cs.RO（2026-10-30）

📊 共 38 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (29 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (29 篇)

#题目一句话要点标签🔗⭐
1 Movens-Zero: Scaling Humanoid Motion Foundation Models with Large-Scale Human Videos 提出Movens-Zero以解决人形运动模型扩展问题 humanoid flow matching motion generation
2 $\nabla$Mimic: Ultra-Efficient Humanoid Control with Differentiable Simulation 提出$ abla$Mimic以解决高效类人控制问题 humanoid humanoid control whole-body control
3 Cross-Embodiment Motion Planning by Coupling Body-Agnostic World Model with Differentiable Ego-Dynamics 提出Hourglass架构以解决跨体态运动规划问题 locomotion motion planning imitation learning
4 Online Learning of Heterogeneous Locomotion Dynamics under Reinforcement Learning Policies for Precise Loco-Manipulation 提出在线学习方法以解决异构运动动态下的精确运动操控问题 locomotion locomotion policy manipulation
5 DiffWBC: Unlocking Steerable General Humanoid Motion Tracking via One-Step Diffusion Whole-Body Control 提出DiffWBC以解决通用人形运动跟踪问题 humanoid whole-body control motion tracking
6 HIPC: Humanoid Iterative Planning and Control via Goal-Conditioned Motion Closure 提出HIPC框架以解决人形机器人运动控制中的反馈问题 humanoid motion tracking motion planning
7 Direct Action-Manifold Modeling for Efficient and Robust Bimanual Manipulation 提出直接动作流形建模以解决双手操作的效率与鲁棒性问题 manipulation bi-manual bimanual manipulation
8 HandMimicX: Learning Human-Like Dexterous Manipulation via an Object-Centric Policy from Egocentric Videos 提出对象中心框架以解决人类视频学习灵巧操作问题 manipulation dexterous manipulation reinforcement learning
9 Nexus-VLA: Bridging Human and Robot Experiences via a Shared Hierarchical Semantic Latent Space 提出Nexus-VLA以解决人类与机器人经验共享问题 manipulation policy learning egocentric
10 ROOF: Learning Humanoid Fall Recovery under Overhead Constraints 提出ROOF以解决人形机器人在障碍物下的跌倒恢复问题 humanoid fall recovery Unitree ✅
11 Hierarchical World Models with Implicit Dynamics 提出隐式动态世界模型以解决长时间任务中的控制问题 manipulation MPC policy learning
12 REA: A Routed Embodied Agent Runtime for Asynchronous Brain-Cerebellum Control 提出REA以解决异步脑小脑控制的协调问题 humanoid whole-body control Unitree
13 Geometry-Aware Humanoid Retargeting via Manifold ODEs 提出基于流形常微分方程的类人运动重定向方法 humanoid motion retargeting spatial relationship
14 Learning from Physical Experience:Context-Space Adaptation for Robotic Manipulation 提出LEXP以解决机器人操作中的上下文适应问题 manipulation foundation model multimodal
15 Joint-Health-Aware Reinforcement Learning for Robust Robot Control Under Actuator Degradation 提出联合健康感知强化学习以解决执行器退化问题 locomotion manipulation domain randomization
16 RTPolicy: Real-Time (32.9 Hz) Multi-View Visuomotor Policy for Robotic Manipulation on Edge Devices 提出RTPolicy以解决机器人操控中的低延迟问题 manipulation bi-manual flow matching ✅
17 When the Past Shapes Action: Understanding Embodied Memory 提出一种新方法以解决动态环境中智能体的记忆挑战 manipulation embodied AI foundation model
18 Interaction-Aware Sampling-Based Motion Planning for Autonomous Surface Vessels in Urban Waterways 提出基于交互感知的运动规划方法以解决城市水道自主航行问题 model predictive control motion planning
19 GPU-accelerated Incremental Euclidean Distance Transform for Online Motion Planning of Mobile Robots 提出GPU加速增量欧几里得距离变换以解决移动机器人在线运动规划问题 motion planning occupancy grid
20 AC-SMPC: Differentiable Actor--Critic MPC with State Constraints for Safe and Fast Robot Navigation 提出AC-SMPC框架以解决安全快速的机器人导航问题 MPC model predictive control
21 MolmoSpaces-CommonSense: Evaluating Commonsense in Robotic Manipulation Policies 提出MolmoSpaces-CommonSense以解决机器人操作中的常识推理问题 manipulation affordance ✅
22 Suspended-Fabric Robotic Manipulation Surfaces: Modelling, Design Space, and Multimodular Extensio 提出悬挂织物机器人操作表面以解决多模块操控问题 manipulation
23 Flexibility-Aware Robotic Manipulation: Deformation Estimation, Kinematics, and Control via Distributed Inertial Measurement 提出灵活性感知机器人操作框架以解决变形估计与控制问题 manipulation
24 Contact-based optimization for collision-free motion planning for a million robots 提出基于接触的优化方法以解决百万机器人无碰撞运动规划问题 motion planning
25 TinyAstral: Transferring Self-Evolving Harnesses to Tiny Generalist Manipulation Agents 提出TinyAstral以提升小型通用操作代理的自我演化能力 manipulation
26 RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory 提出RoboArchitect以自动化设计具有持久记忆的机器人代理 manipulation
27 SketchMate: Agentic Geometric Reasoning for Zero-Shot Precision Insertion 提出SketchMate以解决零-shot精确插入问题 manipulation
28 SAFARI: Semantic- And Frontier-driven Autonomous Risk Inspection 提出SAFARI框架以解决风险感知的自主探索问题 quadruped
29 BioAgent: Self-Directed Skill Acquisition and Capability Growth for Long-Horizon Laboratory Protocols 提出BioAgent以解决实验室协议中的能力不足与有效性问题 dual-arm

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

#题目一句话要点标签🔗⭐
30 VLA Policies Do Not Know When Not to Act: Unintended Task Execution and Start Suppression 提出VLA政策以解决机器人无指令行动问题 vision-language-action VLA
31 Language-Conditioned Behavioral Cloning for Autonomous Endoscope Guidance 提出语言条件行为克隆以解决自主内窥镜引导问题 language conditioned
32 CalibSwitch: Observation-Driven Camera-LiDAR Extrinsic Recovery and Selective Maintenance for Multimodal Perception 提出CalibSwitch以解决多模态感知中的相机-激光雷达外参恢复问题 multimodal
33 Capability-Conditioned Graph Control Barrier Functions for Zero-Shot Safe Navigation of Heterogeneous Mobile Robot Teams 提出能力条件图控制障碍函数以解决异构移动机器人团队的安全导航问题 zero-shot transfer

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
34 When the Simulator Fails, Not the Policy: Auditing Contact Artifacts in Simulated Robot Benchmarks 提出SimuGuard以解决机器人模拟基准中的接触伪影问题 world action model world action models penetration
35 TRACE: Target-State Risk-Aligned Conditional Execution for Embodied Tracking 提出TRACE以解决机器人视觉跟踪中的安全性问题 PPO vision-language-action VLA
36 ResMerge: Residual Policy Learning and Merging for Continual Adaptation of Pre-trained Robot Policies 提出ResMerge以解决机器人预训练策略的持续适应问题 reinforcement learning policy learning ✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
37 Visual-Inertial RGB-D SLAM with Encoders for a Differential Wheeled Robot 提出视觉惯性RGB-D SLAM系统以解决特征点不足问题 VIO
38 OpenVIO: A Versatile Open-Source Visual-Inertial Odometry System 提出OpenVIO以解决视觉惯性里程计系统的多样性问题 VIO ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页