Arriving early 2022

Hello, meet the new Tac-01

The Tac-01 provides robots with the sense of touch via a synergistic combination of tactile sensors and artificial intelligence for intelligent robot manipulation.

The sensors and our tactile intelligence algorithms will be available soon as a development kit for purchase.

Applications

Sensors to enable the next generation of perception

Our next generation AI-enabled low-latency tactile sensors for robotic and health applications, built upon a decade of research and testing here in sunny Singapore.

Technology

Neuromorphic sensors for a new class of tactile intelligence

We build upon know-how from the fields of bioengineering and computer science to engineer a sensor that mimics the human sensory system.

Tactile Acumen

Our Asynchronously Coded Electronic Skin (ACES) platform, an event-based neuro-mimetic architecture, enables responsive, asynchronous transmission of tactile information for dexterous manipulation tasks that require rapid detection of object slippage and object hardness.

High-Frequency, Low-Latency Data: Tactile stimuli can be transmitted at up to 4 kHz, faster than the average human.
40 Taxels per Sensor: Each sensor has 40 taxels (tactile pixels) arranged in a 8x5 grid to provide good spatial resolution.
Event-based or Synchronous-based Tactile Data: Work with data in the synchronous-based or event-based form.

Raw sensor layer, below the protective "skin"

Taxel representation of right and left fingers, grasping a tomato

A Visual-Tactile Spiking Neural Network architecture developed at the National University of Singapore to fuse tactile and vision event spikes

Tactile Intelligence

Our sensors come integrated with our novel Machine Learning models, which uses data from ACES, for fast and accurate tactile perception.

Smart Self-Calibration: Built-in self-calibration algorithm allows the user to calibrate the sensors easily, even after many cycles of wear and tear.
Slip Detection: The slip detection algorithm is able to recognise when the dynamics of the robot causes the object to slip from the grasp, and react accordingly.
GraspForceNet: Our novel GraspForceNet AI model is used to ensure that the forces applied by the gripper does not deform or damage the objects.

Our smart calibration routine uses three object types to run the calculations: soft, hard, intermediate

Tofu grasping without GraspForceNet (left) and with GraspForceNet (right)

Tac-01 Development Kit

Everything you need to get started

Each set of our development kit comes with a pair of the latest Tac-01 sensors, and access to our tactile intelligence APIs with seamless integrations with various robotic grippers.

Next Generation Hardware

Plug-and-play tactile sensors, with an intelligent built-in self-calibration algorithms to last the lifetime of your toughest applications.

Software SDK

Easy to use software SDK with visualisers, tactile intelligence APIs and C++, Python, ROS and ROS2 integrations. Supported on Windows, Mac and Linux.

Systems Integration

Out of the box integration with Robotiq-2F grippers with our custom drivers for a more responsive control. Support for more types of grippers coming soon.

News & Media

Find out how our technology has applied in various fields

See more →

Nov, 2021 James Dyson Award Award
Home Eye Pressure E-skin Sensor - International Winner: Oct, 2021 IEEE International Conference on Intelligent Robots and Systems (IROS) Award
Extended Tactile Perception: Vibration Sensing through Tools and Grasped Objects (Best Paper Award): Oct, 2021 IEEE International Conference on Intelligent Robots and Systems (IROS) Publication
Extended Tactile Perception: Vibration Sensing through Tools and Grasped Objects

Get notified when we are launching.

We are expecting our first shipments of Tac-01 sensors in early 2022. Subscribe to get the latest product news and updates.

We care about the protection of your data. Read our Privacy Policy.