CASIA adds fingertip tactile sensing to robot peg insertion, raising 0.05 mm success to 67%
Overview
Researchers at the Chinese Academy of Sciences' Institute of Automation add a fingertip tactile sensor to a robot arm's insertion policy, raising success at 0.05 mm clearance from 52% to 67%, according to Pandaily.
The tactile signal feeds only the training critic, while the deployed policy relies mainly on vision. Peak interaction force falls 60% and peak torque falls 44%, per the report. The work uses a Franka Emika Panda arm with a PaXini PX-6AX GEN3 sensor, and the sensor was provided through a research collaboration with PaXini Tech.
The paper, by Long Cheng's team, is accepted at IROS 2026 and posted on arXiv as "From Reach to Insert: Tactile-Augmented Precision Assembly under Sub-Millimeter Tolerances," IT Home reported.
Written by AI from the articles below · updated Nov 1, 9:22 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- PandailyNewsCASIA adds fingertip touch to robot insertion, lifting 0.05 mm success from 52% to 67%
AIResearchers at the Chinese Academy of Sciences' Institute of Automation add a fingertip tactile sensor to a robot arm's insertion policy, raising success at 0.05 mm clearance from 52% to 67%. The tactile signal feeds only the training critic, while the deployed policy relies mainly on vision, and peak interaction force falls 60% and peak torque falls 44%. The work, accepted at IROS 2026, uses a Franka Emika Panda arm with a PaXini PX-6AX GEN3 sensor.
Heat Trend
- Current comparable heat
- 6
- Peak comparable heat
- 10Nov 1, 10:00 PM ET
- Change in past 24 hours
- –
The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.