Skip to content
AI News HubLIVE
Original source2 min read

ForPC: Force-Aware Whole-Body Control for Precise Humanoid Cart Pushing

Summary

Researchers propose ForPC, a force-aware whole-body control framework that regulates cart velocity via two-stage reinforcement learning. Without external force sensors or human demonstrations, it significantly outperforms a locomotion-only baseline in simulation and transfers zero-shot to a physical Unitree G1, pushing a 30 kg cart at 0.5 m/s.

SourcearXiv RoboticsAuthor: ZhenYu Zou, Xing Liu, ShiChuang Wang, YunLong Dong, LiNan Deng, Feng Hua, Jun Wan, Cheng Cheng
ForPC: Force-Aware Whole-Body Control for Precise Humanoid Cart Pushing
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 5 Nov 2026]

Title:ForPC: Force-Aware Whole-Body Control for Precise Humanoid Cart Pushing

View a PDF of the paper titled ForPC: Force-Aware Whole-Body Control for Precise Humanoid Cart Pushing, by ZhenYu Zou and 7 other authors

View PDF HTML (experimental)

Abstract:Humanoid robots are expected to take over strenuous material handling in manufacturing, logistics, and healthcare, where operating existing wheeled carts would let them move heavy loads without modifying the workplace. However, humanoid cart pushing remains challenging because the bimanual grasp closes a force-coupled loop in which the contact wrenches that drive the cart also disturb the robot's balance, and payload changes alter the coupled dynamics. We propose ForPC, a force-aware whole-body control framework that regulates cart velocity through two-stage reinforcement learning. A locomotion prior is first trained under varied hand loads and upper-body postures to provide balance support. A force latent and a state latent are then inferred from onboard observations, without external force sensors, and fed to a residual policy that coordinates bounded arm, waist, and leg adjustments with base-velocity commands. Multi-objective rewards penalize bimanual internal opposition, grasp slip, and actuator saturation, encouraging the policy to apply contact force on demand without human demonstrations. Sim-to-sim experiments show that ForPC reduces cart-velocity RMSE by up to 68.2% relative to a locomotion-only baseline (Loco-only) and cross-track RMSE by up to 74.2% on the multi-bend route. Trained solely in simulation, the policy also transfers to a physical Unitree G1 without real-world training or fine-tuning and, with no payload-specific adjustment, pushes a cart carrying up to 30 kg at 0.5 m/s. These results suggest that humanoid robots could eventually replace humans for efficient material handling in daily life.

Comments: 14 pages, 7 figures, 4 tables. Project website: this https URL. Corresponding author: Cheng Cheng

Subjects:

Robotics (cs.RO)

Cite as: arXiv:2611.08664 [cs.RO]

(or arXiv:2611.08664v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2611.08664

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Cheng Cheng [view email] [v1] Thu, 5 Nov 2026 20:21:04 UTC (4,372 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled ForPC: Force-Aware Whole-Body Control for Precise Humanoid Cart Pushing, by ZhenYu Zou and 7 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.RO

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • ForPC uses two-stage RL: a locomotion prior for balance support, then a residual policy coordinating bounded arm, waist, and leg adjustments.
  • Force and state latents are inferred from onboard observations, eliminating the need for external force sensors.
  • Sim-to-sim experiments show up to 68.2% reduction in cart-velocity RMSE and up to 74.2% reduction in cross-track RMSE on multi-bend routes.
  • The policy, trained solely in simulation, transfers zero-shot to a physical Unitree G1 and pushes a 30 kg cart at 0.5 m/s without payload-specific tuning.

Highlights and analysis are generated automatically and may contain errors. Check the original source.