cs.RO（2026-10-14）

📊 共 58 篇论文 | 🔗 9 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (41 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (8 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱三：空间感知与语义 (Perception & Semantics) (3 🔗1) 支柱七：动作重定向 (Motion Retargeting) (2)

🔬 支柱一：机器人控制 (Robot Control) (41 篇)

#题目一句话要点标签🔗⭐
1 PolyMorph: Learning Locomotion Policy for Cross-Embodiment Adaptation 提出PolyMorph框架以解决异构腿部机器人运动策略适应问题 quadruped legged robot bipedal
2 KinoGen: Customizable Humanoid Loco-Manipulation References via Kinematically Grounded Video Generation 提出KinoGen框架以生成可定制的人形运动操控参考 humanoid manipulation loco-manipulation ✅
3 E2DRL: End-to-End Differentiable Reinforcement Learning for 3D Obstacle Avoidance in Quadruped Robots 提出E2DRL以解决四足机器人3D障碍物规避问题 quadruped legged locomotion locomotion
4 Coordi-pi: Coordination-Aware Dual-Hand Action Representation for Bimanual Dexterous Manipulation 提出Coordi-π以解决双手灵巧操作中的动作表示问题 manipulation dexterous manipulation bi-manual
5 TacClaw-Infinity: A Large-Scale Vision-Tactile-Language-Action Dataset for Dexterous Manipulation 提出TacClaw-Infinity以解决触觉操控数据收集难题 manipulation dexterous manipulation cross-embodiment
6 Tactile-Guided Robot Learning: From Representation Learning to Foundation Models 提出触觉引导的机器人学习方法以解决传统触觉应用不足问题 manipulation policy learning world model
7 RoboSpan: Learning Modular Coordination Policies for High-DoF Whole-Body Mobile Manipulation with Teleoperation 提出RoboSpan以解决高自由度全身移动操控中的协调问题 locomotion manipulation mobile manipulation
8 Cracking Mobile Manipulation: From Failure Diagnosis to Agentic Robot System 提出故障诊断与干预以提升移动操作机器人系统的成功率 manipulation mobile manipulation vision-language-action ✅
9 One-shot Human Video-Guided Adaptation for Vision-Language-Action Models 提出CapPro框架以解决VLA模型快速适应新任务的问题 manipulation vision-language-action VLA
10 Hierarchical Residual Policy Learning for Real-World Mobile Manipulation with Sparse Human Guidance 提出HiRe-MoMa以解决真实世界移动操控中的稀疏人类指导问题 manipulation mobile manipulation policy learning
11 Graph-Reweighted Behavior Cloning with Human Interventions for Precise Robotic Manipulation 提出图重加权行为克隆以解决精确机器人操控中的数据质量问题 manipulation behavior cloning vision-language-action
12 AutoRSR: Automated Real-to-Sim-to-Real Data Generation for Scalable Robot Learning 提出AutoRSR框架以解决机器人学习数据生成的高成本问题 manipulation sim-to-real domain randomization
13 Beyond Kinematic Tracking: Preserving Expressive Characteristics in Humanoid Whole-Body Control 提出残差学习框架以增强类人机器人全身控制中的表现特征 humanoid humanoid robot whole-body control
14 Learning Navigation from Multimodal Demonstrations with Geometric Candidate Modes 提出一种层次化神经网络策略以解决多模态导航问题 bipedal biped behavior cloning
15 ObjDream: Guiding Vision-Language-Action Models with Object-Level Understanding and Future State Prediction 提出ObjDream以解决VLA模型在物体理解上的不足问题 manipulation vision-language-action VLA
16 FoveaVLA: Foveation Actions Replace the Wrist Camera in VLAs 提出FoveaVLA以解决传统腕部相机视野限制问题 manipulation vision-language-action VLA
17 Accelerating VLA Inference with Perturbation Informed Execution 提出PICES方法以解决VLA模型执行效率问题 manipulation vision-language-action VLA
18 Dual-arm Cooperation for Tabletop Wiping with Temporal Object Removal 提出双臂协作框架以解决桌面清洁中的物体移除问题 dual-arm motion planning task and motion planning
19 HiFun: a Hierarchical Framework for Efficient Functional Dexterous Manipulation Learning 提出HiFun框架以解决多指灵巧机器人手的功能性操作问题 manipulation dexterous hand dexterous manipulation ✅
20 Modeling and Understanding Neural Weights of Humanoid Policies with Diffusion 提出基于扩散模型的类人政策神经权重建模方法 humanoid humanoid control Unitree
21 ForceBench: Benchmarking Force Integration for Robotic Manipulation 提出ForceBench以解决机器人操作中的力集成评估问题 manipulation vision-language-action VLA ✅
22 PingpongDuo: Agile Humanoid Table Tennis Doubles with Safe Team Coordination 提出PingpongDuo以解决人形乒乓球双打中的安全协调问题 humanoid human motion
23 Complementary Future Token Pruning for World Action Models 提出CF-Prune以解决世界动作模型推理延迟问题 manipulation world action model world action models
24 Safe Reinforcement Learning with Receding-Horizon Safety Critic and Differentiable Action Shields 提出递归视野安全评论员以解决机器人强化学习中的安全问题 quadruped locomotion reinforcement learning
25 FOMI: A Force-Feedback Manipulation Interface for Teaching Contact-Rich Manipulation 提出FOMI以解决接触丰富操作反馈不足问题 manipulation teleoperation policy learning
26 Learning-Based Adaptive MPC for Magnetorquer-Only Satellite Attitude Control 提出基于学习的自适应MPC以解决卫星姿态控制问题 MPC model predictive control
27 Design and Characterization of a Unified Continuum Robot Actuation Platform 提出统一的连续机器人驱动平台以解决定制化限制问题 manipulation bi-manual bimanual manipulation
28 ACRO: Actor-Critic Rollout Orchestration 提出ACRO以优化视觉-语言-动作策略的执行成功率 manipulation vision-language-action VLA
29 Eye, Robot: Learning Expressive Gaze Dynamics via a VLM-Guided Transformer-VAE 提出VLM引导的Transformer-VAE以解决机器人注视动态生成问题 humanoid humanoid robot open-vocabulary
30 Refine Actions If Needed: Adaptive Action Chunk Refinement for Robot Manipulation 提出RAIN框架以优化机器人操作中的动作提案精炼 manipulation diffusion policy ✅
31 VIGOR-MPC: Vision-Guided Objective Regulation MPC 提出VIGOR-MPC以解决视觉感知下的控制问题 MPC
32 FPTAS for Polygonal Multi-Robot Motion Planning 提出FPTAS以解决多机器人运动规划问题 motion planning
33 MUCO: A Mani-Unit-Structured Manipulation Framework for Compositional Long-Horizon Robot Tasks 提出MUCO框架以解决长时间机器人操作任务的效率问题 manipulation
34 Efficient Test-Time Adaptation For Robot Policies 提出TEMPO方法以解决机器人政策在部署时的适应性问题 locomotion Unitree reinforcement learning
35 Physical Time as a Missing Dimension of Robot Policy Memory Dynamics 提出时间流政策以解决机器人记忆动态中的时间维度缺失问题 manipulation diffusion policy flow matching
36 Uncertainty-Driven Self-Play for Robust Multi-Agent Driving Policies 提出不确定性驱动自我对抗以解决多智能体驾驶策略的鲁棒性问题 motion planning zero-shot transfer
37 Active Generative Simulation: Meta-Learning What to Simulate for Sim-and-Real Policy Co-Training 提出主动生成仿真方法以优化机器人学习中的数据生成 manipulation VLA
38 DD-GBP: Anytime Multi-Arm Planning and Continuous Execution via Distributed Dynamic Gaussian Belief Propagation 提出DD-GBP以解决动态环境中的多臂任务规划问题 dual-arm
