---
title: Cross-Embodiment Force-Position Interface
url: https://www.emergentmind.com/topics/cross-embodiment-force-position-interface
type: topic
---

# Cross-Embodiment Force-Position Interface

Searching arXiv for recent papers on cross-embodiment force/position interfaces and closely related mechanisms.
First, searching for the language–force shared-latent work and direct teleoperation/interface papers.
A cross-embodiment force-position interface is an embodiment-agnostic control or representation layer that allows task-relevant motion and interaction information to be transferred across agents with different kinematics, dynamics, sensing, and actuation. In the recent literature, this interface appears in several forms: a shared latent space aligning force trajectories with language, task-space hybrid commands combining motion and wrench intent, tactile shear-field policies that turn human-applied forces into position updates on a position-only robot, sensorless teleoperation schemes that infer virtual force from tracking deviation, calibrated torque-to-fingertip-force pipelines for dexterous hands, and geometry-centered interfaces based on particles or contact-point normals rather than native joint coordinates [2502.02772] [2603.15169] [2409.14896] [2606.15516] [2601.09163]. Across these formulations, the common objective is not merely trajectory retargeting, but preservation of interaction semantics: what direction to move, how strongly to load contact, and how to realize that intent safely on a different embodiment.

## 1. Definition and conceptual scope

Cross-embodiment learning arises because action spaces, workspaces, sensing channels, and compliance properties differ substantially across systems. The cited work spans human arms coupled to a 7-DoF haptic exoskeleton, a 6-DoF heavy-duty hydraulic manipulator, torque-controlled arms, position-only gantries, multi-finger dexterous hands with different coupling structures, and robot hands or human hands represented as particles [2505.14486] [2409.14896] [2606.15516] [2511.01177]. In this setting, a force-position interface is useful only if it abstracts away embodiment-specific coordinates while preserving control relevance.

Two distinctions organize the field. The first is **explicit versus implicit contact representation**. Explicit interfaces expose task-space wrench, joint torque, fingertip force, or calibrated load descriptors; implicit interfaces encode contact through tactile shear, end-effector tracking deviation, particle motion, or contact geometry [2603.15169] [2606.15516] [2511.20887] [2511.01177]. The second is **semantic versus purely physical abstraction**. Some interfaces are grounded in language or task prompts, such as 16-dimensional shared latent codes for force and phrases, or force prompts injected into a vision-language model; others remain entirely within geometry and dynamics, such as particle displacements or functional point clouds with normals [2502.02772] [2603.15169] [2601.09163].

A recurring theme is that “cross-embodiment” does not require identical state or action spaces. In one line of work, different embodiments are unified by a shared latent code; in another, by task-space hybrid action variables; in another, by calibrated physical units such as N·m or fingertip force; and in another, by geometry-centered representations such as particles or point-normal sets [2502.02772] [2606.15516] [2511.01177] [2601.09163]. This suggests that a force-position interface is best understood as a conserved intermediate representation of interaction, rather than as a fixed controller architecture.

## 2. Representational substrates

The literature uses several distinct substrates to instantiate a cross-embodiment interface.

| Interface substrate | Shared content | Representative formulation |
|---|---|---|
| Shared latent code | Force trajectory and phrase semantics | 16-D dual-autoencoder latent [2502.02772] |
| Task-space hybrid action | Motion target plus force/wrench intent | $\tau = J^\top(q)\, f_{ee} + \tau_0$; force-aware MoE [2603.15169] |
| Sensorless contact surrogate | Virtual force or tactile response | End-effector deviation or tactile shear field [2511.20887] [2409.14896] |
| Calibrated contact channel | Joint torque, fingertip force, load descriptor | $\mathcal{G}_h$, $\mathbf{f}_t$, $\boldsymbol{\gamma}_t$ [2606.15516] |
| Geometry-centered interface | Contact-relevant position and orientation | Particles or point-normal sets [2511.01177] [2601.09163] |

