FAME: Force-Adaptive RL for Expanding the Manipulation Envelope of a Full-Scale Humanoid

• URL: http://arxiv.org/abs/2603.08961v1
• Date: Mon, 09 Mar 2026 21:49:00 GMT
• Title: FAME: Force-Adaptive RL for Expanding the Manipulation Envelope of a Full-Scale Humanoid
• Abstract summary: Maintaining balance under external hand forces is critical for humanoid bimanual manipulation.<n>We propose textbfFAME, a force-adaptive reinforcement learning framework.
• Score: 41.604822515681256
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Maintaining balance under external hand forces is critical for humanoid bimanual manipulation, where interaction forces propagate through the kinematic chain and constrain the feasible manipulation envelope. We propose \textbf{FAME}, a force-adaptive reinforcement learning framework that conditions a standing policy on a learned latent context encoding upper-body joint configuration and bimanual interaction forces. During training, we apply diverse, spherically sampled 3D forces on each hand to inject disturbances in simulation together with an upper-body pose curriculum, exposing the policy to manipulation-induced perturbations across continuously varying arm configurations. At deployment, interaction forces are estimated from the robot dynamics and fed to the same encoder, enabling online adaptation without wrist force/torque sensors. In simulation across five fixed arm configurations with randomized hand forces and commanded base heights, FAME improves mean standing success to 73.84%, compared to 51.40% for the curriculum-only baseline and 29.44% for the base policy. We further deploy the learned policy on a full-scale Unitree H12 humanoid and evaluate robustness in representative load-interaction scenarios, including asymmetric single-arm load and symmetric bimanual load. Code and videos are available on https://fame10.github.io/Fame/

Related papers

• One-Shot Multimodal Learning from Demonstration with Force-Constrained Elastic Maps [0.0]
  We propose a novel one-shot multimodal Learning from Demonstration (LfD) framework for the segmentation, encoding, and reproduction of force-inclusive demonstrations.<n>First, we introduce a multimodal probabilistic segmentation method that adaptively weighs spatial and force modalities over time.<n>Second, we extend the elastic maps to incorporate external force constraints during skill encoding and formulate a convex optimization procedure for learning force-consistent trajectory models.
  arXiv  Detail & Related papers  (2026-07-10T15:27:50Z)
• ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching [53.30290192030814]
  ForceFlow is a force-aware reactive framework built upon flow matching.<n>We show that ForceFlow achieves a 37% success rate improvement over the strong baseline ForceVLA.<n>It also exhibits accurate force signal prediction and superior performance in contact force self-regulation.
  arXiv  Detail & Related papers  (2026-05-11T13:27:00Z)
• Tendon Force Modeling for Sim2Real Transfer of Reinforcement Learning Policies for Tendon-Driven Robots [4.374417345150659]
  We propose a method to model the tendon forces produced by typical servo motors.<n>We then utilize our force estimation model in a GPU-accelerated tendon force-driven rigid body simulation to train RL-based controllers.<n>Our model is capable of predicting tendon forces within 3% of the maximum motor force and is robot-agnostic.
  arXiv  Detail & Related papers  (2026-03-04T18:16:58Z)
• ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation [55.467742403416175]
  We introduce a physics-driven neural algorithm that translates large-scale motion capture to humanoid embodiments.<n>We learn a unified multimodal controller that supports both dense references and sparse task specifications.<n>Results show that ULTRA generalizes to autonomous, goal-conditioned whole-body loco-manipulation from egocentric perception.
  arXiv  Detail & Related papers  (2026-03-03T18:59:29Z)
• UniForce: A Unified Latent Force Model for Robot Manipulation with Diverse Tactile Sensors [51.88112610411651]
  We propose a novel unified tactile representation learning framework that learns a shared latent force space across diverse tactile sensors.<n>UniForce reduces cross-sensor domain shift by jointly modeling inverse dynamics (image-to-force) and forward dynamics (force-to-image)<n>To avoid reliance on expensive external force/torque (F/T) sensors, we exploit static equilibrium and collect force-paired data via direct sensor--object--sensor interactions.
  arXiv  Detail & Related papers  (2026-02-01T11:03:01Z)
• GentleHumanoid: Learning Upper-body Compliance for Contact-rich Human and Object Interaction [14.278503723930998]
  GentleHumanoid is a framework that integrates impedance control into a whole-body motion tracking policy to achieve upper-body compliance.<n>We evaluate our approach in both simulation and on the Unitree G1 humanoid across tasks requiring different levels of compliance.
  arXiv  Detail & Related papers  (2025-11-06T18:59:33Z)
• Feel the Force: Contact-Driven Learning from Humans [52.36160086934298]
  Controlling fine-grained forces during manipulation remains a core challenge in robotics.<n>We present FeelTheForce, a robot learning system that models human tactile behavior to learn force-sensitive manipulation.<n>Our approach grounds robust low-level force control in scalable human supervision, achieving a 77% success rate across 5 force-sensitive manipulation tasks.
  arXiv  Detail & Related papers  (2025-06-02T17:57:52Z)
• ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation [62.58034332427291]
  ForceVLA is a novel end-to-end manipulation framework.<n>It treats external force sensing as a first-class modality within VLA systems.
  arXiv  Detail & Related papers  (2025-05-28T09:24:25Z)
• ForceGrip: Reference-Free Curriculum Learning for Realistic Grip Force Control in VR Hand Manipulation [0.10995326465245926]
  We present ForceGrip, a deep learning agent that synthesizes realistic hand manipulation motions.<n>We employ a three-phase curriculum learning framework comprising Finger Positioning, Intention Adaptation, and Dynamic Stabilization.<n>Our evaluations reveal ForceGrip's superior force controllability and plausibility compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-11T05:39:07Z)
• Towards Transferring Tactile-based Continuous Force Control Policies from Simulation to Robot [19.789369416528604]
  grasp force control aims to manipulate objects safely by limiting the amount of force exerted on the object. Prior works have either hand-modeled their force controllers, employed model-based approaches, or have not shown sim-to-real transfer. We propose a model-free deep reinforcement learning approach trained in simulation and then transferred to the robot without further fine-tuning.
  arXiv  Detail & Related papers  (2023-11-13T11:29:06Z)
• Nonprehensile Riemannian Motion Predictive Control [57.295751294224765]
  We introduce a novel Real-to-Sim reward analysis technique to reliably imagine and predict the outcome of taking possible actions for a real robotic platform. We produce a closed-loop controller to reactively push objects in a continuous action space. We observe that RMPC is robust in cluttered as well as occluded environments and outperforms the baselines.
  arXiv  Detail & Related papers  (2021-11-15T18:50:04Z)
• Adaptive Feature Alignment for Adversarial Training [56.17654691470554]
  CNNs are typically vulnerable to adversarial attacks, which pose a threat to security-sensitive applications. We propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths. Our method is trained to automatically align features of arbitrary attacking strength.
  arXiv  Detail & Related papers  (2021-05-31T17:01:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.