Cover Image

Demystifying Action Space Design for Robotic Manipulation Policies

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Feng, Yuchun, Zheng, Jinliang, Wang, Zhihao, Liu, Dongxiu, Li, Jianxiong, Pang, Jiangmiao, Wang, Tai, Zhan, Xianyuan
Format:	Preprint
Published:	2026
Subjects:	Robotics Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Efficient Robotic Policy Learning via Latent Space Backward Planning
by: Liu, Dongxiu, et al.
Published: (2025)

X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
by: Zheng, Jinliang, et al.
Published: (2025)

Universal Actions for Enhanced Embodied Foundation Models
by: Zheng, Jinliang, et al.
Published: (2025)

Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning
by: Li, Jianxiong, et al.
Published: (2024)

InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation
by: Yang, Shuai, et al.
Published: (2025)

RoboGround: Robotic Manipulation with Grounded Vision-Language Priors
by: Huang, Haifeng, et al.
Published: (2025)

CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling
by: Li, Hao, et al.
Published: (2025)

Towards Latency-Aware 3D Streaming Perception for Autonomous Driving
by: Peng, Jiaqi, et al.
Published: (2025)

LoGoPlanner: Localization Grounded Navigation Policy with Metric-aware Visual Geometry
by: Peng, Jiaqi, et al.
Published: (2025)

GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction
by: Chen, Xiao, et al.
Published: (2024)

Instruction-Guided Visual Masking
by: Zheng, Jinliang, et al.
Published: (2024)

GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenes
by: Chen, Xiao, et al.
Published: (2025)

VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding
by: Xu, Runsen, et al.
Published: (2024)

On-Device Diffusion Transformer Policy for Efficient Robot Manipulation
by: Wu, Yiming, et al.
Published: (2025)

InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
by: Chen, Xinyi, et al.
Published: (2025)

Robotic Programmer: Video Instructed Policy Code Generation for Robotic Manipulation
by: Xie, Senwei, et al.
Published: (2025)

Observe Then Act: Asynchronous Active Vision-Action Model for Robotic Manipulation
by: Wang, Guokang, et al.
Published: (2024)

A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning
by: Wen, Xin, et al.
Published: (2025)

Fast Visuomotor Policy for Robotic Manipulation
by: Jia, Jingkai, et al.
Published: (2025)

KAN We Flow? Advancing Robotic Manipulation with 3D Flow Matching via KAN & RWKV
by: Chen, Zhihao, et al.
Published: (2026)

Image Generation as a Visual Planner for Robotic Manipulation
by: Pang, Ye
Published: (2025)

Agentic Scene Policies: Unifying Space, Semantics, and Affordances for Robot Action
by: Morin, Sacha, et al.
Published: (2025)

BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation
by: Wang, Hongyu, et al.
Published: (2025)

StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception
by: Han, Evans, et al.
Published: (2026)

SaPaVe: Towards Active Perception and Manipulation in Vision-Language-Action Models for Robotics
by: Liu, Mengzhen, et al.
Published: (2026)

MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation
by: Shi, Hao, et al.
Published: (2025)

You Only Teach Once: Learn One-Shot Bimanual Robotic Manipulation from Video Demonstrations
by: Zhou, Huayi, et al.
Published: (2025)

PASG: A Closed-Loop Framework for Automated Geometric Primitive Extraction and Semantic Anchoring in Robotic Manipulation
by: Zhu, Zhihao, et al.
Published: (2025)

MAP-VLA: Memory-Augmented Prompting for Vision-Language-Action Model in Robotic Manipulation
by: Li, Runhao, et al.
Published: (2025)

RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation
by: Wang, Boyang, et al.
Published: (2026)

ClothPPO: A Proximal Policy Optimization Enhancing Framework for Robotic Cloth Manipulation with Observation-Aligned Action Spaces
by: Yang, Libing, et al.
Published: (2024)

From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation
by: Li, Yajie, et al.
Published: (2026)

F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions
by: Lv, Qi, et al.
Published: (2025)

Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies
by: Liang, Zhixuan, et al.
Published: (2025)

DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching
by: Chen, Jiayi, et al.
Published: (2026)

TAG: Target-Agnostic Guidance for Stable Object-Centric Inference in Vision-Language-Action Models
by: Zhou, Jiaying, et al.
Published: (2026)

TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation
by: Wen, Junjie, et al.
Published: (2024)

PhysiAgent: An Embodied Agent Framework in Physical World
by: Wang, Zhihao, et al.
Published: (2025)

FlowRAM: Grounding Flow Matching Policy with Region-Aware Mamba Framework for Robotic Manipulation
by: Wang, Sen, et al.
Published: (2025)

DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning
by: Li, Jianxiong, et al.
Published: (2024)