LUCID: Latent-Skill Unified Control via Imagined Dynamics for Long-Horizon Humanoid Loco-Manipulation
Cheng Guo, Mingzhe Ni, Angelo Cangelosi, Arash Ajoudani
cs.LG, cs.RO
Submitted: 2026-08-07
Updated: 2026-08-11
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- World Models
- Dream to Control: Learning Behaviors by Latent Imagination
- Temporal Difference Learning for Model Predictive Control
- Learning and Transfer of Modulated Locomotor Controllers
- SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending
- Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics
- HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model
- Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning
- Neural probabilistic motor primitives for humanoid control
- Proximal Policy Optimization Algorithms
- PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System
- PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction
- HDMI: Learning Interactive Humanoid Whole-Body Control from Human Videos
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks