Texas Instruments

SCUTTLE and TI Edge AI Board

Texas Instruments

Together SCUTTLE + Texas Instruments are empowering the curious with the best hardware & software to build the next generation of Autonomous Robotics.

We're lowering barriers for prototyping & learning with the most advanced embedded machines.  Our partnership with Texas Instruments produced a huge collection of open software & tutorials for embedded machine learning.  Traditionally operating as a business-to-business offering, we won the hearts of TI engineers and they directly addressed eager learners with their Robotics Academy offering step-by-step solutions to get you started with TDA4VM. 

Quick Look

Industrial Application

Blackberry QNX Academy (learn more)


What can you do with Edge AI onboard SCUTTLE?

  • No-mess wiring with the Pi-standard 40-pin header
  • Process 4 or more camera streams in parallel
  • Ditch the Lidar and use solid state, low-energy radar
  • Easily drive 4k graphics on a display while operating the robot
  • Run SLAM at full-resolution

More Tech Details

Integration of the TDA4VM board on SCUTTLE™ opens the door for deep learning at over 4x the speed (8 TOPS) of our last integrated single board computer (Jetson Nano – 1.8 TOPS). Beyond this major uplift in processing power, you the TI processor gains you more operating time with its exceptional power efficiency.

Integrating the TDA4VM on the SCUTTLE platform opens up a wide range of possibilities previously out of reach:

Computer Vision (CV) Processing of multiple simultaneous video streams from SCUTTLE cameras in real time.

Fusing data streams from Wheel Odometry, Lidar, Inertial Measurement Unit (IMU), and Sonar sensors using pre-built software demos

Supercharging your experimentation with the highest efficiency amongst all AI capable Single Boad Computers in class.

Leveraging the world-class engineering capabilities of TI with free support through TI’s E2E community.

Designing a fully functional mobile manipulator, computing kinematics for an arm and base simultaneously.

TI EdgeAI Board Top Down

How does the TDA4VM Development Board stand apart?

Deep Learning Accelerator

A matrix multiplication accelerator on a programmable DSP enables 4K 8-bit and 2K 16-bit fixed multiply accumulate per cycle and power efficiency (fps/watt) that rivals the best in the industry.

Computer Vision Accelerators

Computationally intensive low-level brute-force pixel processing tasks are offloaded to power-efficient hardware accelerators, enabling smaller system footprints and simplified power designs.

Smart Memory & Bus Architecture

A high-bandwidth bus interconnect with a nonblocking infrastructure and large internal memory reduces DDR instances and increases system throughput and power savings.

Functional Safety & Security

Functional Safety-Compliant processors with integrated MCUs help you achieve certifications up to SIL-3, and integrated security features help you reduce system size and cost.

Ready to get started?


See the wiring diagram in our latest wiring guide, get a simplified CAD model,

Check out the video playlist for Edge AI based tutorials & more.


Get details in the board’s User Guide, or grab the TDA4VM gpio Python library for accessing the 40 pin header.


Grab the pre-built Linux image here to go along with the TI robotics academy instructions for TDA4VM on SCUTTLE.


TDA4VM (Edge AI) evaluation module, also called the starter kit (SK). Quick links to the recommended addons: wifi module & wifi antenna.