The most direct latent formulation is the dual-autoencoder force-language model. There, processed 3D force trajectories are resampled to 256 time steps, converted to impulse profiles, flattened to 768 dimensions, and mapped by a feedforward encoder to a 16-dimensional latent vector; phrases are mapped to the same latent space either from a 62-D binary representation or a 150-D GloVe representation [2502.02772]. Training combines reconstruction, a Hadsell-type contrastive alignment term, and cross-decoding loss,
\[
\mathcal{L} = k_r \mathcal{L}_r + k_z \mathcal{L}_c + k_t \mathcal{L}_t,
\]
with corresponding force–phrase pairs pulled together and non-pairs pushed apart. The paper explicitly proposes that replacing the force-only encoder with one operating on force-position trajectories would turn this into a cross-embodiment force-position-language interface [2502.02772].

A second substrate is the task-space hybrid action representation. ForceVLA2 formulates contact-rich manipulation as regulation of both task-space motion and end-effector interaction force, with a Jacobian-based execution layer and “active torque-level modulation” rather than passive compliance alone [2603.15169]. In the beyond-human-scale teleoperation setting, the same idea appears as coupled velocity references with independent motion and force scaling, where ideal transparency is expressed by
\[
G_{\text{ideal}}=
\begin{bmatrix}
0 & \kappa_f^{-1}\\
-\kappa_p & 0
\end{bmatrix},
\]
so that slave velocity scales with $\kappa_p$ and reflected master force scales with $\kappa_f^{-1}$ [2505.14486].

A third substrate replaces direct force sensing with sensorless contact surrogates. ACE-F interprets follower end-effector positional deviation as a virtual force signal and regulates feedback magnitude by
\[
\text{Factor} = \sqrt{\frac{\alpha \cdot \|\Delta \mathbf{ee}\|^2}{1 + \|\mathbf{v}_\text{cartesian}\|^2}},
\]
then renders that signal back to the leader through impedance control [2511.20887]. The collaborative manipulation work on tactile transfer uses GelSlim shear fields
\[
\tau = \{v_x^L, v_y^L, \text{div}^L, v_x^R, v_y^R, \text{div}^R\}
\]
as the common language between an impedance-capable robot and a purely position-controlled gantry, thereby learning a tactile-to-position mapping that emulates compliant behavior without force sensing on the target platform [2409.14896].

A fourth substrate makes contact explicit in physical units. In compliant cross-hand grasping, each hand has a retargeting map $\mathcal{R}_h : \boldsymbol{\psi} \mapsto \mathbf{q}^{(h)}$ from a shared 15-D MANO-based pose latent and a hand-specific torque predictor $\mathcal{G}_h$ from raw effort history to joint torque in N·m [2606.15516]. Joint torques are mapped to fingertip forces through the translational Jacobian, and per-finger spatial torque descriptors
\[
\boldsymbol{\gamma} = [c,\rho,\ell]
\]
encode load centroid, participation ratio, and lateral share. This is one of the clearest explicit force-position interfaces in the cited corpus because both motion intent and contact loading are hand-agnostic by construction [2606.15516].

Finally, several papers define geometry-centered substitutes for direct wrench representations. Cross-embodiment world models represent end-effectors and objects as particle sets and actions as particle displacements, learning a shared dynamics model in particle space [2511.01177]. CEI represents end-effectors as point-normal sets and aligns trajectories through Directional Chamfer Distance, thereby matching contact-relevant geometry across embodiments [2601.09163]. Neither system exposes force explicitly, but both are designed so that contact effects are preserved through geometric interaction.

## 3. Architectural realizations and control laws

Architecturally, the cited systems differ in whether the interface is realized as a latent embedding module, a high-level semantic conditioner, or a closed-loop controller.

The force-language model is the most compact latent-space realization. It has two encoders, two decoders, and a shared latent $\mathcal{Z}\subset\mathbb{R}^{16}$ supporting force reconstruction, phrase reconstruction, force-to-language translation, and language-to-force translation [2502.02772]. The paper’s interpretation is particularly relevant to cross-embodiment settings: different robots could learn their own encoders into the same latent space and their own decoders back to feasible trajectories, while phrases such as “gently up” or “sharp backward-right” become shared latent points [2502.02772].

