Key Notes
- DJI’s Matrice 5T combines a native 1280x1024 thermal sensor with LiDAR, millimetre-wave radar and visual sensing for enterprise fieldwork.
- The platform supports third-party onboard AI models and custom Pilot 2 plugins, extending its role beyond recording images.
- DJI advertises up to 59 minutes of flight and IP55 protection, with published performance measured under controlled conditions.
DJI has introduced the Matrice 5T, a compact enterprise drone combining native 1K thermal imaging with LiDAR, millimetre-wave radar and visual sensing. Announced on November 5, the aircraft also supports third-party onboard AI models for inspection and other field workflows.
The launch announcement lists IP55 protection and up to 59 minutes of flight time, with availability through authorized enterprise dealers. DJI says its performance data was measured using a production model under controlled conditions, rather than representing a guaranteed result on every mission.
Thermal Detail Without Confusing Enhanced Resolution
The thermal camera’s native resolution is 1280 by 1024 pixels. DJI also offers an enhanced image mode at 2560 by 2048, which should be distinguished from the sensor’s native pixel count. More thermal detail can help operators inspect equipment and investigate apparent heat anomalies.
The sensor package includes visible-light cameras for viewing the scene alongside the thermal feed. A thermal image still needs interpretation in context; a bright patch does not by itself identify a fault or replace an appropriate inspection procedure.
More Than a Flying Camera
DJI’s technical overview describes a combination of low-light sensing and onboard computing intended to keep work moving when lighting, weather or connectivity become difficult. LiDAR and radar add observations that can complement the cameras.
That combination matters to aerial robotics because sensing supports both the inspection job and the aircraft’s awareness of its surroundings. It does not mean the drone can safely handle every obstacle or condition without operator judgment.
Custom AI Moves Into the Aircraft
Open onboard computing gives developers a route to deploy specialised models closer to the sensors. DJI also describes Pilot 2 plugins for custom capabilities, letting organisations adapt the operating interface to their own workflows.
For a utility or survey team, that could connect image collection with an application-specific analysis step. The useful measure is whether the resulting workflow identifies relevant observations consistently, rather than the presence of an AI label alone.
Inspection Robots Need a Complete Workflow
Our grid robotics coverage follows ground-based inspection development, while the Greenland robot expedition shows autonomous platforms gathering environmental observations. The Matrice 5T addresses the aerial side of field data collection.
Its launch brings a new hardware and software option for enterprise teams. Actual endurance, usable sensing range and inspection quality will depend on the task and operating conditions; the next test is performance in the customer’s workflow, not the maximum figures in isolation.
Disclaimer: RobotsBeat is an independent media brand owned and operated by NuvexMedia LLC, publishing news, research, and insights on artificial intelligence, emerging technologies, automation, and related industries. NuvexMedia LLC invests in and collaborates with companies across the AI, Robotics, technology, software, and digital innovation sectors. These relationships do not influence RobotsBeat's editorial coverage, and the publication maintains full editorial independence to provide accurate, timely, and objective information. © 2026 NuvexMedia LLC. All rights reserved. This content is for informational purposes only and should not be considered legal, tax, investment, financial, or other professional advice.
