Uncertainty-Aware Finger Force Estimation for Reliable Box Manipulation

Anonymous Authors

With force adaptation

FEEL

Task success 10/10 · Damage-free 10/10 · Reliability 10/10

Without force adaptation

Baseline

Task success 10/10 · Damage-free 7/10 · Reliability 7/10

10 trials per condition, using the same box specification and predefined motion. Reliability = task success and a damage-free outcome.

Reliability

Primary status for all experiment grids below.

Reliable Unreliable

Reliable indicates task success and a damage-free outcome. Each card reports both criteria separately.

With force estimation experiments

(K_p, K_d) = (200, 400)

Force-adaptive manipulation driven by FEEL estimates.

Trial 01Reliable

Task success: Yes
Damage-free: Yes

Trial 02Reliable

Task success: Yes
Damage-free: Yes

Trial 03Reliable

Task success: Yes
Damage-free: Yes

Trial 04Reliable

Task success: Yes
Damage-free: Yes

Trial 05Reliable

Task success: Yes
Damage-free: Yes

Trial 06Reliable

Task success: Yes
Damage-free: Yes

Trial 07Reliable

Task success: Yes
Damage-free: Yes

Trial 08Reliable

Task success: Yes
Damage-free: Yes

Trial 09Reliable

Task success: Yes
Damage-free: Yes

Trial 10Reliable

Task success: Yes
Damage-free: Yes

Without force estimation experiments

(K_p, K_d) = (200, 400)

Fixed finger commands without force-estimation feedback.

Trial 01Unreliable

Task success: Yes
Damage-free: No

Trial 02Reliable

Task success: Yes
Damage-free: Yes

Trial 03Reliable

Task success: Yes
Damage-free: Yes

Trial 04Reliable

Task success: Yes
Damage-free: Yes

Trial 05Reliable

Task success: Yes
Damage-free: Yes

Trial 06Reliable

Task success: Yes
Damage-free: Yes

Trial 07Reliable

Task success: Yes
Damage-free: Yes

Trial 08Reliable

Task success: Yes
Damage-free: Yes

Trial 09Unreliable

Task success: Yes
Damage-free: No

Trial 10Unreliable

Task success: Yes
Damage-free: No

Gain comparison experiments

Ten force-adaptive box-manipulation trials for each controller-gain setting.

(K_p, K_d) = (100, 200)

RMSE: 0.233 ± 0.005 N

10 trials

Trial 01Unreliable

Task success: No
Damage-free: Yes

Trial 02Reliable

Task success: Yes
Damage-free: Yes

Trial 03Unreliable

Task success: No
Damage-free: Yes

Trial 04Unreliable

Task success: No
Damage-free: Yes

Trial 05Unreliable

Task success: No
Damage-free: Yes

Trial 06Unreliable

Task success: No
Damage-free: Yes

Trial 07Reliable

Task success: Yes
Damage-free: Yes

Trial 08Reliable

Task success: Yes
Damage-free: Yes

Trial 09Reliable

Task success: Yes
Damage-free: Yes

Trial 10Unreliable

Task success: No
Damage-free: Yes

(K_p, K_d) = (200, 400)

Used in the main experiments

RMSE: 0.251 ± 0.010 N

10 trials

Trial 01Reliable

Task success: Yes
Damage-free: Yes

Trial 02Reliable

Task success: Yes
Damage-free: Yes

Trial 03Reliable

Task success: Yes
Damage-free: Yes

Trial 04Reliable

Task success: Yes
Damage-free: Yes

Trial 05Reliable

Task success: Yes
Damage-free: Yes

Trial 06Reliable

Task success: Yes
Damage-free: Yes

Trial 07Reliable

Task success: Yes
Damage-free: Yes

Trial 08Reliable

Task success: Yes
Damage-free: Yes

Trial 09Reliable

Task success: Yes
Damage-free: Yes

Trial 10Reliable

Task success: Yes
Damage-free: Yes

(K_p, K_d) = (300, 600)

RMSE: 0.255 ± 0.008 N

10 trials

Trial 01Reliable

Task success: Yes
Damage-free: Yes

Trial 02Reliable

Task success: Yes
Damage-free: Yes

Trial 03Reliable

Task success: Yes
Damage-free: Yes

Trial 04Unreliable

Task success: No
Damage-free: Yes

Trial 05Reliable

Task success: Yes
Damage-free: Yes

Trial 06Unreliable

Task success: Yes
Damage-free: No

Trial 07Reliable

Task success: Yes
Damage-free: Yes

Trial 08Reliable

Task success: Yes
Damage-free: Yes

Trial 09Unreliable

Task success: Yes
Damage-free: No

Trial 10Reliable

Task success: Yes
Damage-free: Yes

Data collection

Wearable F/T reference measurements synchronized with per-finger proprioceptive histories.

L Thumb

L Index

L Middle

L Ring

L Little

R Thumb

R Index

R Middle

R Ring

R Little

Approximately 25,000 synchronized estimator samples and an additional 5,000 calibration samples were collected per finger. Robot states and F/T measurements were aligned by timestamp.

Uncertainty-aware force estimation

Per-finger force estimates and predictive uncertainty under proprioceptive ambiguity.

Force through joints

Force through structure

Epistemic uncertainty is used as an empirical proxy for ambiguity in the proprioceptive force estimate.

Uncertainty-Aware Finger Force Estimation for Reliable Box Manipulation

With force adaptation

Without force adaptation

With force estimation experiments

Without force estimation experiments

Gain comparison experiments

(Kp, Kd) = (100, 200)

(Kp, Kd) = (200, 400)

(Kp, Kd) = (300, 600)

Data collection

Uncertainty-aware force estimation

Force through joints

Force through structure

(K_p, K_d) = (100, 200)

(K_p, K_d) = (200, 400)

(K_p, K_d) = (300, 600)