APEX: Adaptive Policy Execution for Precise Manipulation

2026-06-15 · Mengfei Zhao, Chenxi Jiang, Tuo An, Jindou Jia, Jianfei Yang arxiv

Modern imitation learning methods, including visuomotor and Vision-Language-Action (VLA) policies, typically output high-level action references that are executed by low-level controllers. However, the absence of higher-order reference signals, together with the policy's lack of awareness of the underlying low-level control dynamics during training, inevitably induces an execution gap. As a result, realized actions deviate systematically from policy-commanded ones, with a critical impact on precision-sensitive manipulation. Prior work either modifies the policy architecture or the low-level controller, both requiring intrusive changes to the pretrained policy or packaged controller. This raises a natural question: when the policy and controller are both treated as inaccessible black boxes, can we bridge the execution gap? We propose Adaptive Policy Execution (APEX), a plug-and-play framework inserted between the policy and the controller that reconstructs a dynamically feasible reference from policy outputs and adapts at test-time according to low-level state feedback, with a provable convergence guarantee. Extensive empirical studies show that APEX reduces controller-induced tracking error by 41.2% on demonstration replay and improves manipulation success by 4.8--25.8 percentage points across four visuomotor and VLA policy classes.

📄 PDF Abstract BibTeX arXiv:2606.16504

Code (0)

등록된 구현이 없습니다.

ESCAPE: Episodic Spatial Memory and Adaptive Execution Policy for Long-Horizon Mobile Manipulation

2026-04-15 · Jingjing Qian, Zeyuan He, Chen Shi, Lei Xiao 외 arxiv

Coordinating navigation and manipulation with robust performance is essential for embodied AI in complex indoor environments. However, as tasks extend over long horizons, existing methods often struggle due to catastroph…

APEX: Empowering LLMs with Physics-Based Task Planning for Real-time Insight

2025-05-20 · Wanjing Huang, Weixiang Yan, Zhen Zhang, Ambuj Singh

Large Language Models (LLMs) demonstrate strong reasoning and task planning capabilities but remain fundamentally limited in physical interaction modeling. Existing approaches integrate perception via Vision-Language Mod…

Causal Inference Decision Making motion prediction Reinforcement Learning (RL)+1

APEX: Action Priors Enable Efficient Exploration for Robust Motion Tracking on Legged Robots

2025-11-12 · Shivam Sood, Laukik Nakhwa, Sun Ge, Yuhong Cao 외 arxiv

Learning natural, animal-like locomotion from demonstrations has become a core paradigm in legged robotics. Despite the recent advancements in motion tracking, most existing methods demand extensive tuning and rely on re…

Reinforcement Learning

HiPolicy: Hierarchical Multi-Frequency Action Chunking for Policy Learning

2026-04-07 · Jiyao Zhang, Zimu Han, Junhan Wang, Xionghao Wu 외 arxiv

Robotic imitation learning faces a fundamental trade-off between modeling long-horizon dependencies and enabling fine-grained closed-loop control. Existing fixed-frequency action chunking approaches struggle to achieve b…

Human-AI Co-Embodied Intelligence for Scientific Experimentation and Manufacturing

2025-11-03 · Xinyi Lin, Yuyang Zhang, Yuanhang Gan, Juntao Chen 외 arxiv

Scientific experimentation and manufacturing rely on prolonged protocol development and complex, multi-step implementation, which require continuous human expertise for precise execution and decision-making, limiting int…