PERA: Plug-in Experts for Robotic Actions in Continual Whole-Body Control
cs.RO
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- Perpetual Humanoid Control for Real-time Simulated Avatars
- KungfuBot2: Learning Versatile Motion Skills for Humanoid Whole-Body Control
- Continual Humanoid Motion Learning
- LiMoDE: Rethinking Lifelong Robot Manipulation from a Mixture-of-Dynamic-Experts Perspective
- MoE-Loco: Mixture of Experts for Multitask Locomotion
- FlexOlmo: Open Language Models for Flexible Data Use
- Continual Policy Consolidation for Lifelong Robot Learning
- HoloMotion-1 Technical Report
- SuperMimic: Scaling Humanoid Whole-Body Control with One Differentiable World Model
- Proximal Policy Optimization Algorithms
- Deep Whole-body Parkour
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation