cs.RO（2026-03-04）

📊 共 25 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (22 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱九：具身大模型 (Embodied Foundation Models) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (22 篇)

#题目一句话要点标签🔗⭐
1 Large-Language-Model-Guided State Estimation for Partially Observable Task and Motion Planning CoCo-TAMP：利用大语言模型指导部分可观测任务与运动规划 motion planning large language model task and motion planning
2 X-Loco: Towards Generalist Humanoid Locomotion Control via Synergetic Policy Distillation X-Loco：基于协同策略蒸馏的通用人形机器人运动控制 humanoid humanoid locomotion locomotion
3 SkillVLA: Tackling Combinatorial Diversity in Dual-Arm Manipulation via Skill Reuse SkillVLA：通过技能复用解决双臂操作中的组合多样性问题 manipulation bi-manual dual-arm
4 Structural Action Transformer for 3D Dexterous Manipulation 提出结构化动作Transformer，解决3D灵巧操作中跨机械臂的技能迁移问题。 manipulation dexterous manipulation imitation learning
5 Cognition to Control - Multi-Agent Learning for Human-Humanoid Collaborative Transport 提出认知到控制(C2C)框架，解决人-人形机器人协作搬运中的长期规划与稳定控制问题 humanoid whole-body control manipulation
6 ManipulationNet: An Infrastructure for Benchmarking Real-World Robot Manipulation with Physical Skill Challenges and Embodied Multimodal Reasoning ManipulationNet：用于真实世界机器人操作基准测试的基础设施，包含物理技能挑战和具身多模态推理。 manipulation dexterous manipulation multimodal
7 Tendon Force Modeling for Sim2Real Transfer of Reinforcement Learning Policies for Tendon-Driven Robots 提出基于Transformer的肌腱力建模方法，提升肌腱驱动机器人强化学习策略的Sim2Real迁移效果。 manipulation sim-to-real sim2real
8 Interaction-Aware Whole-Body Control for Compliant Object Transport 提出交互导向全身控制，解决人型机器人在复杂环境中协同搬运的难题。 humanoid whole-body control WBC
9 Swimming Under Constraints: A Safe Reinforcement Learning Framework for Quadrupedal Bio-Inspired Propulsion 提出ACPPO-PID算法，解决仿生四足水下推进中的安全强化学习问题 quadruped locomotion reinforcement learning
10 Self-adapting Robotic Agents through Online Continual Reinforcement Learning with World Model Feedback 提出基于世界模型反馈的在线持续强化学习方法，实现机器人自主适应 quadruped reinforcement learning world model
11 GarmentPile++: Affordance-Driven Cluttered Garments Retrieval with Vision-Language Reasoning 提出GarmentPile++，通过视觉-语言推理实现乱堆衣物中基于语义的精准抓取。 manipulation dual-arm affordance ✅
12 Sim2Sea: Sim-to-Real Policy Transfer for Maritime Vessel Navigation in Congested Waters Sim2Sea：提出一种水上交通拥堵场景下船舶自主导航的Sim2Real策略迁移框架 sim-to-real domain randomization spatiotemporal
13 RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots RoboCasa365：用于训练和评估通用机器人大规模模拟框架 manipulation mobile manipulation foundation model
14 HALyPO: Heterogeneous-Agent Lyapunov Policy Optimization for Human-Robot Collaboration HALyPO：异构智能体 Lyapunov 策略优化，提升人机协作的泛化性和鲁棒性 humanoid humanoid robot reinforcement learning
15 Compliant In-hand Rolling Manipulation Using Tactile Sensing 提出基于触觉反馈的柔顺灵巧手掌内滚动操作控制方法 manipulation
16 RoboLight: A Dataset with Linearly Composable Illumination for Robotic Manipulation RoboLight：用于机器人操作的线性可组合光照数据集 manipulation
17 Learning Surgical Robotic Manipulation with 3D Spatial Priors 提出Spatial Surgical Transformer，通过3D空间先验提升手术机器人操作能力 manipulation
18 Characterization and Correlation of Robotic Snake Scale Friction and Locomotion Speed 提出一种模块化蛇形机器人伪皮肤设计，研究摩擦特性与运动速度的相关性 locomotion
19 Learning Hip Exoskeleton Control Policy via Predictive Neuromusculoskeletal Simulation 提出基于预测性神经肌肉骨骼仿真的髋关节外骨骼控制策略学习方法 sim-to-real reinforcement learning distillation
20 Force-Aware Residual DAgger via Trajectory Editing for Precision Insertion with Impedance Control 提出TER-DAgger，通过轨迹编辑和力感知，提升阻抗控制下的精密插入任务成功率。 manipulation imitation learning behavior cloning
21 Perception-Aware Time-Optimal Planning for Quadrotor Waypoint Flight 提出感知驱动的时优轨迹规划框架，提升四旋翼飞行器在复杂环境下的自主飞行性能。 trajectory optimization
22 Whole-Body Safe Control of Robotic Systems with Koopman Neural Dynamics 提出基于Koopman神经网络动力学的机器人全身安全控制方法 quadruped

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

#题目一句话要点标签🔗⭐
23 IROSA: Interactive Robot Skill Adaptation using Natural Language IROSA：利用自然语言进行交互式机器人技能自适应，应用于工业场景。 imitation learning open-vocabulary open vocabulary
24 ArthroCut: Autonomous Policy Learning for Robotic Bone Resection in Knee Arthroplasty ArthroCut：用于膝关节置换术中机器人骨切除的自主策略学习框架 policy learning multimodal

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

#题目一句话要点标签🔗⭐
25 Lightweight Visual Reasoning for Socially-Aware Robots 提出轻量级语言-视觉反馈模块，增强社交机器人视觉推理能力 multimodal instruction following ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页