ForceVLA2 uses a more hierarchical architecture. A VLM expert processes images, language, and force prompts, while an action expert built as a Cross-Scale Mixture-of-Experts fuses these force-aware task concepts with real-time interaction forces to produce hybrid commands [2603.15169]. The policy-level “hybrid” definition is explicit: motion-related and force-related outputs are produced jointly, then realized through a Jacobian-based mapping and torque-level modulation. Force prompts act as semantic switches between non-contact Position Mode and contact-rich Hybrid Mode, so the interface spans semantics, perception, and control in a single stack [2603.15169].

Teleoperation systems implement the interface as a bidirectional coupling law. In the beyond-human-scale hydraulic teleoperation framework, master and slave required end-effector velocities are modified by force feedback,
\[
V_{mr}=V_{md}-\mathcal{A}\,\boldsymbol{F}_m,\qquad
V_{sr}=V_{sd}-\mathcal{A}\,\hat{\boldsymbol{F}}_s,
\]
and joint references are obtained through the master and slave Jacobians [2505.14486]. Motion scaling up to $\kappa_p=13$ and force scaling up to $\kappa_f=1000$ are integrated into the bilateral coordination law, while sensorless force reflection and a human-robot augmented dynamic model preserve stability and transparency under up to 150 ms one-way delay [2505.14486].

ACE-F realizes a lighter-weight cross-embodiment teleoperation interface. The leader is treated as a generic 6-DoF end-effector device, with 3-DoF position from a foldable arm and orientation from an IMU or glove; the follower is retargeted by augmented IK, and virtual force is synthesized from end-effector tracking error rather than direct force sensing [2511.20887]. This design separates task-space human intent from embodiment-specific joint-space realization and deliberately limits haptic feedback to 3-D translation, which the paper presents as sufficient for many contact-rich tasks [2511.20887].

In dexterous grasping, the low-level controller itself is hybrid. A shared pose latent provides a reference configuration, while calibrated torques produce desired fingertip force targets. The force-limited position controller retreats from the position reference when torque overshoot is detected:
\[
q_{\mathrm{cmd},j}=q_{\mathrm{ref},j}-\mathrm{clip}(r_j,0,o_{\max}),
\]
with retreat driven only by positive torque overshoot [2606.15516]. This one-sided compliance is chosen for safety, especially with non-backdrivable actuators, and the same calibrated signal is used during teleoperation, training, and autonomous execution [2606.15516].

## 4. Empirical evidence and evaluation

Empirical validation spans translation quality, success rates in contact-rich manipulation, teleoperation transparency, sense of embodiment, and transfer ratios.

For force-language embedding, in-distribution evaluation uses 90% train / 10% test random splits over 30 random seeds, with out-of-distribution evaluations that hold out modifiers or direction words [2502.02772]. Dual autoencoders outperform direct MLP baselines across force and phrase metrics, with roughly 20–30% improvement versus baselines. DAE\_B achieves the highest phrase-level performance, with ModSim approximately 0.58 and PhraseSim approximately 0.78, while GloVe-based models generalize better to unseen modifiers or directions in force reconstruction and force-direction accuracy [2502.02772]. These results matter because a cross-embodiment interface must tolerate embodiment-induced distribution shift, and the paper explicitly interprets out-of-distribution generalization as a necessary property for that role.

ForceVLA2 provides the clearest task-level evidence for hybrid force-position control. Its dataset contains 1,000 trajectories over 5 contact-rich tasks, including wiping, pressing, and assembling [2603.15169]. In the comparison table, ACP achieves 16% average success, $\pi_0$ with force input 17%, $\pi_0$ with impedance 22%, and Foca-VLA 66%, with task-specific scores of 80.0 on Press bottle, 75.0 on Clean vase, 70.0 on Clean board, 35.0 on Retrieve plate, and 70.0 on Assemble gears [2603.15169]. The paper attributes these gains to active torque-level modulation, force prompts, and force-aware MoE gating rather than to naive force concatenation.

The beyond-human-scale teleoperation system reports high accuracy tracking under up to 1:13 motion scaling and 1:1000 force scaling, and establishes the stability-transparency tradeoff for motion tracking and force reflection under up to 150 ms of one-way fixed and time-varying delays [2505.14486]. In free motion, task time decreases from 35 s at $\kappa_p=1$ to 16.6 s at $\kappa_p=13$, while max position error rises from 0.011 m to 0.029 m; in the user study, the overall normalized sense of embodiment score is 76.4%, with 10 participants and no reported gender limitation [2505.14486]. These data show that a cross-embodiment force-position interface can be evaluated not only by task success but also by transparency and subjective embodiment.

ACE-F emphasizes teleoperation usability and downstream imitation learning. In blind can insertion, ACE-F achieves 100% success versus 50% for Gello, while in simulated box stacking it is reported as approximately 55% faster with fewer errors and higher success rate than joint-copy Gello [2511.20887]. The system is also designed so that demonstrations collected with force feedback improve learned policy performance, including a reported 95% versus 60% success gap in the lifting example [2511.20887].

Explicit cross-hand force-position interfaces show strong transfer gains. MARC raises cross-hand mean success from 0.44 to 0.71 over 10 reach-and-lift tasks, with improvements such as 0.54 to 0.84 on Inspire and 0.48 to 0.79 on Wuji; removing fingertip force and spatial torque descriptors drops average success from 0.89 to 0.39 in the ablation table [2606.15516]. On an unseen 15-DoF configuration, transfer is achieved zero-shot once a new retargeting map and torque regressor are provided [2606.15516]. This directly supports the claim that calibrated contact feedback, not motion retargeting alone, enables transferable compliant grasping.

Adjacent geometry-centered interfaces also exhibit strong transfer. CEI transfers data and policies from a Franka Panda to 16 embodiments across 3 tasks in simulation and supports bidirectional transfer between UR5+AG95 and UR5+Xhand across 6 real-world tasks, with an average transfer ratio of 82.4% [2601.09163]. The particle-based cross-embodiment world model reports three findings: scaling to more training embodiments improves generalization to unseen ones, co-training on simulated and real data outperforms training on either alone, and the learned models enable effective control on robots with varied degrees of freedom [2511.01177]. Although these systems are not explicit force interfaces, they supply quantitative evidence that embodiment-invariant intermediate spaces can be learned at scale.

## 5. Applications and adjacent formulations

The most immediate applications are contact-rich manipulation, collaborative manipulation, teleoperation, and dexterous grasping. ForceVLA2 targets pressing, wiping, retrieving, and assembling under alternating contact and non-contact phases [2603.15169]. The beyond-human-scale teleoperation framework targets heavy-duty manipulation with immersive VR, distributed haptics, and force reflection [2505.14486]. ACE-F is positioned as a portable teleoperation platform for collecting high-quality demonstrations across embodiments, especially for contact-rich tasks such as stacking, dragging, wiping, blind insertion, and can sorting [2511.20887]. The tactile collaborative manipulation work addresses cooperative object carrying and box placement, with tactile sensing acting as the common interface between an impedance-capable source robot and a position-only target robot [2409.14896].

A second application class is dexterous manipulation under occlusion or deformability. The calibrated force-position interface across heterogeneous hands is evaluated on rigid and compliant objects including toy fruits, a marker, stacked cups, brioche buns, and an egg, and the resulting learned primitives are stated to be reusable in long-horizon manipulation pipelines [2606.15516]. This is significant because the object regimes that benefit most from explicit contact feedback are precisely those where vision is unreliable or motion-only retargeting is underdetermined.

