Kavana

NASDAQ: WLDS

NASDAQ: WLDS

Investor Relations

Investor Relations

Captures Hand Pose, Force and Intent where cameras can't

Captures Hand Pose, Force and Intent where cameras can't

Captures Hand Pose, Force and Intent where cameras can't

Start a data program

See the fusion

Kavana™ sensing technology | Wearable Devices Ltd.

Kavana™ sensing technology | Wearable Devices Ltd.

Kavana™ sensing technology | Wearable Devices Ltd.

Start a data program

See the fusion

13 Patents

13 Patents

7 granted Patents + 6 pending Patents

7 granted Patents + 6 pending Patents

surface EMG · neural input

surface EMG · neural input

12+ yrs

12+ yrs

surface EMG R&D

surface EMG R&D

Wearable Devices Ltd.

Wearable Devices Ltd.

4

4

product generations

consumer-proven hardware

consumer-proven hardware

The Challenges

The Challenges

The Challenges

What cameras miss, EMG captures

What cameras miss, EMG captures

What cameras miss, EMG captures

Dexterous manipulation is a bottleneck in robotics. Today it’s captured with vision alone - egocentric and palm cameras - which fail in different ways:

01

01

Occlusions

Tools, hands, and equipment frequently block camera views during real-world tasks, causing critical loss of tracking data.

Tools, hands, and equipment frequently block camera views during real-world tasks, causing critical loss of tracking data.

02

02

Reflections and glare

Reflective surfaces, glare and low light degrade tracking exactly where real work happens.

03

03

Force is invisible

Force is invisible

No camera measures newtons. Grip, pressure and effort simply are not in the frame at any resolution.

No camera measures newtons. Grip, pressure and effort simply are not in the frame at any resolution.

04

04

Motion blur

Vision can only register a movement once it exists. The command that caused it has already happened.

Vision can only register a movement once it exists. The command that caused it has already happened.

05

Out of FOV

Hands constantly leave the camera’s field of view - reaching, turning, working below the table edge. Every exit is a gap in the data.

06

Hardware overhead

Extra cameras, mounts and calibration add cost and setup time to every session - and still miss what happens inside the grip.

Use Kavana to scale up

Use Kavana to scale up

Use Kavana to scale up

Fuse our EMG-based neural wristband with any egocentric camera array. No gloves, no line-of-sight dependency, no additional rigs.

Fuse our EMG-based neural wristband with any egocentric camera array. No gloves, no line-of-sight dependency, no additional rigs.


Start a data program

Train on the right Data, not on a partial snapshot

Train on the right Data, not on a partial snapshot

Papers comparing vision-only with vision + touch

36 head-to-head comparisons · grey = before VLAs

3

2023 · VLAs introduced

5

11

17

2018–22

2024

2025

2026

2018, 2019 and 2022: one paper each, pooled.

Touch uplift: success with touch ÷ vision-only

Median · whiskers = interquartile range

3.0×

2023 · VLAs introduced

2.0×

1.8×

2.2×

2018–22

2024

2025

2026

Our Hardware

Our Hardware

Our Hardware

Two bands, one platform. Mudra Ultimate is the research-grade capture band for physical-AI data programs. Mudra Pro is the light, everyday band for research labs and academic groups.

3 EMG channels · launched May 2026

3 EMG channels · launched May 2026

Mudra Pro

Mudra Pro

Light, ergonomic and quick to fit - on in seconds and comfortable through long sessions. Cable or on-device SD capture. Built for research labs, academic groups and exploration.

8 EMG channels · research-grade

8 EMG channels · research-grade

Mudra Ultimate

Mudra Ultimate

Full-forearm coverage for spatial decomposition, Wi-Fi streaming and multi-sensor sync out of the box. Built for physical-AI companies running data collection at scale.

Specs

Specs

Specs

Mudra Pro

Mudra Ultimate

General

Mudra Pro

Mudra Ultimate

Weight

38g

43g

Fit

adjustable fit

adjustable fit

EMG

Mudra Pro

Mudra Ultimate

Channels

3 ch

8 ch

Sample rates

200 · 400 · 800 · 1600 · 2133 · 3200 · 4267 · 6400 Hz

500 · 1000 · 2000 · 4000 Hz

Noise floor

TBD

3.0 µVrms

at 500 Hz

4.1 µVrms

at 1000 Hz

6.1 µVrms

at 2000 Hz

12.5 µVrms

at 4000 Hz

DRL

Included

Included

Resolution

24 bit

24 bit

IMU

Mudra Pro

Mudra Ultimate

Type

6-DoF

6-DoF

Resolution

16 bit

16 bit

Sample rate

25 · 50 · 100 · 200 · 400 · 800 · 1600 Hz

25 · 50 · 100 · 200 · 400 · 800 · 1600 Hz

Gyroscope range

±500 dps

±500 dps

Accelerometer range

±4 g

±4 g

PPG

Mudra Pro

Mudra Ultimate

Sampling rates

25 · 50 · 100 · 200 · 400 Hz

25 · 50 · 100 · 200 · 400 Hz

Resolution

24 bit

24 bit

Connectivity

Mudra Pro

Mudra Ultimate

Data streaming

USB-C + BLE

USB-C + BLE / Wi-Fi

Internal SD

Optional

Optional

Software

Mudra Pro

Mudra Ultimate

SDK

Python · C++

Python · C++

Features

Fully Agentic · Lab Streaming Layer (LSL)

Fully Agentic · Lab Streaming Layer (LSL)

Platforms

Windows · macOS · Linux

Windows · macOS · Linux

Join us in building the

human layer of physical AI.

Join us in building thehuman layer of physical AI.

Join us in building the

human layer of physical AI.

How a programme runs

Step 1

Step 1

Scope

Scope

One call to define the task, the modalities and what “better” looks like measurably. We'll tell you if we're the wrong tool.

One call to define the task, the modalities and what “better” looks like measurably. We’ll tell you if we’re the wrong tool.

Step 2

Step 2

Pilot

Pilot

A bounded recording - tight protocol, small subject count, synchronised to your streams. You train on it and we both read the result.

A bounded recording - tight protocol, small subject count, synchronised to your streams. You train on it and we both read the result.

Step 3

Step 3

Scale

Scale

If the pilot moves the metric, we scale subjects, sites and session hours - we scale with you.

We reply within two working days. No newsletter.

Kavana is the physical AI unit of Wearable Devices Ltd. (Nasdaq: WLDS)