Exp-Force: Experience-Conditioned Pre-Grasp Force Selection with Vision-Language Models

• URL: http://arxiv.org/abs/2603.08668v1
• Date: Mon, 09 Mar 2026 17:41:22 GMT
• Title: Exp-Force: Experience-Conditioned Pre-Grasp Force Selection with Vision-Language Models
• Abstract summary: We propose Exp-Force, a framework that predicts the minimum feasible grasping force from a single RGB image.<n>On 129 object instances, ExpForce achieves a best-case MAE of 0.43 N, reducing error by 72% over zero-shot inference.<n>These results demonstrate that Exp-Force enables reliable and generalizable pre-grasp force selection.
• Score: 0.9449650062296823
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate pre-contact grasp force selection is critical for safe and reliable robotic manipulation. Adaptive controllers regulate force after contact but still require a reasonable initial estimate. Starting a grasp with too little force requires reactive adjustment, while starting a grasp with too high a force risks damaging fragile objects. This trade-off is particularly challenging for compliant grippers, whose contact mechanics are difficult to model analytically. We propose Exp-Force, an experience-conditioned framework that predicts the minimum feasible grasping force from a single RGB image. The method retrieves a small set of relevant prior grasping experiences and conditions a vision-language model on these examples for in-context inference, without analytic contact models or manually designed heuristics. On 129 object instances, ExpForce achieves a best-case MAE of 0.43 N, reducing error by 72% over zero-shot inference. In real-world tests on 30 unseen objects, it improves appropriate force selection rate from 63% to 87%. These results demonstrate that Exp-Force enables reliable and generalizable pre-grasp force selection by leveraging prior interaction experiences. http://expforcesubmission.github.io/Exp-Force-Website/

Related papers

• Compact Visuotactile World Models for Lifting: Prediction, Reward Alignment, and Force Constraints [0.0]
  Visuotactile dynamics reduce force action-effect MAE from 0.413 N for persistence to 0.338 N.<n>Model-assisted feedback raises ID force-budgeted success from 73.3% to 93.3%.<n> Imagined RL achieves 11.9% pooled joint success versus 25.0% for reactive IQL.
  arXiv  Detail & Related papers  (2026-09-09T01:50:54Z)
• ForceBand: Learning Forceful Manipulation with sEMG [55.186900419710746]
  We introduce ForceBand, a low-cost wrist-worn sEMG system that turns human muscle activity into force-enriched demonstrations.<n>We pre-train an EMG2Force model that predicts per-finger forces from sEMG and IMU signals.<n>Experiments show that ForceBand recovers fine-grained fingertip interactions with over 50% lower force prediction error than vision-based baselines.
  arXiv  Detail & Related papers  (2026-06-24T17:59:35Z)
• ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching [53.30290192030814]
  ForceFlow is a force-aware reactive framework built upon flow matching.<n>We show that ForceFlow achieves a 37% success rate improvement over the strong baseline ForceVLA.<n>It also exhibits accurate force signal prediction and superior performance in contact force self-regulation.
  arXiv  Detail & Related papers  (2026-05-11T13:27:00Z)
• Rollback-Free Stable Brick Structures Generation [51.856925926010184]
  Existing approaches rely on external physical simulators during inference to perform rejection sampling and brick-by-brick rollbacks.<n>We propose a reinforcement learning paradigm that shifts physical validity enforcement from test-time correction to training-time policy optimization.<n> Experimental results demonstrate that our approach achieves state-of-the-art generation quality while accelerating inference speed by orders of magnitude.
  arXiv  Detail & Related papers  (2026-05-07T21:06:44Z)
• Characterization, Analytical Planning, and Hybrid Force Control for the Inspire RH56DFX Hand [2.574393697080417]
  dexterous robot hands are increasingly prevalent, but many remain difficult to use as scientific instruments.<n>We contribute three improvements to the Inspire RH56DFX to transform it from a black-box device to a research tool.<n>We validate these components on peg-in-hole insertion, achieving 65% success and outperforming a wrist-force-only baseline of 10%.
  arXiv  Detail & Related papers  (2026-03-09T22:25:38Z)
• AMPS: Adaptive Modality Preference Steering via Functional Entropy [66.69992693275061]
  We introduce an instance-aware diagnostic metric that quantifies each modality's information contribution and reveals sample-specific susceptibility to steering.<n> Experimental results show that our instance-aware steering outperforms conventional steering in modulating modality preference.
  arXiv  Detail & Related papers  (2026-02-13T02:29:06Z)
• Learning Force-Regulated Manipulation with a Low-Cost Tactile-Force-Controlled Gripper [18.40849472506029]
  TF-Gripper is a low-cost force-controlled parallel-jaw gripper that integrates tactile sensing as feedback.<n> RETAF is a framework that decouples grasping force control from arm pose prediction.<n>We evaluate TF-Gripper and RETAF across five real-world tasks requiring precise force regulation.
  arXiv  Detail & Related papers  (2026-02-10T17:36:33Z)
• In-the-Wild Compliant Manipulation with UMI-FT [18.632109897570835]
  UMI-FT is a handheld data-collection platform that mounts compact, six-axis force/torque sensors on each finger.<n>We train an adaptive compliance policy that predicts position targets, grasp force, and stiffness for execution on standard compliance controllers.
  arXiv  Detail & Related papers  (2026-01-15T02:00:03Z)
• Steerable Adversarial Scenario Generation through Test-Time Preference Alignment [58.37104890690234]
  Adversarial scenario generation is a cost-effective approach for safety assessment of autonomous driving systems.<n>We introduce a new framework named textbfSteerable textbfAdversarial scenario textbfGEnerator (SAGE)<n>SAGE enables fine-grained test-time control over the trade-off between adversariality and realism without any retraining.
  arXiv  Detail & Related papers  (2025-09-24T13:27:35Z)
• ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation [62.58034332427291]
  ForceVLA is a novel end-to-end manipulation framework.<n>It treats external force sensing as a first-class modality within VLA systems.
  arXiv  Detail & Related papers  (2025-05-28T09:24:25Z)
• ForceGrip: Reference-Free Curriculum Learning for Realistic Grip Force Control in VR Hand Manipulation [0.10995326465245926]
  We present ForceGrip, a deep learning agent that synthesizes realistic hand manipulation motions.<n>We employ a three-phase curriculum learning framework comprising Finger Positioning, Intention Adaptation, and Dynamic Stabilization.<n>Our evaluations reveal ForceGrip's superior force controllability and plausibility compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-11T05:39:07Z)
• Learning Gentle Grasping Using Vision, Sound, and Touch [4.482495915731277]
  This paper proposes using visual, tactile, and auditory signals to learn to grasp and regrasp objects stably and gently.<n>We use audio signals as an indicator of gentleness during the grasping, and then train an action-conditional model from raw visuo-tactile inputs.<n> Experimental results on a multi-fingered hand over 1,500 grasping trials demonstrated that our model is useful for gentle grasping.
  arXiv  Detail & Related papers  (2025-03-11T00:12:25Z)
• Self-Play Preference Optimization for Language Model Alignment [75.83359213697854]
  Recent advancements suggest that directly working with preference probabilities can yield a more accurate reflection of human preferences. We propose a self-play-based method for language model alignment, which treats the problem as a constant-sum two-player game. Our approach, dubbed Self-Play Preference Optimization (SPPO), utilizes iterative policy updates to provably approximate the Nash equilibrium.
  arXiv  Detail & Related papers  (2024-05-01T17:59:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.