# DexForce: Extracting Force-informed Actions from Kinesthetic Demonstrations for Dexterous Manipulation

arXiv: https://arxiv.org/abs/2501.10356 · HTML: https://mlsanity.com/paper/2501.10356/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data.
- First posted on arXiv 17 Jan 2025.

## Placed in

- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Built on by (most cited first, 24 of 24)

- [FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning](https://mlsanity.com/paper/2502.17432/) (2025)
- [Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration](https://mlsanity.com/paper/2504.12609/) (2025)
- [TA-VLA: Elucidating the Design Space of Torque-aware Vision-Language-Action Models](https://mlsanity.com/paper/2509.07962/) (2025)
- [DEXOP: A Device for Robotic Transfer of Dexterous Human Manipulation](https://mlsanity.com/paper/2509.04441/) (2025)
- [SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation](https://mlsanity.com/paper/2602.16863/) (2026)
- [FACET: Force-Adaptive Control via Impedance Reference Tracking for Legged Robots](https://mlsanity.com/paper/2505.06883/) (2025)
- [OSMO: Open-Source Tactile Glove for Human-to-Robot Skill Transfer](https://mlsanity.com/paper/2512.08920/) (2025)
- [ImplicitRDP: An End-to-End Visual-Force Diffusion Policy with Structural Slow-Fast Learning](https://mlsanity.com/paper/2512.10946/) (2025)
- [Flow with the Force Field: Learning 3D Compliant Flow Matching Policies from Force and Demonstration-Guided Simulation Data](https://mlsanity.com/paper/2510.02738/) (2025)
- [FA-RDP: A Frequency-Adaptive Reactive Diffusion Policy for Contact-Rich Manipulation](https://mlsanity.com/paper/2607.28596/) (2026)
- [Demystifying When and Why VLAs Fail in Contact-Rich Tasks and How to Fix Them](https://mlsanity.com/paper/2608.01402/) (2026)
- [Unfettered Forceful Skill Acquisition with Physical Reasoning and Coordinate Frame Labeling](https://mlsanity.com/paper/2505.09731/) (2025)
- [Gentle Object Retraction in Dense Clutter Using Multimodal Force Sensing and Imitation Learning](https://mlsanity.com/paper/2508.19476/) (2025)
- [HAFO: A Force-Adaptive Control Framework for Humanoid Robots in Intense Interaction Environments](https://mlsanity.com/paper/2511.20275/) (2025)
- [How to Peel with a Knife: Aligning Fine-Grained Manipulation with Human Preference](https://mlsanity.com/paper/2603.03280/) (2026)
- [Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?](https://mlsanity.com/paper/2606.26428/) (2026)
- [TAP-VLA: Tactile Annotation Prompting for Vision Language Action Models](https://mlsanity.com/paper/2606.29089/) (2026)
- [Learning Pivoting Manipulation with Force and Vision Feedback Using Optimization-based Demonstrations](https://mlsanity.com/paper/2508.01082/) (2025)
- [TransDex: Pre-training Visuo-Tactile Policy with Point Cloud Reconstruction for Dexterous Manipulation of Transparent Objects](https://mlsanity.com/paper/2603.13869/) (2026)
- [Dreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation](https://mlsanity.com/paper/2609.19137/) (2026)
- [Beyond State-as-Action: Exploiting Command-State Discrepancy for Robot Imitation Learning](https://mlsanity.com/paper/2609.33145/) (2026)
- [X-Reset: Scaling Object-Centric Reinforcement Learning via Cross-Embodiment Resets](https://mlsanity.com/paper/2609.35715/) (2026)
- [SoTa: Soft Tactile Skins for Dexterous Manipulation](https://mlsanity.com/paper/2610.02338/) (2026)
- [Force-Modulated Dexterity: Unified Compliance for Contact-Rich Manipulation](https://mlsanity.com/paper/2610.17161/) (2026)

## Abstract (arXiv)

Imitation learning requires high-quality demonstrations consisting of sequences of state-action pairs. For contact-rich dexterous manipulation tasks that require dexterity, the actions in these state-action pairs must produce the right forces. Current widely-used methods for collecting dexterous manipulation demonstrations are difficult to use for demonstrating contact-rich tasks due to unintuitive human-to-robot motion retargeting and the lack of direct haptic feedback. Motivated by these concerns, we propose DexForce. DexForce leverages contact forces, measured during kinesthetic demonstrations, to compute force-informed actions for policy learning. We collect demonstrations for six tasks and show that policies trained on our force-informed actions achieve an average success rate of 76% across all tasks. In contrast, policies trained directly on actions that do not account for contact forces have near-zero success rates. We also conduct a study ablating the inclusion of force data in policy observations. We find that while using force data never hurts policy performance, it helps most for tasks that require advanced levels of precision and coordination, like opening an AirPods case and unscrewing a nut.