Exp-Force: Experience-Conditioned Pre-Grasp Force Selection with Vision-Language Models
2026-03-09 • Robotics
Robotics
AI summaryⓘ
The authors address the problem of choosing the right amount of force before a robot gripper touches an object, which is important to avoid dropping or damaging it. They created Exp-Force, a system that looks at a photo of the object and uses past grasping experiences to guess the minimum force needed. This approach does not rely on complicated physical models and works better than other methods, especially for soft grippers. Tests on many objects showed that Exp-Force picks more accurate force levels, leading to safer and more reliable grasps.
robotic manipulationgrasp forcecompliant grippersexperience-conditioned learningRGB image processingvision-language modelsforce predictionin-context inferenceadaptive control
Authors
Siqi Shang, Minchao Huang, Bill Fan, Lillian Chin
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/