Image de couverture de livre

Beyond Pixels: Learning Invariant Rewards for Real-World Robotics From a Few Demonstrations

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xu, Tengye, Sun, Yangting, Shen, Ziju, Chen, Guanqi, Fu, Zhen, yizhou, Chen, Chen, Hua, Pan, Jia
Format:	Preprint
Publié:	2026
Sujets:	Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

PRISM: Projection-based Reward Integration for Scene-Aware Real-to-Sim-to-Real Transfer with Few Demonstrations
par: Sun, Haowen, et autres
Publié: (2025)

Semantically Structured Mixture-of-Experts for Compositional Robotic Manipulation
par: Deng, Chengyu, et autres
Publié: (2026)

Language-Augmented Symbolic Planner for Open-World Task Planning
par: Chen, Guanqi, et autres
Publié: (2024)

Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learning
par: Yu, Dongjie, et autres
Publié: (2026)

Restoring Noisy Demonstration for Imitation Learning With Diffusion Models
par: Chen, Shang-Fu, et autres
Publié: (2025)

Reinforced Embodied Planning with Verifiable Reward for Real-World Robotic Manipulation
par: Bo, Zitong, et autres
Publié: (2025)

LongBench: Evaluating Robotic Manipulation Policies on Real-World Long-Horizon Tasks
par: Chen, Xueyao, et autres
Publié: (2026)

ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics
par: Chen, Letian, et autres
Publié: (2024)

One-Shot Real-World Demonstration Synthesis for Scalable Bimanual Manipulation
par: Zhou, Huayi, et autres
Publié: (2025)

Sampling-Based System Identification with Active Exploration for Legged Robot Sim2Real Learning
par: Sobanbabu, Nikhil, et autres
Publié: (2025)

RoboWheel: A Data Engine from Real-World Human Demonstrations for Cross-Embodiment Robotic Learning
par: Zhang, Yuhong, et autres
Publié: (2025)

Understanding Particles From Video: Property Estimation of Granular Materials via Visuo-Haptic Learning
par: Zhang, Zeqing, et autres
Publié: (2024)

POMDP-Guided Active Force-Based Search for Robotic Insertion
par: Wang, Chen, et autres
Publié: (2024)

Learning Stability Certificate for Robotics in Real-World Environments
par: Shen, Zhe
Publié: (2025)

RoboPaint: From Human Demonstration to Any Robot and Any View
par: Fan, Jiacheng, et autres
Publié: (2026)

EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards
par: Wang, Ruixiang, et autres
Publié: (2026)

FeasibleCap: Real-Time Embodiment Constraint Guidance for In-the-Wild Robot Demonstration Collection
par: Yin, Zi, et autres
Publié: (2026)

Beyond Viewpoint Generalization: What Multi-View Demonstrations Offer and How to Synthesize Them for Robot Manipulation?
par: Cai, Boyang, et autres
Publié: (2026)

Tactile Beyond Pixels: Multisensory Touch Representations for Robot Manipulation
par: Higuera, Carolina, et autres
Publié: (2025)

Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface
par: Zhao, Yujie, et autres
Publié: (2025)

AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models
par: Sun, Xiaoquan, et autres
Publié: (2026)

Whole-Body Control Through Narrow Gaps From Pixels To Action
par: Wu, Tianyue, et autres
Publié: (2024)

Few-Shot Demonstration-Driven Task Coordination and Trajectory Execution for Multi-Robot Systems
par: Kim, Taehyeon, et autres
Publié: (2025)

Human Demonstrations are Generalizable Knowledge for Robots
par: Cui, Te, et autres
Publié: (2023)

Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation
par: Zhang, Hai, et autres
Publié: (2026)

Learning Getting-Up Policies for Real-World Humanoid Robots
par: He, Xialin, et autres
Publié: (2025)

Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic Manipulation
par: Xie, Yifan, et autres
Publié: (2026)

Learning Fine Pinch-Grasp Skills using Tactile Sensing from A Few Real-world Demonstrations
par: Mao, Xiaofeng, et autres
Publié: (2023)

UniDomain: Pretraining a Unified PDDL Domain from Real-World Demonstrations for Generalizable Robot Task Planning
par: Ye, Haoming, et autres
Publié: (2025)

Vision-Based Dexterous Motion Planning by Dynamic Movement Primitives with Human Hand Demonstration
par: Chen, Nuo, et autres
Publié: (2024)

DexCanvas: Bridging Human Demonstrations and Robot Learning for Dexterous Manipulation
par: Xu, Xinyue, et autres
Publié: (2025)

WorldEval: World Model as Real-World Robot Policies Evaluator
par: Li, Yaxuan, et autres
Publié: (2025)

ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations
par: Zhang, Jiahui, et autres
Publié: (2025)

Learning Generalizable Robot Policy with Human Demonstration Video as a Prompt
par: Zhu, Xiang, et autres
Publié: (2025)

Augmented Reality-Enhanced Robot Teleoperation for Collecting User Demonstrations
par: Gong, Shiqi, et autres
Publié: (2025)

Training People to Reward Robots
par: Sun, Endong, et autres
Publié: (2025)

W-PoseNet: Dense Correspondence Regularized Pixel Pair Pose Regression
par: Xu, Zelin, et autres
Publié: (2019)

From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models
par: Gumbsch, Christian, et autres
Publié: (2026)

MA-ROESL: Motion-aware Rapid Reward Optimization for Efficient Robot Skill Learning from Single Videos
par: Wang, Xianghui, et autres
Publié: (2025)

Demonstrating Agile Flight from Pixels without State Estimation
par: Geles, Ismail, et autres
Publié: (2024)