cs.RO（2026-04-29）

📊 共 12 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (9) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱一：机器人控制 (Robot Control) (9 篇)

#题目一句话要点标签🔗⭐
1 Reactive Motion Generation via Phase-varying Neural Potential Functions 提出相位可变神经势函数(PNPF)，用于解决学习自演示中轨迹交叉时的运动生成问题。 manipulation motion generation reactive motion
2 STARRY: Spatial-Temporal Action-Centric World Modeling for Robotic Manipulation STARRY：面向机器人操作的时空动作中心世界建模 manipulation world model world models
3 Bi-Level Optimization for Contact and Motion Planning in Rope-Assisted Legged Robots 提出双层优化框架，用于绳索辅助腿式机器人攀爬的接触与运动规划 legged robot locomotion motion planning
4 3D Generation for Embodied AI and Robotic Simulation: A Survey 针对具身智能与机器人仿真的3D生成技术综述，弥合虚拟与现实差距。 sim-to-real sim2real embodied AI
5 HiPAN: Hierarchical Posture-Adaptive Navigation for Quadruped Robots in Unstructured 3D Environments HiPAN：用于非结构化3D环境中四足机器人的分层姿态自适应导航 quadruped locomotion curriculum learning
6 ATLAS: An Annotation Tool for Long-horizon Robotic Action Segmentation ATLAS：用于长时程机器人动作分割的标注工具，支持多模态数据同步可视化。 manipulation reinforcement learning policy learning
7 Atomic-Probe Governance for Skill Updates in Compositional Robot Policies 提出原子探针治理方法，用于组合机器人策略中技能更新的可靠性保障 manipulation dual-arm
8 Stochastic Entanglement of Deterministic Origami Tentacles For Universal Robotic Gripping 提出基于确定性折纸触手随机缠绕的通用机器人抓取器 manipulation
9 Alter-Art: Exploring Embodied Artistic Creation through a Robot Avatar 提出Alter-Art框架，通过机器人化身探索具身艺术创作的新范式 teleoperation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
10 LLM-Flax : Generalizable Robotic Task Planning via Neuro-Symbolic Approaches with Large Language Models LLM-Flax：利用大语言模型和神经符号方法实现通用机器人任务规划 large language model
11 Walk With Me: Long-Horizon Social Navigation for Human-Centric Outdoor Assistance 提出Walk with Me框架，实现基于人类指令的户外长程社交导航。 vision-language-action VLA

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
12 Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising X-WAM：统一的4D世界模型，通过异步去噪实现高效机器人动作执行和高质量4D场景合成。 world model world models world action model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页