Set up radar sensing for contactless heart rate, breathing rate, presence, and distance measurements. It covers supported hardware, firmware, and combining radar with WiFi CSI, sensing data derived from wireless signals, for shared readings and 3D views.
Set up and run RuView mmWave / FMCW radar sensing — ESP32-C6 + Seeed MR60BHA2 (60 GHz, heart rate / breathing rate / presence) and HLK-LD2410 (24 GHz, presence + distance), plus mmWave↔WiFi-CSI sensor fusion (48-byte fused vitals, MR60BHA2/LD2410 auto-detect, v0.5.0+). Use when the deployment includes a millimetre-wave radar alongside or instead of WiFi CSI.
Review the instructions the agent will receive before you install.
The radio side-channel: 60 GHz and 24 GHz FMCW radar, standalone and fused with WiFi CSI.
| Device | Port | Band | Provides | ~Cost |
|---|---|---|---|---|
| ESP32-C6 + Seeed MR60BHA2 | COM4 (typical) | 60 GHz FMCW | Heart rate, breathing rate, presence | ~$15 |
| HLK-LD2410 | — | 24 GHz FMCW | Presence + distance (gated zones) | ~$3 |
The C6 is RISC-V and can run the radar pipeline; it is not a WiFi-CSI node (use an ESP32-S3 for CSI). LD2410 is a UART module wired to a host or to the C6.
The ESP32 firmware auto-detects an attached MR60BHA2 or LD2410 and emits 48-byte fused vitals records (CSI-derived + radar-derived, reconciled). Binary is ~12 KB larger than the CSI-only build. Build/flash as in ruview-hardware-setup (Windows: Python-subprocess; ESP-IDF v5.4 ≠ Git Bash). Recommended stable firmware tag: v0.5.0-esp32 or later — see docs/user-guide.md release table.
# Provision the radar/fusion node (same provision.py; the firmware probes for the radar on boot)
python firmware/esp32-csi-node/provision.py --port COM8 --ssid "WiFi" --password "secret" --target-ip 192.168.1.20
# Confirm: serial monitor should report which radar was detected and start emitting fused vitals
python scripts/mmwave_fusion_bridge.py # bridges radar HR/BR + CSI → unified spatial model
node scripts/passive-radar.js # passive-radar style processing for exploration
The 3D point-cloud demo fuses camera depth (MiDaS) + WiFi CSI + mmWave radar → unified spatial model (~22 ms pipeline, 19K+ pts/frame; ADR-094). Drive it with scripts/mmwave_fusion_bridge.py plus the point-cloud front-end.
examples/medical/README.md.| Situation | Prefer |
|---|---|
| Contactless vitals, subject stationary, line of sight | MR60BHA2 (cleaner HR/BR than CSI alone) |
| Cheap, robust presence / occupancy in a defined zone | LD2410 (or LD2410 + CSI) |
| Through-wall presence / activity, no line of sight | WiFi CSI (mmWave doesn't penetrate walls) |
| Pose / skeletons | WiFi CSI (WiFlow) — mmWave doesn't do this here |
| Highest-confidence vitals | Fusion — 48-byte fused vitals reconcile CSI + radar |
| Volumetric 3D | Fusion — camera depth + CSI + mmWave point cloud |
README.md, docs/user-guide.md (release table — v0.5.0 mmWave fusion notes, binary sizes)scripts/mmwave_fusion_bridge.py, scripts/passive-radar.jsexamples/medical/README.md (60 GHz mmWave vitals)ruview-verifyNo reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Build advanced AgentDB workflows with database synchronization, multiple databases, and search that combines meaning with attribute filters. Covers similarity measures, diverse search results, and operational patterns for distributed AI applications.
Create AgentDB learning plugins that use recorded experience to improve agent decisions. Choose a learning method, store states, actions, and rewards, train models, and evaluate suggested actions through CLI and API workflows.
Build AI agents that retain conversation history, user preferences, and useful interaction patterns with AgentDB. The skill covers persistent storage, meaning memories survive between sessions, plus retrieval, context management, and ReasoningBank integration.
Tune AgentDB memory use and search speed through quantization, which stores vectors more compactly, search indexes, caching, and batch operations. Includes configuration examples and benchmarks to help balance accuracy, speed, and storage as datasets grow.
Build document search with AgentDB that finds related content by meaning. Store documents as numerical representations, combine similarity search with metadata filters, and retrieve relevant passages for systems that generate answers using source material.
Automate browser tasks with agent-browser, using snapshots that label page elements for the agent. Handle login flows, fill and submit forms, extract page information, and capture screenshots through a repeatable navigation and interaction workflow.