Adaptive Hybrid Force-Vision Control with EMG-Derived References for Deformable Bottle Manipulation
Adaptive Hybrid Force-Vision Control with EMG-Derived References for Deformable Bottle Manipulation
This paper presents an adaptive hybrid vision-force controller for robotic manipulation of deformable laboratory squeeze bottles. The system integrates force and vision feedback based on interaction states to handle bottle deformation and recovery. Human demonstrations were collected via electromyography (EMG) sensing, mapped to desired grip forces, and used as references for the controllers. Validation across 12 condition combinations (varying target dispense volumes, plastic bottle types, and squeeze counts) showed that the proposed controller achieved a mean absolute error of 6.54 mL compared to 15.92 mL for a pure force controller, while more closely replicating human actions recorded from EMG signals.
The study validates an adaptive hybrid vision-force controller against a pure force baseline using EMG-derived references on 12 condition combinations, reporting a mean absolute error of 6.54 mL versus 15.92 mL for liquid dispensing in deformable squeeze bottles.
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.
Reported numbers
mean absolute error (MAE)
6.54
View original evidence
1 to 3 squeezes used to dispense. Human demonstrations of these operating conditions were collected using electromyography (EMG) sensing mapped to a desired grip force, which was then used as the force reference for the controllers to squeeze the bottles. Results demonstrated that the proposed adaptive hybrid vision-force controller achieved more accurate liquid dispensing with a mean absolute error (MAE) of 6.54 mL
Open source S4mean absolute error (MAE)
15.92
View original evidence
compared to a MAE of 15.92 mL from the pure force controller, while also replicating the human action recorded from the EMG signal more closely.
Open source S5target dispense volumes
2
View original evidence
ate laboratory squeeze bottles to dispense liquid. This approach integrates force and vision feedback according to the interaction state, enabling effective squeezing while accounting for bottle deformation and recovery. The proposed controller is validated by comparing its performance with a pure force controller on 12 combinations of conditions consisting of 2 target dispense volumes, 2 plastic squeeze bottles, and
Open source S3plastic squeeze bottles
2
View original evidence
ate laboratory squeeze bottles to dispense liquid. This approach integrates force and vision feedback according to the interaction state, enabling effective squeezing while accounting for bottle deformation and recovery. The proposed controller is validated by comparing its performance with a pure force controller on 12 combinations of conditions consisting of 2 target dispense volumes, 2 plastic squeeze bottles, and
Open source S3squeezes used to dispense
2
View original evidence
ate laboratory squeeze bottles to dispense liquid. This approach integrates force and vision feedback according to the interaction state, enabling effective squeezing while accounting for bottle deformation and recovery. The proposed controller is validated by comparing its performance with a pure force controller on 12 combinations of conditions consisting of 2 target dispense volumes, 2 plastic squeeze bottles, and
Open source S3combinations of conditions
12
View original evidence
ate laboratory squeeze bottles to dispense liquid. This approach integrates force and vision feedback according to the interaction state, enabling effective squeezing while accounting for bottle deformation and recovery. The proposed controller is validated by comparing its performance with a pure force controller on 12 combinations of conditions consisting of 2 target dispense volumes, 2 plastic squeeze bottles, and
Open source S3
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
1 to 3 squeezes used to dispense. Human demonstrations of these operating conditions were collected using electromyography (EMG) sensing mapped to a desired grip force, which was then used as the force reference for the controllers to squeeze the bottles. Results demonstrated that the proposed adaptive hybrid vision-force controller achieved more accurate liquid dispensing with a mean absolute error (MAE) of 6.54 mL
Open source S4
compared to a MAE of 15.92 mL from the pure force controller, while also replicating the human action recorded from the EMG signal more closely.
Open source S5
ate laboratory squeeze bottles to dispense liquid. This approach integrates force and vision feedback according to the interaction state, enabling effective squeezing while accounting for bottle deformation and recovery. The proposed controller is validated by comparing its performance with a pure force controller on 12 combinations of conditions consisting of 2 target dispense volumes, 2 plastic squeeze bottles, and
Open source S3
Source：arXiv Robotics — research abstracts · arxiv.org