39 Enabling Tidying Tasks in Robotic Vacuum Cleaners via a Geometry-Induced Self-Locking Deployable Linkage 提出自锁式可展开连杆机制以提升扫地机器人清洁能力 manipulation
40 A VR Training System for Robot-Assisted Vascular Intervention with Dual-Mode Control and Model-Based Interaction Response 提出一种双模式控制的VR训练系统以提升机器人辅助血管介入的效果 manipulation
41 A Master-to-Simulation Interface with Demonstration-Trajectory Guidance for Vascular Intervention 提出一种主控与仿真接口以优化血管介入操作指导 manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
42 What Matters for World Modeling in Vision-Language-Action Models? 提出世界建模方法以提升视觉-语言-行动模型的性能 world model world models vision-language-action ✅
43 SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving 提出SafeDriveVLA以解决自动驾驶中的冲突感知问题 world model world models vision-language-action
44 Atomic-WAM: Execution-Grounded Atomic-Motion Reasoning for World Action Models 提出Atomic-WAM以解决任务指令模糊导致的动作选择问题 world action model world action models motion prediction ✅
45 Back on Track: Deployment-time Policy Improvement via World Model Planning 提出离线监控干预框架以提升部署时策略性能 diffusion policy world model world models
46 When Do Discrete Actions Make Good Continuous Controllers? 提出离散动作预测作为连续控制的有效替代方案 flow matching classifier-free guidance VLA ✅
47 Towards Agentic Robots: Model, Data, Environment, and Harness 提出统一框架以推动智能机器人领域的研究进展 world model world models vision-language-action
48 Investigating Behavior Cloning from Few Demonstrations for Autonomous Driving based on Bird's-Eye View in Simulated Cities 提出加权行为克隆方法以解决稀缺示范下的自动驾驶问题 policy learning behavior cloning
49 Instruction-Conditioned Motion Control for Robotic Arms: Language-to-Code Decomposition and Reinforcement Learning 提出指令条件下的运动控制方法以解决机器人臂控制问题 reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
50 Paraphrase Consensus Is Not Self-Consistency: Instruction Reliance and Robustness in VLA Policies 提出改进的VLA策略以解决指令依赖性和鲁棒性问题 vision-language-action VLA OpenVLA
51 Robota-Embed: Unified VLA Embeddings for Robot In-Context Learning and Evolution 提出Robota-Embed以解决机器人上下文学习与演化问题 vision-language-action VLA
52 Human Demonstrations as Post-Training Data for Any Robot Body: Retargeting the Object, Not the Hand 提出人类示范作为机器人后训练数据以解决目标重定向问题 vision-language-action
53 MorphAct: Robot Policies Morphing with the Worlds They Act In 提出MorphAct以解决机器人学习在多环境中的适应性问题 VLA

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
54 GS-PRM: Gaussian Visual Roadmap for Image-Goal Navigation 提出GS-PRM以解决图像目标导航中的全局规划问题 3DGS gaussian splatting splatting
55 HM3D-M3: A Benchmark for Multi-Agent, Multi-Modal, Multi-Object Goal Navigation 提出HM3D-M3基准以解决多智能体、多模态、多目标导航问题 open-vocabulary open vocabulary ✅
56 Dungeon and Visibility World Generator 提出Dungeon和可视性世界生成器以解决机器人探索问题 occupancy grid

🔬 支柱七：动作重定向 (Motion Retargeting) (2 篇)

#题目一句话要点标签🔗⭐
57 CoWear: Towards Collaborative Wearable Inertial Localization with Multiple Smart Devices 提出CoWear以解决多设备协作惯性定位问题 human motion
58 Spacecraft Pose Tracking via Kinematic Prediction and Selective Event Correction 提出基于运动预测与选择性事件修正的航天器姿态跟踪方法 motion prediction

⬅️ 返回 cs.RO 首页 · 🏠 返回主页