diff --git a/CHANGELOG.md b/CHANGELOG.md
index cbd2a304..a2db4593 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -8,6 +8,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [Unreleased]
 
 ### Fixed
+- **`adaptive_classifier.rs:94` no longer panics on NaN feature values** (closes #611).
+  `sorted.sort_by(|a, b| a.partial_cmp(b).unwrap())` returned `None` and panicked
+  whenever a single `NaN` reached the classifier from real ESP32 hardware (silent
+  DSP div-by-zero, empty buffer). One bad frame killed the entire sensing-server
+  process. Swapped for `unwrap_or(Ordering::Equal)`, matching the pattern the
+  same file already used at lines 149-150 and 155. Per-frame hot path; this was
+  a real production crash vector.
 - **`ui/utils/pose-renderer.js` no longer divides by zero** when two render frames land in the same `performance.now()` tick (issue #519 Bug 2). `deltaTime` is now `Math.max(currentTime - lastFrameTime, 1)` before the `1000 / deltaTime` division, capping displayed FPS at 1000 — far above any real render rate, but finite so the EMA `averageFps = averageFps * 0.9 + fps * 0.1` no longer poisons itself to `Infinity` on a single zero-dt tick.
 
 ### Removed
diff --git a/v2/crates/wifi-densepose-sensing-server/src/adaptive_classifier.rs b/v2/crates/wifi-densepose-sensing-server/src/adaptive_classifier.rs
index b89cb58c..cc652f43 100644
--- a/v2/crates/wifi-densepose-sensing-server/src/adaptive_classifier.rs
+++ b/v2/crates/wifi-densepose-sensing-server/src/adaptive_classifier.rs
@@ -91,7 +91,11 @@ fn subcarrier_stats(amps: &[f64]) -> (f64, f64, f64, f64, f64, f64, f64, f64) {
 
     // IQR (inter-quartile range).
     let mut sorted = amps.to_vec();
-    sorted.sort_by(|a, b| a.partial_cmp(b).unwrap());
+    // partial_cmp returns None on NaN — fall back to Equal so a single NaN
+    // frame from real ESP32 hardware (silent DSP div-by-zero, empty buffer)
+    // can't panic the whole sensing server (#611). The same file already
+    // uses unwrap_or(Equal) at lines 149-150 and 155; this was an oversight.
+    sorted.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal));
     let q1 = sorted[sorted.len() / 4];
     let q3 = sorted[3 * sorted.len() / 4];
     let iqr = q3 - q1;