cs.RO（2026-10-26）

📊 共 35 篇论文 | 🔗 8 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (25 🔗6) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱一：机器人控制 (Robot Control) (25 篇)

#题目一句话要点标签🔗⭐
1 Zero-HLM: Generalizable Humanoid Loco-Manipulation without Real Robot Data 提出Zero-HLM框架以解决人形机器人无实物数据的运动操控问题 humanoid manipulation loco-manipulation ✅
2 Differentiable Contact Dynamics for Legged Locomotion: Policy Learning and Contact-Implicit Trajectory Optimization 提出可微接触动力学以优化四足机器人运动控制 legged locomotion locomotion trajectory optimization
3 Learning Force-Reactive Humanoid Loco-Manipulation 提出FLORE框架以解决人形机器人力反应行走操控问题 humanoid whole-body control manipulation ✅
4 Enhancing Deep Reinforcement Learning for Robotic Motion Planning via Task Decomposition 提出任务分解框架以提升机器人运动规划的深度强化学习效率 manipulation motion planning reinforcement learning
5 DEX-PHD: A Dexterous Portable Handheld Device for Multimodal Data Collection 提出DEX-PHD以解决多模态数据收集的便携性与准确性问题 humanoid humanoid robot manipulation
6 Profiling a Frontier Agent with EBench: From Direct Control to Harness with Policy 提出EBench评估框架以优化多模态大语言模型的机器人控制能力 manipulation world action model world action models ✅
7 JevVLA: Jev-Inspired Energy-Based Adaptation for Vision-Language-Action Policies 提出JevVLA以解决视觉-语言-动作策略适应问题 manipulation embodied AI vision-language-action ✅
8 Reward-Guided RRT* for Budgeted Task and Motion Planning 提出奖励引导的RRT*以解决预算限制的任务与运动规划问题 motion planning task and motion planning
9 Dream to Assist: Intent-Conditioned World Models for Shared Vehicle Control 提出Dream2Assist以解决共享车辆控制中的意图对齐问题 sim-to-real shared control reinforcement learning
10 The Language of Deformation: Semantic Failure Analysis as a Prerequisite for Dexterous Manipulation of Deformable Objects 提出语义失效分析以解决可变形物体灵巧操控问题 manipulation dexterous manipulation
11 3D-Force Estimation for Dual-arm Manipulation of Deformable Linear Objects via Factor Graphs 提出基于因子图的3D力估计方法以解决可变形线性物体操控问题 manipulation dual-arm
12 Continuous-Time Safe Planning and Control for Agile Quadrupeds 提出连续时间安全规划与控制方法以解决灵活四足机器人导航问题 quadruped locomotion motion planning
13 VisGeo-PipeTrack: A Visual Geometric Servo Control Framework with MPC-RCAPID Control for UAV-Based Dynamic Pipes Tracking 提出VisGeo-PipeTrack以解决动态管道跟踪问题 MPC model predictive control
14 Labference: Benchmarking the Reasoning-Action Connection in Robotic Laboratories 提出Labference以解决机器人实验室中推理与行动连接问题 manipulation embodied AI VLA
15 Quantile-Based Command-Reserve MPC for Current-Command Gimbal Pointing 提出基于分位数的命令保留MPC以解决当前指向控制问题 MPC model predictive control
16 Networked Humanoid Intelligence: Communication, Coordination, Collaboration, and Social Interaction 提出网络化类人智能以解决机器人协作与人机交互问题 humanoid humanoid robot
17 RobotAgentBench: Towards Open-world Robot Autonomy 提出RobotAgentBench以解决开放世界机器人自主性评估问题 manipulation vision-language-action VLA
18 RoKON: Efficient and Adaptive Data-Enabled Predictive Control for Robotic Manipulation 提出RoKON以解决机器人操作中的实时控制问题 manipulation
19 ISB-NMPC: Interception-Oriented Spherical-Bearing Nonlinear Model Predictive Control for Quadrotors 提出ISB-NMPC以解决四旋翼无人机拦截目标的可视性与机动性冲突问题 model predictive control ✅
20 Pretraining Knows What, Simulation Teaches How: Compositional Generalization in a Sim-Trained Robot Agent 提出ZAP以解决机器人任务理解与执行问题 manipulation VLA
21 EmbodiedLab: Benchmarking Embodied Agents That Act to Know 提出EmbodiedLab基准以解决机器人自主探索问题 manipulation motion planning ✅
22 TrySee: Modular Perception-Enhanced VLM Grounding for Closed-Loop Robot Task Planning in Specialized Domains 提出TrySee以解决专用领域机器人任务规划问题 motion planning
23 Distributed Predictive Flocking for a Swarm of Miniature Vibration-Driven Robots in a Confined Arena 提出分布式预测集群控制以解决微型机器人协调问题 model predictive control
24 Learning Direct Control from Optimization for Dynamic Target Tracking 提出LECO框架以解决动态目标跟踪中的控制优化问题 trajectory optimization
25 MMGNet: Multi-Modal 6-DoF Grasp Synthesis for Cluttered Scenes 提出MMGNet以解决杂乱场景中的6自由度抓取合成问题 manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
26 Robot-Aligned 3D Gaussian Splatting for Precise Reaching with Wrist-Camera VLA Policies 提出基于3D高斯点云的机器人对齐方法以解决精确抓取问题 policy learning 3D gaussian splatting 3DGS ✅
27 Context-Aware Generation and Modulation of Expressive Motion Behavior using Multimodal Foundation Models 提出多模态模型以生成和调节机器人表达性动作行为 distillation foundation model multimodal ✅
28 VLA-HWBench: Where the Time Goes When VLA Models Run on Edge Hardware 提出VLA-HWBench以优化边缘设备上的VLA模型推理延迟 flow matching VLA
29 SceneAgent: An Agentic Pipeline from 3D and 4D Captures to Simulation Environments 提出SceneAgent以解决3D/4D场景转化为模拟环境的问题 policy learning 3D gaussian splatting 3DGS
30 VISTA: Active Exploration for Self-Improvement in Embodied Agents 提出VISTA框架以解决自我改进的主动探索问题 policy learning foundation model
31 Behavioural Quality Is Not Learning Utility: Objective Mismatch in Human Behaviour Models for Robot Learning 提出人类行为模型评估新方法以优化机器人学习效果 reinforcement learning policy learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
32 From Language to Drives: A Multimodal Framework for Aligning Autonomous Robots with Human Purposes 提出多模态框架以对齐自主机器人与人类目的 large language model multimodal
33 FISRF: Flexible Instructional Scaffolding Reflection Framework for Robotics Task Planning with Large Language Model 提出灵活指导反思框架以改善机器人任务规划中的错误修正 large language model
34 Preemptive Instruction Following with Resumption 提出PIFR基准以解决长时间导航中的任务中断与恢复问题 instruction following

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
35 Benchmarking Obstacle-Conditioned Safety in Household Robot Navigation 提出OSMA-Bench以解决家庭机器人导航中的安全性问题 motion adaptation vision-language-action VLA

⬅️ 返回 cs.RO 首页 · 🏠 返回主页