CompVLA: A Variable Compliance Vision-Language-Action Model for Contact-rich Manipulation

2026-09-20

AI Summary

为解决接触丰富操作任务中机器人运动与对外力响应的调控问题，提出CompVLA模型，通过RGB和语言输入联合预测运动和刚度矩阵，提高任务成功率。

Abstract

Contact-rich manipulation, requiring robots to regulate not only motion but also how they yield to external forces, has emerged as the next frontier for Vision-Language-Action (VLA) models. However, existing VLAs output purely kinematic commands, degrading performance on real-world contact-rich tasks. In this paper, we introduce CompVLA, a unified VLA framework that jointly predicts motion and stiffness matrix from RGB and language inputs. Our approach augments the conventional architecture with a dedicated Compliance Expert, which outputs time-varying stiffness and virtual displacement profiles executed via geometric impedance control. We demonstrate that CompVLA achieves the highest average success rate across diverse contact-rich tasks, outperforming both vanilla and compliance-aware VLA baselines, with ablations confirming each component is essential.

Problem

• Contact-rich manipulation
• Vision-Language-Action model
• Compliance

Innovation

• Variable Compliance
• Vision-Language-Action Model
• Contact-rich Manipulation
• Geometric Impedance Control