cs.RONov 6, 2026

SUGARv2: Learning Diverse Visual Humanoid Loco-Manipulation Skills from Synthesized Interaction References

Authors: Tianshu Wu, Tianxiang Gui, Yue Chen, Tingxu Liu, Ziye Peng, Guangjie Yang, Xiangqi Kong, Ye Shi, 

Organizations: CFCS, School of Computer Science, Peking University · ShanghaiTech University · Beihang University

Abstract

Scaling up visual humanoid loco-manipulation skill acquisition requires reducing the human effort needed as tasks and spatial configurations expand, particularly in demonstration collection and task-specific training design. We present SUGARv2, a unified framework for learning diverse visual humanoid loco-manipulation skills through interaction reference synthesis and a shared training pipeline. To obtain diverse references at low cost, we adapt reusable task templates to different spatial configurations, synthesizing coordinated robot and object motions. To reduce task-specific reward design and training effort, we use reference-based imitation as a common learning objective across tasks. We first train privileged teachers to execute these references, then train visual policies through teacher distillation and reinforcement learning with the same reference-based mimic rewards, using diverse object instances and visual domain randomization to support visual generalization and sim-to-real transfer. Across five humanoid loco-manipulation tasks, SUGARv2 achieves a mean success rate of 91.0% in simulation. Deployment on a real humanoid robot further demonstrates successful sim-to-real transfer for whole-body manipulation. These results demonstrate the framework's potential for learning diverse visual humanoid loco-manipulation skills.

Figures & tables

Explore similar work

CardsList
  1. SUGAR: A Scalable Human-Video-Driven Generalizable Humanoid Loco-Manipulation Learning Framework

    May 19, 2026Tianshu Wu, Xiangqi Kong, Yue Chen +5Humanoid Loco-ManipulationLong-Horizon Robotic Manipulation

  2. FetchMan: Learning Visual Humanoid Loco-Manipulation Policies from Simulated Experiences

    Aug 17, 2026Omar Rayyan, Zhi Li, Max Argus +4Robotic Loco-ManipulationLoco-Manipulation

  3. Zero-HLM: Generalizable Humanoid Loco-Manipulation without Real Robot Data

    Oct 26, 2026Dianyi Yang, Mengya Liu, Zhumei Wang +9Humanoid Loco-ManipulationSim-to-Real Transfer