Robot Talk · 21 Sept 2026 · 20m
Vladimir Ivan, Vice President of Robotics at Touchlab, explains how his company develops e-skins to give robots the sense of touch, moving beyond visual-only perception. He details their new product, Tacto, a generalizable tactile fingertip with 16 sensing elements that detects pressure, vibration, and texture to enable dexterous manipulation in healthcare and manufacturing. Ivan discusses the engineering trade-offs between material robustness and sensitivity, highlighting the sensor's ability to withstand abuse while maintaining high-resolution data for AI-driven robot control.
Where this conversation describes AI being used to build or deliver a product. Part of the AI in practice tracker.
Engineering & simulation
Touchlab trained AI models to interpret raw data from their tactile fingertips, enabling the detection of specific object properties like ripeness and texture.
“one of the really exciting things that we've been doing with these sensors is training AI models to interpret this data and we have some really exciting sleep detection that we've been we've been trying out with picking up ice cubes and picking up fresh produce, ripe blueberries.”
Speaker 2 · Hear it at 6:13
early-stage companies
Other shows on the same ground, closest first.
Professor Gordon Cheng of the Technical University of Munich explains his development of event-driven e-skins for humanoid robots, using off-the-shelf sensors to create a low-power, autonomous touch system that improves safety and enables brain-machine interface applications. He discusses the challenges of scaling sensor data, the move from conventional control to neuromorphic event-based processing, and the potential for sensory substitution in prosthetics. The episode also features commentary from Dr. Giulia D’Angelo and Professor Ralph Etienne-Cummings on the definition of neuromorphic engineering and the current state of the industry.
Youssef Benmokhtar, CEO of GelSight, explains how his company is digitizing the human sense of touch using imaging-based tactile sensors to solve quality inspection challenges in manufacturing. He details the technology's origin at MIT, its ability to measure micron-scale surface features and roughness, and its application in aerospace for characterizing scratches, dents, and radii on engine blades and airframes. Benmokhtar also discusses the concept of 'perceptual quality,' where AI analyzes tactile data to replace subjective human grading of textures, and outlines future applications in surgical robotics and haptic feedback systems.
Professor Gordon Cheng of the Technical University of Munich explains his development of event-driven e-skin for humanoid robots, using off-the-shelf sensors and neuromorphic communication to enable safe, autonomous physical interaction. He details how hexagonal sensor patches covering the robot's body transmit only change-based events to avoid data overload, allowing the robot to sense proximity, force, temperature, and vibration. The discussion with Dr. Giulia D’Angelo and Professor Ralph Etienne-Cummings explores the distinction between device-level and system-level neuromorphic engineering, the challenges of scaling such technology, and its applications in brain-machine interfaces and prosthetics.
Daniel and Forbode discuss a team from MIT, including lead author Sandra Lou, who developed the 'Gel Palm' robotic hand to address the lack of tactile feedback in current robotic designs. The system combines a semi-flexible endoskeleton with a soft gel layer and uses embedded LEDs and Raspberry Pi cameras to reconstruct 3D geometry and pressure data from reflected light. The hosts highlight the platform's ability to handle delicate objects safely and its potential application in creating more human-like prosthetics, noting the use of off-the-shelf components like Adafruit LEDs and 3D printed molds.
Hosts Daniel and Forbode discuss two recent engineering breakthroughs inspired by biology. First, they cover research from the University of Michigan on 'RAILS' (Robust Adversarial Immune-inspired Learning System), which uses B-cell immune system logic to make AI image classifiers robust against adversarial attacks. Second, they analyze electronic skin developed by Pohang University of Science and Technology (POSTECH) and UNIST, which mimics human nerve pathways to achieve low-latency tactile sensing for robotics and prosthetics.
The summary, chapters and topics are generated from the episode’s audio by this directory, not written by Robot Talk. The episode itself belongs to its publisher.