A third application class is semantic mediation between human-readable commands and embodiment-specific execution. The force-language latent model shows that force profiles and phrases can supplement, integrate, and substitute for one another, so that a force trajectory can decode to a phrase and a phrase can decode to a force trajectory [2502.02772]. BLM$_1$ is not a force-position interface, but its intent-bridging architecture shows how a frozen multimodal language model can provide shared high-level semantics to a policy module with embodiment-specific state and action encoders across four robot embodiments and six tasks [2510.24161]. This suggests that semantic intent layers and force-position interfaces are complementary rather than competing abstractions.

Finally, two geometry-centered formulations define an adjacent but important design frontier. CEI uses functional similarity in 3D contact geometry via Directional Chamfer Distance over point-normal sets, while the cross-embodiment world model uses particles and particle displacements as a shared state-action space [2601.09163] [2511.01177]. Both systems currently encode contact implicitly. A plausible implication is that they provide the structural scaffold on which explicit force or wrench channels could be added without abandoning embodiment invariance.

## 6. Limitations, misconceptions, and open problems

A common misconception is that a cross-embodiment interface must expose force through direct force/torque sensing. The cited work does not support that claim. ACE-F derives virtual force from end-effector positional deviation, and the tactile transfer system achieves compliant collaborative behavior on a target robot with no force/torque sensing by mapping tactile shear directly to position commands [2511.20887] [2409.14896]. These are still force-position interfaces in the functional sense, because they preserve contact-aware behavior across embodiments.

A second misconception is that pose retargeting or shared joint representations are sufficient for contact-rich transfer. Several papers argue otherwise. ForceVLA2 explicitly attributes failures of baselines to position-only control or naive force concatenation, while the dexterous grasping work shows that removing calibrated force and load descriptors collapses success toward motion-centric baselines [2603.15169] [2606.15516]. CEI likewise notes that visual-kinematic inputs alone limit detection of unstable contacts such as slippage in InsertFlower, and proposes tactile integration as a future direction [2601.09163].

The current limitations are substantial. The force-language embedding work is restricted to simple single-phase 3-D force interactions and a modifier-plus-direction phrase template, with no position or pose, no torque or wrench, and no temporal models beyond MLP autoencoders [2502.02772]. ForceVLA2 avoids heavy sim pretraining because friction and contact modeling are unreliable in simulation, and its dataset, while force-rich, is still modest relative to vision-only corpora [2603.15169]. ACE-F renders only 3-DoF translational virtual force, not full 6-DoF wrench feedback, and its virtual force signal depends on controller tuning because it is inferred from tracking error rather than measured directly [2511.20887].

Calibration cost is another major obstacle. The dexterous grasping interface requires per-hand system identification to train $\mathcal{G}_h$, and errors in calibration propagate to both policy observations and low-level controllers [2606.15516]. The tactile collaborative manipulation system is currently planar and reports poor normal-force estimation with GelSlim-based setups, limiting straightforward extension to full 3D force control [2409.14896]. Geometry-centered systems solve embodiment mismatch in position space but omit explicit force, tactile, or impedance channels, which leaves them vulnerable in slip-prone or highly dynamic contact regimes [2511.01177] [2601.09163].

Open problems are correspondingly clear in the cited literature. They include learning embodiment-invariant latent spaces with explicit domain adaptation or multi-domain training, integrating richer language and temporal models, using task-centric or object-centric coordinate frames, extending tactile and calibrated force representations to full wrench spaces, incorporating safety constraints directly into controllers and learned decoders, and building multi-robot datasets rich enough to span both kinematic and contact diversity [2502.02772] [2603.15169] [2606.15516]. The broad technical direction is already visible: position-only abstractions are being supplemented by contact-aware signals, and embodiment-agnostic semantics are moving from geometry and latent pose toward physically calibrated loading descriptors. This suggests that the mature form of a cross-embodiment force-position interface will likely be multimodal, physically normalized, and explicitly hybrid, with motion intent, contact state, and execution constraints represented in a single transferable layer.

Source: https://www.emergentmind.com/topics/cross-embodiment-force-position-interface