In a recent study from @ADI_News, researchers demonstrated how tactile sensing can enable robots to perform a complex manipulation task without relying on vision.
In "Touch2Trace", a robotic hand was trained to feed cables through its fingers using tactile feedback and joint-state data, achieving zero-shot transfer to unseen cables and routing conditions.
To collect training demonstrations, operators used @ManusMeta Metagloves Pro to capture finger movements and teleoperate a @Tesollo_Inc DG-5F robotic hand.
Joint-state and tactile data were recorded throughout the process for training.
Read the paper: arxiv.org/pdf/2609.15921#humanoids#humanoidrobotics#humanoidrobot#humanoid
🎬 ROBOTWORLD 2026 Highlights!
Thank you to everyone who visited Tesollo at KINTEX!
We showcased our advanced robotic grippers and humanoid robot hands—and proudly celebrated a Distinction at the 2026 ROBOTWORLD Awards! 🏆
#Tesollo#ROBOTWORLD2026#Robotics#PhysicalAI
🤖 Meet Tesollo at #RoboBusiness2026!
📅 Oct 20–21 | Santa Clara, CA
📍 Booth #812
Explore our Delto Gripper Series with live demos of AI manipulation, teleoperation, and tactile sensing!
See you there! 🚀
#Tesollo#Robotics#PhysicalAI
🤖 Tesollo is heading to RoboBusiness 2026! 🚀
Visit Booth #812 for live demos featuring Touchlab tactile sensing, MANUS teleoperation, AI manipulation & more!
📍 Santa Clara, CA
📅 Oct 20–21
See you there! 😊
#Tesollo#RoboBusiness2026#RoboticGripper
🇩🇪 Meet NEXT robotics, Tesollo’s distributor in Germany! 🤖
In our Global Partner Spotlight interview, we explore their insights on automation and robotics.
Stay tuned for more partner stories! 🌍
#Tesollo#NEXTrobotics#Robotics
In a recent study from @ADI_News, “Touch2Trace,” a robotic hand was trained to feed cables through its fingers using tactile sensing and joint-state feedback, without visual input. By combining a pretrained tactile encoder with imitation learning, the policy demonstrated zero-shot transfer to unseen cables and routing conditions.
To collect demonstrations, operators used MANUS Metagloves Pro to track finger joint angles and teleoperate a @Tesollo_Inc DG-5F hand through a custom retargeting pipeline. Robot joint commands, joint states and tactile data from sensors on the robot’s fingertips were recorded together for training.
Read more: grmmtt.github.io/corl26-touc…
Meet @unboxindustry, Tesollo’s distributor in India 🇮🇳
From product inquiries and demos to purchasing and after-sales support, Unbox Industry helps customers across India explore Tesollo’s robotic hands.
#Tesollo#UnboxIndustry#Robotics
🤖 Meet Tesollo at #IROS2026!
See the Delto Gripper Series in action:
🔹 AI Manipulation
🔹 Repetitive Motion
🔹 Real-Time Teleoperation
📍 Pittsburgh, PA
📅 Sept. 28–30
📌 Booth #314
#TESOLLO#Robotics#RoboticGripper
New bundle: @SenseGlove R1 haptic gloves + @Tesollo_Inc DG-5F-M robotic hand, for teleoperation and imitation learning.
Built for teams doing remote dexterous manipulation.
More details: knoxlabs.com/products/senseg…
NEW RESEARCH: Robot hands can now play the piano!
It involves @amberxie_, @HaozhiQ, and @DorsaSadigh.
Called HandelBot, it is a bimanual system that plays real songs on a real piano using two Tesollo DG-5F dexterous hands, one on a Franka Panda arm and one on an FR3 arm, using only three fingers per hand (index, middle, ring; 9 residual action dimensions per hand).
A policy trained entirely in simulation with RL is adapted to the real piano in two stages:
1. a structured refinement step that repeatedly executes the trajectory, compares the intended key against the key actually pressed, and nudges each finger's lateral joint to correct it.
2. then residual RL that learns fine corrective actions on top.
The arm wrist poses are scripted from sheet music. The only real-world feedback, and the reward, is the keyboard's own MIDI output.
There are no cameras and no tactile sensing.
It replaces collecting large real demonstration sets for millimeter-precise contact tasks.
The DG-5F fingertip (about 2.2 cm) is wider than a piano key (about 2.16 cm), so a single fingertip physically straddles two keys.
Which is why sub-millimeter lateral alignment is the whole game and why the thumb and pinky are dropped, only three fingers per hand fit, and songs must be re-fingered and the hands separated by octaves to avoid arm collision.
The real-world adaptation uses only the keyboard's MIDI output: as the per-finger error signal for the lateral refinement and as the sole RL reward (key-press reward, no fingering or energy terms).
No camera, no touch. The task's own output is a dense, objective reward for free, the cleanest instance of the instrument being the reward function.
For this task, 30 to 60 minutes of real data beats 40 million sim steps deployed directly.
RL trained from scratch on hardware (mean F1 55.8) beats the open-loop sim policy (41.8) on 4 of 5 songs, therefore sim pretraining's value is as an exploration-reducing initialization.
The scope is narrow and honest: five short pieces (16 to 33 s), three fingers per hand, no chords beyond three notes, no thumb, and the hardest piece (Fur Elise) tops out at 66 to 71 F1 with large left-hand jumps as named failures.
Refinement can only fix mis-located presses, not missed ones, and its heuristics are piano-specific (the authors suggest a VLM to generalize the coarse step).
.@ADI_News demonstrates the benefits of wrist-mounted vision for robotic manipulation.
Using Analog Devices' advanced Time-of-Flight sensor and RGB imaging, the robot can accurately judge distances and understand its environment in real time. This enables reliable, precise, and safe manipulation, even when objects move outside the overhead camera's field of view.
Discover more about Analog Devices here: humanoidroboticstechnology.c…#humanoids#humanoidrobotics#humanoid#humanoidrobot