Free e-book: IEEE 802.15.4ab vs IEEE 802.15.4z

A door chime doesn't save a sleeping child. Sensing one does

Q: How does UWB radar detect a child in a car?

UWB radar detects a child by operating in sensing mode - emitting impulses and reading the reflections from the cabin to perceive movement, including the micro-movement of breathing. Because it senses respiration rather than only gross motion, it can detect a child who is asleep and still, where door-sequence reminders and basic motion sensors fail. needCode pairs this with edge AI classification to confirm a child rather than an object.

Q: Can it detect a sleeping or completely still child?

Yes - detecting a still, sleeping child is the core reason to use radar, and UWB radar does it by sensing the tiny chest movement of breathing. A child who isn't moving still breathes, and that signal is what the system reads, which is exactly the case that defeats motion- and weight-based approaches. This is the difference between reminding a driver and actually detecting the child.

Q: How is this different from a seatbelt or door reminder?

A reminder relies on indirect logic - a door opened, a seatbelt unbuckled - and assumes the driver simply needs prompting, so it cannot detect a child no one remembered. Direct sensing detects the child itself, which is why Euro NCAP scores it well above indirect reminders. needCode builds the direct-sensing approach, using UWB radar and AI classification.

Q: Does UWB child presence detection meet Euro NCAP?

UWB radar child presence detection is built for Euro NCAP's direct-sensing assessment, which rewards detecting the occupant over indirect reminders. needCode develops the firmware and classification with that assessment in mind and supports validation and readiness, though the exact scoring and timeline should be confirmed against the current Euro NCAP protocol. Direct sensing is the category Euro NCAP scores most highly.

Q: How do you avoid false alarms from a coat, a pet, or a phone?

False alarms are handled with edge ML classification that interprets the radar signature to distinguish a child from a pet, a bag, a coat, or an empty seat, rather than triggering on any movement. A reliable system has to reject these cases, because a CPD feature that cries wolf gets switched off. needCode's UWB-plus-edge-AI approach is built specifically to keep false alarms low.

Q: Why UWB radar instead of a 60GHz radar, a camera, or a PIR sensor?

Each has trade-offs: 60GHz mmWave radar is a mature, high-resolution dedicated sensing technology; cameras raise privacy concerns; and PIR motion sensors miss a still child. UWB radar's distinct advantage is that it can reuse a UWB radio a vehicle may already carry for digital key, adding child presence as a largely software and sensing feature on one multi-function node - and it senses presence without a camera. needCode helps weigh UWB against 60GHz for a given programme rather than claiming one always wins.

Q: Can one sensor do child presence and other functions?

Yes - a single UWB sensing node can serve child presence, seat occupancy, seatbelt-reminder logic, and intrusion detection together, instead of a separate sensor per function. This consolidates several safety features onto one radio and one integration, reducing BOM and complexity. needCode designs the node to cover the functions a programme needs.

Q: Is UWB radar presence detection privacy-preserving?

Yes - UWB radar senses movement and presence rather than capturing images, so it can detect a person, and even vital signs, without a camera in the cabin or the room. That makes it suitable for privacy-sensitive settings such as vehicle interiors, bedrooms, and eldercare. needCode treats this no-camera property as a core advantage of radar sensing.

Q: Can UWB radar do vital-sign or breathing monitoring?

Yes - the same micro-movement sensing that detects a child's breathing can be used for contactless vital-sign monitoring, including respiration and movement, in healthcare and eldercare settings. It enables fall detection and bed-occupancy sensing without a wearable on the patient. needCode builds these from the same UWB sensing and edge-AI foundation.

Q: Which chipsets support UWB radar sensing?

needCode works with sensing-capable UWB silicon, including Qorvo QM33 and QM35, alongside platforms from NXP, ST, and Infineon, building on IEEE 802.15.4ab sensing capabilities. As a certified Qorvo partner with nine hardware-platform bring-ups completed, needCode starts from chipset-level knowledge. The right part depends on whether the radio is shared with a digital-key or positioning function.

needCode builds in-cabin child presence detection on UWB radar - sensing a living presence by its breathing and micro-movement, so a sleeping or covered child is detected where a door-sequence reminder is not. Euro NCAP direct-sensing aligned, AI-classified to reject false alarms, and able to share a single sensing node across child presence, seatbelt reminder, and intrusion. From a certified Qorvo partner with deep UWB engineering.

Book a discovery call

How UWB radar detects a child

We work with Industry Leaders

Reminders assume the driver forgot. The dangerous case is the one no one remembers.

Most in-cabin safety systems are reminders - they chime based on a door-and-seatbelt sequence, on the assumption that the driver simply needs prompting. The cases that cause tragedies are different: a child left asleep, quiet, sometimes covered, that no sequence logic and no simple motion sensor reliably detects. Euro NCAP has recognised this, scoring direct sensing of the child well above indirect reminders.

