# ForceVLA2: Unleashing Hybrid Force-Position Control with Force Awareness for Contact-Rich Manipulation

arXiv: https://arxiv.org/abs/2603.15169 · HTML: https://mlsanity.com/paper/2603.15169/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2026.

## Built on by (most cited first, 22 of 22)

- [From Foundation to Application: Improving VLA Models in Practice](https://mlsanity.com/paper/2607.06403/) (2026)
- [TacForeSight: Force-Guided Tactile World Model for Contact-Rich Manipulation](https://mlsanity.com/paper/2606.11184/) (2026)
- [DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action model](https://mlsanity.com/paper/2606.12105/) (2026)
- [ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching](https://mlsanity.com/paper/2605.11048/) (2026)
- [UniTacVLA: Unified Tactile Understanding and Prediction in Vision Language Action Models](https://mlsanity.com/paper/2606.31723/) (2026)
- [ViTacWorld: Scaling Visuo-Tactile World Models for Contact-Rich Robot Manipulation](https://mlsanity.com/paper/2607.22530/) (2026)
- [TORL-VLA: Tactile Guided Online Reinforcement Learning for Contact-Rich Manipulation](https://mlsanity.com/paper/2606.09337/) (2026)
- [Never Too Late for Force: Accelerating VLA Post-Training with Reactive Force Injection](https://mlsanity.com/paper/2607.14236/) (2026)
- [SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds](https://mlsanity.com/paper/2604.08544/) (2026)
- [Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation](https://mlsanity.com/paper/2606.05660/) (2026)
- [Kepler-Encoder-v0.1: Towards a Multimodal Embedding Model for Robots](https://mlsanity.com/paper/2607.13522/) (2026)
- [Learning Physical Interaction: A Survey of Tactile- and Force-aware Robot Learning](https://mlsanity.com/paper/2608.07558/) (2026)
- [FWBC-VLA: Force-Aware Whole-Body Compensation for Contact-Rich Loco-Manipulation](https://mlsanity.com/paper/2609.03889/) (2026)
- [ForceU-VLA: A Force-Aware Vision-Language-Action Model for Embodied Ultrasound Scanning](https://mlsanity.com/paper/2608.15009/) (2026)
- [US-VLA: An Ultrasound Vision-Language-Action Model for Embodied Abdomina](https://mlsanity.com/paper/2608.16074/) (2026)
- [ForceDelta-VLA: Distilling Force-Conditioned ActionCorrections for Contact-Rich Manipulation](https://mlsanity.com/paper/2609.18242/) (2026)
- [TAO-Force: Unifying Force-Aware Perception and Fast-Slow Control for Contact-Rich Manipulation](https://mlsanity.com/paper/2609.18497/) (2026)
- [VT-Bridge: Bridging Pretrained Foundation VLAs to VTLAs via Lightweight Residual Adaptation](https://mlsanity.com/paper/2609.22606/) (2026)
- [ForceRFT: Refining VLA Actions through Force-Guided Residual Reinforcement Learning](https://mlsanity.com/paper/2609.22840/) (2026)
- [CompVLA: A Variable Compliance Vision-Language-Action Model for Contact-rich Manipulation](https://mlsanity.com/paper/2609.23614/) (2026)
- [Beyond State-as-Action: Exploiting Command-State Discrepancy for Robot Imitation Learning](https://mlsanity.com/paper/2609.33145/) (2026)
- [Triggering Generalist Reasoning via Predictive Uncertainty for Dual-System VLA](https://mlsanity.com/paper/2610.05025/) (2026)

## Abstract (arXiv)

Embodied intelligence for contact-rich manipulation has predominantly relied on position control, while explicit awareness and regulation of interaction forces remain under-explored, limiting stability, precision, and robustness in real-world tasks. We propose ForceVLA2, an end-to-end vision-language-action framework that equips robots with hybrid force-position control and explicit force awareness. ForceVLA2 introduces force-based prompts into the VLM expert to construct force-aware task concepts across stages, and employs a Cross-Scale Mixture-of-Experts (MoE) in the action expert to adaptively fuse these concepts with real-time interaction forces for closed-loop hybrid force-position regulation. To support learning and evaluation, we construct ForceVLA2-Dataset, containing 1,000 trajectories over 5 contact-rich tasks, including wiping, pressing, and assembling, with multi-view images, task prompts, proprioceptive state, and force signals. Extensive experiments show that ForceVLA2 substantially improves success rates and reliability in contact-rich manipulation, outperforming pi0 and pi0.5 by 48.0% and 35.0%, respectively, across the 5 tasks, and mitigating common failure modes such as arm overload and unstable contact, thereby actively advancing force-aware interactive physical intelligence in VLAs. The project page is available at https://sites.google.com/view/force-vla2/home.