RadarGuard

mmWave cobot safety system — build logs from bringup through field testing.

Real-time human presence detection and collision avoidance for robot arms, built around the IWR6843AOP and a swept-volume safety pipeline. These are the build logs, in order — bringup, bugs, and the fixes that came out of them.

Swept-volume workspace clipper — the sensor finally knows what the arm can reach

This part teaches the safety system the arm’s reachable envelope, so detections the arm can’t physically reach stop triggering stops. The safety zones stop being uniform spheres and start being shaped to what the arm can actually threaten.

Micro-doppler classifier — not everything that moves is a person

This part adds a layer that tells a walking person apart from a box on a cart before the detection reaches the zone logic — so the system stops crying wolf at harmless objects, without ever being able to miss a real person.

Persistent background map — the sensor shouldn't relearn the room every boot

The startup background-learning phase is necessary — but only once. Phase 5 makes the learned map persist across reboots, and closes the loophole where a person standing still long enough could be quietly absorbed into the background.

Full safety stack live — background learning, ego-motion compensation, and the motionless person problem

The IWR6843AOP is now running a complete ROS 2 safety pipeline on the Jetson — CLEAR/CAUTION/STOP zone detection with ego-motion compensation, voxel background learning, fault handling, and a heartbeat watchdog. One non-obvious bug dominated the session: velocity filtering was silently eating motionless people.

TLV frames live on the Jetson — wrong firmware was the whole problem

Two days chasing a sensor that accepted every config command, then emitted 16 bytes of 0xFF. Root cause: ISK firmware on AOP hardware. The fix was one file.

sensorStart Error -1 — the chirp was running outside the 60–64 GHz band

All 12 calibrations passed. Sensor State 1. Then nothing. The chirp engine silently refused to run because the end frequency exceeded the regulatory band by 750 MHz.

IWR6843AOPEVM arrived — bringup notes and the mmWave Studio trap

EVM in hand, USB detection working immediately. mmWave Studio looked like the obvious next step. It was a trap — the AOP standalone board can’t connect. UniFlash is the right tool.