arXiv Machine Learning
Social Humanoid: Socially Responsive Human-Humanoid Interaction
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computer Vision
Oct 15
$\lambda_0$: Scaling Open-World Egocentric Human Data for Humanoid Loco-Manipulation
arXiv:2610.18950v1 Announce Type: cross Abstract: Humanoid loco-manipulation requires coordinated whole-body interaction with the physical world, yet collecting robot demonstrations at scale remains...
arXiv AI
Sep 23
HIGenNTO: Scalable Humanoid Interaction Generation via Noise-Space Trajectory Optimization
arXiv:2609.22611v1 Announce Type: cross Abstract: Humanoid robots can acquire complex skills by imitating kinematic humanoid motion references, yet reliable references for contact-rich interactions r...
arXiv AI
Jul 17
Scaling Behavior Foundation Model for Humanoid Robots
arXiv:2607. 15163v1 Announce Type: cross Abstract: Humanoid control requires natural whole-body coordination, precise real-time responses to control signals, and robust generalization across diverse environmental contexts, making it a cornerstone for generalist embodied agents.
arXiv AI
Oct 21
VLM-Guided Contact Retargeting and Generative Partner Modeling for Humanoid-Human Interaction
arXiv:2610.28523v1 Announce Type: cross Abstract: Humanoid-human interaction requires robots to operate under severe partial observability: during close physical contact, the human partner is occlude...
arXiv AI
Sep 18
GigaBrain-WBC-0.5: A Behavior World Model for Robust Humanoid Whole-Body Tracking with Environment Interaction
The paper introduces InterTrack, a behavior world model that enables humanoid robots to perform robust whole-body tracking while interacting with varied terrain and objects. Using a Transformer architecture, InterTrack predicts actions, states, and behavior distributions conditioned on the environment, and it is trained with an automated pipeline that reconstructs 3D support geometry from retargeted motions. The system achieves an 81.3% success rate on terrain interaction, a 99.3% fall-recovery rate, and outperforms leading baselines in both free-space tracking and cross-terrain scenarios.
arXiv AI
Oct 23
SP-HLM: Sparse-Pose-Driven Motion Generation and Whole-Body Control for Humanoid Loco-Manipulation
SP-HLM is a framework for humanoid loco‑manipulation that uses a sparse‑pose‑driven interface to separate spatial intent from whole‑body coordination. It predicts five task‑critical body poses and finger joint positions via a vision‑language‑action model, then reconstructs full‑body motion in real time with a motion generation model and integrates this with a latent motion prior for control. Experiments on simulation and a real robot show better motion tracking, coordination, and manipulation success compared to existing methods.