cs.RO（2026-04-13）

📊 共 27 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (21 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (21 篇)

#题目一句话要点标签🔗⭐
1 CLAW: Composable Language-Annotated Whole-body Motion Generation CLAW：可组合的语言标注全身运动生成，用于人型机器人 humanoid humanoid robot whole-body control
2 AffordSim: A Scalable Data Generator and Benchmark for Affordance-Aware Robotic Manipulation AffordSim：一个可扩展的具身操作数据生成器与基准测试平台 manipulation sim-to-real domain randomization
3 ViserDex: Visual Sim-to-Real for Robust Dexterous In-hand Reorientation ViserDex：利用视觉Sim-to-Real实现鲁棒的灵巧手部物体重定向 legged robot manipulation dexterous manipulation
4 Simulator Adaptation for Sim-to-Real Learning of Legged Locomotion via Proprioceptive Distribution Matching 提出基于本体感受分布匹配的模拟器自适应方法，提升腿足机器人Sim-to-Real性能 quadruped legged locomotion locomotion
5 CLASP: Closed-loop Asynchronous Spatial Perception for Open-vocabulary Desktop Object Grasping CLASP：面向开放词汇桌面物体抓取的闭环异步空间感知 manipulation sim-to-real teleoperation
6 Ψ-Map: Panoptic Surface Integrated Mapping Enables Real2Sim Transfer 提出Ψ-Map，实现大规模场景下几何精确、语义连贯的全景表面重建与Real2Sim迁移。 real2sim 3D gaussian splatting 3DGS
7 Safe Human-to-Humanoid Motion Imitation Using Control Barrier Functions 提出基于控制屏障函数的安全人-人形机器人运动模仿框架 humanoid humanoid robot motion retargeting
8 Fast-SegSim: Real-Time Open-Vocabulary Segmentation for Robotics in Simulation 提出Fast-SegSim，实现机器人仿真中实时开放词汇分割重建 sim-to-real gaussian splatting splatting
9 Grounded World Model for Semantically Generalizable Planning 提出Grounded World Model，用于语义可泛化的规划任务 MPC model predictive control world model
10 ScoRe-Flow: Complete Distributional Control via Score-Based Reinforcement Learning for Flow Matching 提出ScoRe-Flow，通过基于Score的强化学习微调Flow Matching策略，实现更高效的机器人控制。 locomotion manipulation reinforcement learning
11 AIM: Intent-Aware Unified world action Modeling with Spatial Value Maps 提出AIM，利用空间价值图建模交互意图，提升机器人操作任务性能。 manipulation reinforcement learning world model
12 WM-DAgger: Enabling Efficient Data Aggregation for Imitation Learning with World Models 提出WM-DAgger以解决模仿学习中的数据聚合问题 manipulation imitation learning world model ✅
13 3D-Anchored Lookahead Planning for Persistent Robotic Scene Memory via World-Model-Based MCTS 提出基于世界模型的3D锚定前瞻规划，用于机器人持久场景记忆 manipulation world model world models
14 Micro-Dexterity in Biological Micromanipulation: Embodiment, Perception, and Control 提出微灵巧性框架，分析生物微操作中的具身、感知与控制问题。 locomotion manipulation dexterous manipulation
15 Dyadic Partnership(DP): A Missing Link Towards Full Autonomy in Medical Robotics 提出Dyadic Partnership(DP)范式，促进医疗机器人向完全自主化演进 manipulation world model world models
16 ComSim: Building Scalable Real-World Robot Data Generation via Compositional Simulation ComSim：通过组合式仿真构建可扩展的真实世界机器人数据生成方法 sim2real world model world models
17 EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems 提出EmbodiedGovBench以解决机器人系统治理评估问题 manipulation embodied AI foundation model
18 Optimal Kinodynamic Motion Planning Through Anytime Bidirectional Heuristic Search with Tight Termination Condition 提出BTIT*算法，通过双向启发式搜索实现运动规划的渐近最优和快速求解 motion planning
19 Identifying Inductive Biases for Robot Co-Design 提出自适应协同设计算法，提升软体机器人形态与控制的协同优化效率。 locomotion manipulation
20 Disentangled Point Diffusion for Precise Object Placement 提出TAX-DPD：一种解耦点扩散框架，用于精确物体放置，提升机器人操作精度。 manipulation
21 Modeling, Analysis and Activation of Planar Viscoelastically-combined Rimless Wheels 提出基于粘弹性元件组合的无轮辋被动行走机器人，探索新型行走支持设备。 dynamic walking

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

#题目一句话要点标签🔗⭐
22 DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models 提出DA-PTQ，解决VLA模型量化后在机器人控制中产生的轨迹漂移问题 embodied AI vision-language-action VLA
23 StarVLA-$α$: Reducing Complexity in Vision-Language-Action Systems StarVLA-$α$：简化视觉-语言-动作系统，实现通用机器人控制。 vision-language-action VLA ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
24 Diffusion Reinforcement Learning Based Online 3D Bin Packing Spatial Strategy Optimization 提出基于扩散强化学习的在线三维装箱空间策略优化算法 reinforcement learning deep reinforcement learning DRL
25 Multi-ORFT: Stable Online Reinforcement Fine-Tuning for Multi-Agent Diffusion Planning in Cooperative Driving Multi-ORFT：面向协同驾驶的多智能体扩散规划稳定在线强化微调 diffusion policy multimodal

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
26 MR.ScaleMaster: Scale-Consistent Collaborative Mapping from Crowd-Sourced Monocular Videos MR.ScaleMaster：解决众包单目视频协作建图中的尺度漂移与崩溃问题 VGGT

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
27 Learning Racket-Ball Bounce Dynamics Across Diverse Rubbers for Robotic Table Tennis 提出基于高斯过程的球拍-球反弹动力学建模方法，提升机器人乒乓球控制精度。 PULSE

⬅️ 返回 cs.RO 首页 · 🏠 返回主页