|
Vision language action models for robotic manipulation: A comparative evaluation of policy and value architectures
|
Authors: Hongliang Wang, Jin Liu, Xiaolin Zhu, Qiang Fu, Yuhua Zheng, Wangmeng Zuo, Changqing Zou, Evgeny Burnaev
Status: Final
Date of publication: 30 September 2026
Published in: ITU Journal on Future and Evolving Technologies, Volume 7 (2026), Issue 3, Pages 477-491
Article DOI : https://doi.org/10.52953/ELHO4991
|
Abstract:
Vision Language Action (VLA) models have become an important approach to robotic manipulation by integrating visual observations, language instructions, and robot states for action generation. Nevertheless, behavior cloning-based VLA policies remain vulnerable to distribution shifts, accumulated execution errors, and failure recovery difficulties during long horizon closed-loop operation. This paper investigates whether an auxiliary value architecture can improve the reliability of VLA policy learning without replacing the policy as the low-level controller. We present a controlled real-robot study on a LeRobot SO-101 platform covering block grasping, placing, and sorting tasks. The study compares three policy architectures, namely ACT, diffusion policy, and SmolVLA, and two value architectures, namely ValueLite and ValueVision. The value models estimate state quality, identify early failure precursors, and generate Advantage-Conditioned Policy (ACP) labels for policy retraining. Our evaluation considers policy-only success, human-assisted success, intervention rate, recovery success, completion time, action smoothness, value prediction error, early failure detection, and inference cost. In addition, data-controlled and mechanism-level ablations are designed to separate the effects of additional recovery or rollout data from the effects of learned value signals and ACP conditioning. The results show that value models provide useful trajectory ranking and failure-detection signals in the studied manipulation setting. Value-guided variants improve assisted task completion and reduce takeover frequency relative to recovery-only training, although these gains must be distinguished from fully autonomous policy performance. |
Keywords: Advantage-conditioned policy, closed-loop evaluation, robotic manipulation, value architecture, vision language action models
Rights: © International Telecommunication Union, available under the CC BY-NC-ND 3.0 IGO license.
|
|
| ITEM DETAIL | ARTICLE | PRICE | |
|---|
ENGLISH 
Full article (PDF) |
|
| 0
| Free of charge | DOWNLOAD |
|
|
| |