigation.
80k+
Image annotations in production