Direct sensing is a radar problem. UWB radar can detect the micro-movement of breathing, which means it can find a still, sleeping child where motion and weight sensors miss them - then pair that signal with AI classification to tell a child from a coat, a pet, or an empty seat. needCode builds exactly that, on the UWB depth in-cabin sensing depends on.

Detects breathing, not just motion

UWB radar senses the micro-movement of respiration - so a sleeping, still child is detected rather than missed.

Euro NCAP direct-sensing aligned

Built for the assessment that scores detecting the child above reminding the driver.

One node, several functions

The same UWB radar covers child presence, seatbelt reminder, and intrusion - fewer parts, one integration.

How UWB radar detects a child

In-cabin presence detection is a sensing-and-AI problem in four parts. We build all four.

UWB Radar Sensing

UWB operates as an impulse radar, illuminating the cabin and reading reflections - not ranging to a tag, but sensing the space itself. IEEE 802.15.4ab adds the sensing capabilities this builds on, turning a positioning radio into a perception sensor.

Ultra-Wideband

Micro-Movement & Vital-Sign Detection

The radar resolves the tiny chest motion of breathing - the signal that separates a living presence from an object, and the reason it detects a child who is asleep and otherwise still. This is why radar succeeds where motion and weight sensors fail.

AI Classification

Edge ML interprets the radar returns to tell a child from an adult, a pet, a bag, or an empty seat - the layer that turns a raw signal into a reliable decision and keeps false alarms low. A radar return is only useful once it's classified.

Single-Node Multi-Function

One UWB sensing node serves child presence, seat occupancy, seatbelt-reminder logic, and intrusion detection - consolidating several safety features onto one radio and one integration instead of a sensor per function.

Multi-Protocol / Coexistence

Building child presence detection or radar sensing?

Book a discovery call with our CEO

Book a discovery call

Beyond the cabin: where presence sensing goes.

The same UWB radar that finds a child in a car senses human presence and vital signs anywhere - and, because it reads movement rather than images, it does so without a camera. The capability extends well past automotive.

Automotive Child Presence

In-cabin child presence, seat occupancy, and intrusion to Euro NCAP direct-sensing - the flagship, regulation-driven application.

Automotive & SDV

Smart Home Occupancy & Security

Presence-based lighting, HVAC, and intrusion detection that works in the dark and through stillness, where PIR motion sensors drop out - without a camera in the room.

Healthcare & Eldercare Monitoring

Contactless vital-sign monitoring - breathing and movement - plus fall and bed-occupancy sensing, without a wearable on the patient or a camera on the room.

Industrial IoT & RTLS

Building Presence & Intrusion

People-presence and intrusion sensing for secure and smart buildings - single-sensor, and privacy-preserving where a camera isn't acceptable.

Why presence-detection teams bring in needCode

UWB radar depth, not just ranging

Most UWB work is ranging and positioning; in-cabin sensing is radar - a distinct discipline. As the largest dedicated UWB team in Central Europe, we work across both, including the IEEE 802.15.4ab sensing capabilities presence detection is built on.

Detection plus classification

A radar return is only useful once it's classified. We pair UWB sensing with edge ML so the system reliably distinguishes a child from a false alarm - the difference between a safety feature and a nuisance that gets switched off.

One radio you may already have

If a vehicle carries UWB for CCC digital key, child presence detection can run largely as a sensing-and-software addition on the same radio - consolidating child presence, occupancy, seatbelt, and intrusion onto one node and cutting BOM against multiple single-purpose sensors.

Certified Qorvo partner

Direct access to UWB silicon (QM33 / QM35) and roadmap, including sensing-capable parts, so your bring-up starts ahead of the public SDK.

Four ways to bring needCode in

From a sensing feasibility study to a standing team. We match the engagement to where the system is.

01 Feasibility & Sensing Study

Duration:
2–4 weeks
Best for:
Validating radar-sensing feasibility and a detection/classification approach for your cabin or space
Deliverable:
Feasibility assessment, sensing/classification approach, integration path, leadership readout

02 Detection & Classification Build

Duration:
Phased
Best for:
Building the UWB radar firmware and edge-ML classification on target silicon
Deliverable:
Sensing firmware, trained classifier, test results, demo

03 Productization & Euro NCAP Readiness

Duration:
Phased
Best for:
Taking a prototype to production firmware and assessment readiness
Deliverable:
Hardened firmware, validation, conformity and Euro NCAP readiness support

04 Embedded Team

Duration:
Multi-year, retainer-based
Best for:
Product teams who want a dedicated UWB-sensing and edge-AI squad
Deliverable:
An embedded team in your cadence - the model behind the 30-FTE Qorvo programme

What we ship on

We pick the silicon and stack that match your sensing target and environment.

