DexTeleop-0: Force-Aware Bimanual Dexterous Teleoperation with Ego-Centric Perception towards Shared Autonomy
DexTeleop-0: Force-Aware Bimanual Dexterous Teleoperation with Ego-Centric Perception towards Shared Autonomy
This research introduces DexTeleop-0, a system that enhances bimanual dexterous manipulation through tactile-driven adaptation. By integrating fingertip feedback into teleoperation pipelines, the framework performs real-time optimization to correct contact forces and positions. Evaluated in both simulation and real-world hardware, the system achieves 91% success rates for Ball Assembly and 62% for Stir in Cup tasks, outperforming force tracking alone. The project is open-sourced at https://henryhcliu.github.io/dexteleop-0.
The study presents DexTeleop-0, a tactile-driven adaptation strategy for bimanual dexterous teleoperation that achieves 91% success in simulated Ball Assembly tasks and 62% in Stir in Cup tasks by combining human tracking with robot-side contact corrections.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Control
- TeleoperatedOpen source S1
Reported numbers
Reported success rate
91%
Reported trials
View original evidence
predicted-contact-moment regularization, and bounded hand-joint residuals. We evaluate this tactile-driven adaptation strategy across both simulated environments and real-world hardware. Controlled simulation replay yields final-stage success rates of 91% for Ball Assembly and 62% for Stir in Cup, versus 88% and 49% for force tracking alone. Fixed-input replay on two hand types, seven-operator teleoperation, and exte
Open source S4Reported success rate
62%
Reported trials
View original evidence
predicted-contact-moment regularization, and bounded hand-joint residuals. We evaluate this tactile-driven adaptation strategy across both simulated environments and real-world hardware. Controlled simulation replay yields final-stage success rates of 91% for Ball Assembly and 62% for Stir in Cup, versus 88% and 49% for force tracking alone. Fixed-input replay on two hand types, seven-operator teleoperation, and exte
Open source S4robots
2
View original evidence
predicted-contact-moment regularization, and bounded hand-joint residuals. We evaluate this tactile-driven adaptation strategy across both simulated environments and real-world hardware. Controlled simulation replay yields final-stage success rates of 91% for Ball Assembly and 62% for Stir in Cup, versus 88% and 49% for force tracking alone. Fixed-input replay on two hand types, seven-operator teleoperation, and exte
Open source S4operators
7
View original evidence
predicted-contact-moment regularization, and bounded hand-joint residuals. We evaluate this tactile-driven adaptation strategy across both simulated environments and real-world hardware. Controlled simulation replay yields final-stage success rates of 91% for Ball Assembly and 62% for Stir in Cup, versus 88% and 49% for force tracking alone. Fixed-input replay on two hand types, seven-operator teleoperation, and exte
Open source S4tasks
2
Reported trials
View original evidence
predicted-contact-moment regularization, and bounded hand-joint residuals. We evaluate this tactile-driven adaptation strategy across both simulated environments and real-world hardware. Controlled simulation replay yields final-stage success rates of 91% for Ball Assembly and 62% for Stir in Cup, versus 88% and 49% for force tracking alone. Fixed-input replay on two hand types, seven-operator teleoperation, and exte
Open source S4
- code: not_reported
- weights: not_reported
- dataset: not_reported
- paper: not_reported
What remains unknown
Not established in the collected evidence: Environment, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
predicted-contact-moment regularization, and bounded hand-joint residuals. We evaluate this tactile-driven adaptation strategy across both simulated environments and real-world hardware. Controlled simulation replay yields final-stage success rates of 91% for Ball Assembly and 62% for Stir in Cup, versus 88% and 49% for force tracking alone. Fixed-input replay on two hand types, seven-operator teleoperation, and exte
Open source S4
DexTeleop-0: Force-Aware Bimanual Dexterous Teleoperation with Ego-Centric Perception towards Shared Autonomy
Open source S1
rnal-force traces further assess contact assistance. The open-sourced project page can be found at https://henryhcliu.github.io/dexteleop-0.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org