cs.RO（2026-08-06）

📊 共 28 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (24 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (24 篇)

#题目一句话要点标签🔗⭐
1 $ω$-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation 提出$ω$-0模型以解决人形机器人同时运动与操作问题 humanoid locomotion manipulation
2 In-Context VLA: Endowing Vision-Language-Action Models with Language via In-Context Post-Training and Agentic Tool Use 提出In-Context VLA以解决VLA模型语言理解不足问题 manipulation behavior cloning monocular depth
3 DyPES-VLA: Learning Shared Dynamics Priors and Embodiment-Specific Control for Cross-Embodiment Manipulation 提出DyPES-VLA以解决跨机器人形态操控问题 manipulation cross-embodiment embodiment transfer
4 KILVO: Kinematic-Inertial-LiDAR-Visual Odometry with Robust Multimodal Adaptation for Humanoid Robots 提出KILVO以解决类人机器人运动估计问题 humanoid humanoid robot visual odometry
5 GeniWorld: A Generalizable Interactive World Model for Robotic Manipulation via Visual Actions 提出GeniWorld以解决机器人操控在复杂环境中的泛化问题 manipulation world model world models
6 XEWorld: Can Action-Conditioned World Models Generalize to Unseen Robot Embodiments? 提出XEWorld以解决机器人模型跨体态泛化问题 manipulation world model world models
7 Beyond Flat Policies: Hierarchical Post-Training for Embodied Agents in Robotic Manipulation 提出HiRoC框架以解决机器人操作中的层次化任务规划问题 manipulation reinforcement learning vision-language-action
8 SkillMemo: Expert-guided Skill Memory Framework for Compositional Embodied Manipulation 提出SkillMemo框架以解决机器人操作中的技能记忆问题 manipulation diffusion policy vision-language-action
9 Visual Grounding in Zero-Shot Vision-Language Control 提出视觉语言模型以解决零样本控制中的决策基础问题 MPC MAE visual grounding
10 VIDP: Variable Impedance Diffusion Policy for Compliant Robot Manipulation from Diverse Demonstrations 提出可变阻抗扩散策略以解决机器人柔性操作问题 manipulation imitation learning diffusion policy
11 A Master-Salve Robot Manipulator for Needle-Based Teleoperation in MRI Chamber 提出一种安全的主从机器人以解决MRI室内腹部介入问题 teleoperation penetration multimodal
12 JoyAI-RA 0.5: Scaling Robot Manipulation Learning via Dual Action Alignment 提出JoyAI-RA 0.5以解决机器人操作学习数据稀缺问题 manipulation world model world models ✅
13 TRACE: Learned Proprioceptive Odometry for Legged Robots under Unreliable Contact Conditions 提出TRACE以解决腿式机器人在不可靠接触条件下的里程计问题 legged robot sim-to-real contact-aware
14 Design and Evaluation of a Touchscreen-Based Teleoperation Interface for Robotic Manipulators 提出触摸屏远程操作界面以解决传统操控方式的局限性 manipulation teleoperation
15 Acoustic-driven millimetric helical robot: ultrasonic synergistic manipulation in confined fluidic environment 提出协调多声场方法以提升毫米级螺旋机器人在生物环境中的操控能力 locomotion manipulation
16 Hijacking Robots with a Piece of Paper: A Systematic Study of Physical Prompt Injection in VLM-Controlled Robots 提出物理提示注入攻击研究以解决VLM控制机器人安全问题 manipulation scene understanding instruction following
17 PathCover: A Fast Convex Decomposition along a Path via Randomized Iterative Space Partitioning (RISP) on Point Clouds 提出PathCover以解决自主机器人导航中的障碍物区域生成问题 quadruped MPC trajectory optimization
18 Coordinated Multi-Robot Disassembly for Makespan Optimization of Large-Scale Assemblies 提出协调多机器人拆解方法以优化大规模装配的完工时间 motion planning task and motion planning
19 Nonvisual Classification of Ground-Condition by Artificial Proprioception in an Amoeba-Inspired Autonomous Walking Robot 提出基于人工本体感知的地面状态非视觉分类方法 legged robot multimodal
20 Robot Learning from Human Demonstrations: Handwritten Alphabet Trajectories and Human-Likeness Evaluation 提出基于人类示范的机器人学习框架以提升人类相似性 teleoperation
21 ARGUS: Aligning Robot Scene Geometry Under Shifting Views with Large 3D Vision Models 提出ARGUS以解决机器人场景几何对视角依赖的问题 manipulation
22 Fast and Accurate: An Adaptive VLA Inference Framework through Environment-aware Model Selection 提出环境感知模型选择框架以解决VLA推理效率问题 manipulation dual-arm reinforcement learning
23 A Master-Slave Robot Manipulator for Needle-Based Teleoperation in MRI Chamber 提出一种安全的主从机器人以解决MRI室内针灸操作问题 teleoperation penetration multimodal
24 LyEvO: Lyapunov-Guided Evolutionary Optimization for Safe and Robust Sim-to-Real Policy Learning 提出LyEvO以解决安全和鲁棒性不足的仿真到现实转移问题 sim-to-real policy learning

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

#题目一句话要点标签🔗⭐
25 Prior-SG: Task and Prior Driven Region Segmentation for Scene Graphs in Arbitrarily-Structured Environments 提出Prior-SG以解决开放式环境中的场景图生成问题 open-vocabulary open vocabulary large language model

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

#题目一句话要点标签🔗⭐
26 Search-Aided Joint Agent-Environment Reinforcement Learning for Robust Lifelong Multi-Agent Path Finding with Rotations 提出搜索辅助联合强化学习以解决复杂的多智能体路径规划问题 reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)

#题目一句话要点标签🔗⭐
27 IcFuzz: Fuzzing Isaac Sim with Semantic Stage Guidance and Multi-level Mutation 提出IcFuzz以解决Isaac Sim模拟器的模糊测试问题 embodied AI

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

#题目一句话要点标签🔗⭐
28 Transcutaneous Spinal Cord Stimulation Disrupts Conscious Ankle Proprioception and Produces a More Constrained Locomotor Pattern in Unimpaired Adults 研究表明经皮脊髓刺激影响意识踝关节本体感觉与步态模式 spatiotemporal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页