Sensing

UWB radar (IEEE 802.15.4ab sensing)

impulse radar

micro-movement / vital-sign detection

AI

Edge ML classification

sensor fusion

on-device inference

Ambiq Apollo

Google Coral / Astra

Silicon

Qorvo QM33 / QM35 (sensing-capable)

NXP

STMicroelectronics

Infineon

legacy DW3000

Functions

Child presence

seat occupancy

seatbelt reminder

intrusion

vital-sign monitoring

Standards & assessment

Euro NCAP direct-sensing

FiRa

IEEE 802.15.4ab

RTOS

Zephyr

FreeRTOS

ThreadX

Case studies

needCode doesn't publish named child-presence programmes. What we can show is the UWB and edge-AI capability presence sensing is built on.

Qorvo: RF Leadership

Context: Rapid scaling for new chipset bring-up.

Scale: Grew from <10 to 30 FTEs.
Output: Supported bring-up of 9 new hardware platforms (SDKs, Drivers, Stacks).
Retention: Zero-churn core team retained for 5+ years.

Dedicated Development Center for RF Solutions

Bluetooth Mesh Smart Lighting Control System

Smart Lighting: Core R&D Extension

Context: Client needed deep, specialized expertise to pivot from proprietary tech to a new global standard.

Service: Deployed a dedicated squad of embedded engineers to function as the client's core R&D team.
Output: Co-authored official Bluetooth SIG protocols and delivered the world’s first certified BLE Mesh stack.
Value: Enabled the client to secure Series A funding and defined the industry standard for smart buildings.

Creative Werks: Innovation rescue

Context: Hardware obsolescence threatened production shutdown.

Action: Full-stack takeover (PCB redesign + Firmware + Mobile App).
ROI: 1230% ($1.6M value generated).
Speed: Payback period of 2–3 months.

NeedCode-case study - IoT Solution for Boat Lift Modernization - cover2s

PowerPollen: AgTech automation

Context: Lack of internal expertise stalled a critical automation project.

Action: Re-architected system using unified MCU and ISOBUS standards.
ROI: 13.8x ($2.9M value generated).
Impact: Enabled $1.9M increase in harvester value.

Strategic Partnership

needCode is an official business partner of Qorvo, bringing over 8 years of proven expertise and trusted service to the technology sector.

Check our performance

Members of the UWB Alliance

In 2025 we became a member of the UWB Alliance. This strategic step reinforces our commitment to pioneering Ultra-Wideband (UWB) technology.

Proudly Certified for Excellence and Security

needCode is officially certified for:
ISO 9001:2015 – Quality Management
ISO/IEC 27001:2022 – Information Security

ISO certifications reflect our focus on delivering reliable IoT solutions, smart product development, and secure technology services.

Testimonials

“I think the key takeaway from needCode is their ability to adapt and understand the customer's requirements. That took away probably a large portion of what could have been a lot of development time and expense for both companies.”

Bob Folkestad

President at Creative Werks

“One aspect that truly sets needCode apart is its profound expertise in firmware development. Their proficiency in various programming languages, embedded systems and hardware architecture is truly impressive. When faced with difficult problems, their strong problem-solving skills and analytical mindset shine through, allowing them to overcome obstacles with remarkable ease.”

Semeh Sarhan

CEO at Xtrava

“I worked with needCode while leading the NWTN-Berlin team in 2018. A big chunk for our FW development has been outsourced to them and they had proven to iterate very quickly, following specs and deliver on time. It was great working with them. I recommend working with needCode’s team on any Embedded SW development.”

Marco Salvioli Mariani

CTO at NWTN Berlin GmbH

“needCode Team proved to be one of the best engineers I have ever met. The part I like the most about the team is the more difficult an obstacle seems to be, the more motivated they were to find a solution and a way forward.”

Szymon Słupik

CTO at Silvair

“needCode is an outstanding partner. Their quick follow-up, scalability, and extensive professional network set them apart. Their expertise in wireless technologies has been valuable, supporting us from low-level drivers to architecture discussions.”

Tim Allemeersch

Director at Qorvo, Inc.

“needCode did a great job improving the firmware of the Vai Kai connected toys and developing new features, surpassing our expectations multiple times. I would definitely recommend hiring Bartek and needCode for the embedded software projects!”

Matas Petrikas

CEO & Co-founder at Vai Kai UG

Insights

Docker and Dev Containers for Embedded: Killing “Works on My Machine”

Every embedded team has lived through some version of the same conversation. A developer pushes a change that builds cleanly on their machine. The CI build fails. The developer pulls the failing log, cannot reproduce the failure locally, and spends two hours establishing that the CI is using a slightly different version of the ARM […]

Documentation as a product: how good SDKs treat docs as code

The deliverable customers interact with most often is the one most commonly treated as a secondary artifact. Six document types, six audiences, and one release gate that fixes most of the failure modes. A semiconductor SDK can have an exemplary architecture, a thoughtfully versioned C API, a security framework that maps cleanly to PSA Certified […]

FAQ