arXiv
Pixel: Genel Amaçlı Mobil Manipülasyonu Öğrenmek için Ortak Tasarlanmış Tam Yığınlı Robot Sistemi
Genel amaçlı mobil manipülasyon, yetenekli robot donanımı, ölçeklenebilir gösteri toplama, etkileyic...
HABERLER
Tüm Haberler
Yapay zekâ dünyasından son haberler, derinlikli analizler, teknik incelemeler.
114Yazı
1Yazar
5.1KOkuma · 30g
5Bu Hafta
arXiv
Pixel-UMI: Sensörlü İnsan Gösterilerinden Ortam Farkında Tüm Vücut Manipülasyonunu Öğrenme
Sensörlü insan gösterileri, mobil manipülasyon için ölçeklenebilir veriler sunar, ancak düzenleme fa...
arXiv
D&A: Ayrıştırma Açıklaması ve Değerlendirmesi, VLM’lerin Sıfır Atışlı Robotik Ödül Modelleri Olmasını Sağlıyor
Vizyon-Dil Modelleri (VLM'ler), robot öğreniminde sıfır çekimli video görev ilerlemesi tahmini için ...
arXiv
Hierarchical World Models with Implicit Dynamics
Planning with world models enables test-time adaptation for embodied agents, offering superior gener...
arXiv
RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory
Recent work shows that a frozen robot policy performs far better inside an agent harness, where cont...
arXiv
SymAnt: Grounding Long-Horizon Action Anticipation with Adaptable Symbolic Priors
As robots and intelligent systems increasingly interact with humans, they must anticipate long seque...
arXiv
ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning
Vision-Language-Action (VLA) models have made substantial progress in robotic manipulation, but thei...
arXiv
Pushing Dexterity and Safety for In-Hand Object Pose Reaching That Works Remarkably Well
Dexterous manipulation with multi-fingered hands is the next frontier of robotics, yet learned hand ...
arXiv
Perceiving and Predicting Dynamic Sports: Spatiotemporal Intelligence in Vision Models for Egocentric Tennis Video
Agile robots require spatiotemporal intelligence to interpret scenes, reason about interactions, and...
arXiv
OSWAM: An Effective World Action Model with One-Step Action Generation
Direct-policy World Action Models (WAM) have demonstrated the benefits of decoupling action generati...
arXiv
Profiling a Frontier Agent with EBench: From Direct Control to Harness with Policy
Frontier multimodal large language models (MLLMs) can control robots without robot-specific training...
arXiv
Pretraining Knows What, Simulation Teaches How: Compositional Generalization in a Sim-Trained Robot Agent
A robot policy needs to understand what a task is asking for in a scene, and how to move the robot t...
arXiv
Learning Force-Reactive Humanoid Loco-Manipulation
Many everyday tasks require controlling contact force as well as motion.
arXiv
SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning
Training generalizable embodied agents requires realistic, varied, and simulation-ready indoor envir...
arXiv
RobustRLlib: A Unified Library and Benchmark for Robust Reinforcement Learning Algorithms
Robust reinforcement learning (RL) is critical for reliable real-world deployment, where policies ma...