cs.RO（2026-03-06）

📊 共 30 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (24 🔗5) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱七：动作重定向 (Motion Retargeting) (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 Moving Through Clutter: Scaling Data Collection and Benchmarking for 3D Scene-Aware Humanoid Locomotion via Virtual Reality 提出MTC框架，通过VR数据收集与评测，实现3D杂乱场景下的人形机器人运动。 humanoid humanoid robot humanoid locomotion
2 History-Conditioned Spatio-Temporal Visual Token Pruning for Efficient Vision-Language Navigation 提出一种免训练的时空视觉Token剪枝框架，用于高效的视觉-语言导航。 quadruped Unitree vision-language-action
3 SuperSuit: An Isomorphic Bimodal Interface for Scalable Mobile Manipulation SuperSuit：一种用于可扩展移动操作的同构双模态接口 locomotion manipulation mobile manipulation
4 Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration 提出IGAR，通过无训练注意力重校准解决VLA模型中的语言盲区问题 manipulation vision-language-action VLA
5 Terrain characterization and locomotion adaptation in a small-scale lizard-inspired robot 提出一种小尺度蜥蜴机器人，通过地形感知与运动模式自适应，提升复杂地形下的运动能力。 locomotion motion adaptation
6 CDF-Glove: A Cable-Driven Force Feedback Glove for Dexterous Teleoperation 提出低成本、轻量化的力反馈手套CDF-Glove，提升灵巧遥操作的模仿学习效果 manipulation dexterous manipulation bi-manual ✅
7 Unified Learning of Temporal Task Structure and Action Timing for Bimanual Robot Manipulation 提出一种统一学习框架，用于双臂机器人操作中时序任务结构和动作时序 manipulation bi-manual bimanual manipulation
8 AnyCamVLA: Zero-Shot Camera Adaptation for Viewpoint Robust Vision-Language-Action Models AnyCamVLA：零样本相机自适应，提升VLA模型在视角变化下的鲁棒性 manipulation vision-language-action VLA
9 Task-Level Decisions to Gait Level Control: A Hierarchical Policy Approach for Quadruped Navigation 提出TDGC：一种四足机器人分层策略导航方法，解决地形适应性问题 quadruped locomotion gait control
10 Underactuated multimodal jumping robot for extraterrestrial exploration 提出一种欠驱动多模态跳跃机器人，用于地外探索 locomotion multimodal
11 DexEMG: Towards Dexterous Teleoperation System via EMG2Pose Generalization 提出DexEMG以解决灵巧机器人远程操作的性能与便携性问题 manipulation dexterous hand teleoperation
12 TADPO: Reinforcement Learning Goes Off-road TADPO：强化学习用于非结构化道路自动驾驶，实现零样本迁移 sim-to-real reinforcement learning PPO
13 DreamToNav: Generalizable Navigation for Robots via Generative Video Planning DreamToNav：基于生成视频规划的通用机器人导航框架 quadruped locomotion foundation model
14 Dual-Agent Multiple-Model Reinforcement Learning for Event-Triggered Human-Robot Co-Adaptation in Decoupled Task Spaces 提出双智能体多模型强化学习，用于解耦任务空间中事件触发的人机协同自适应 shared control reinforcement learning
15 Swooper: Learning High-Speed Aerial Grasping With a Simple Gripper Swooper：提出一种基于深度强化学习的无人机高速抓取方法，使用简单夹爪实现高成功率。 manipulation reinforcement learning deep reinforcement learning ✅
16 Safe Consensus of Cooperative Manipulation with Hierarchical Event-Triggered Control Barrier Functions 提出基于分层事件触发控制障碍函数的多机器人协同操作安全共识方法 manipulation
17 Few-Shot Neural Differentiable Simulator: Real-to-Sim Rigid-Contact Modeling 提出少量样本神经可微模拟器以解决真实到模拟的刚性接触建模问题 manipulation policy learning differentiable simulation
18 How to Model Your Crazyflie Brushless 针对Crazyflie Brushless无人机，提出精确动力学模型并验证其在强化学习控制中的有效性 sim-to-real domain randomization reinforcement learning
19 OpenHEART: Opening Heterogeneous Articulated Objects with a Legged Manipulator 提出OpenHEART框架，用于腿式机器人与异构铰接物体的稳健交互 legged robot manipulation reinforcement learning ✅
20 Iterative Convex Optimization with Control Barrier Functions for Obstacle Avoidance among Polytopes 提出基于迭代凸优化的控制屏障函数方法，解决多面体障碍物避障问题 MPC model predictive control
21 Control Barrier Corridors: From Safety Functions to Safe Sets 提出控制屏障走廊，统一控制屏障函数与安全运动走廊，实现安全自主导航。 motion planning
22 KISS-IMU: Self-supervised Inertial Odometry with Motion-balanced Learning and Uncertainty-aware Inference KISS-IMU：基于运动平衡学习和不确定性感知推理的自监督惯性里程计 quadruped ✅
23 Sticky-Glance: Robust Intent Recognition for Human Robot Collaboration via Single-Glance Sticky-Glance：基于单次注视的人机协作鲁棒意图识别 shared control
24 Multi-Robot Trajectory Planning via Constrained Bayesian Optimization and Local Cost Map Learning with STL-Based Conflict Resolution 提出基于约束贝叶斯优化和局部代价地图学习的多机器人轨迹规划方法，解决STL约束下的运动规划问题。 motion planning ✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
25 HarvestFlex: Strawberry Harvesting via Vision-Language-Action Policy Adaptation in the Wild 提出HarvestFlex以解决温室草莓采摘中的视觉-语言-动作策略迁移问题 vision-language-action VLA
26 Lifelong Embodied Navigation Learning 提出Uni-Walker框架，解决具身导航中的终身学习和灾难性遗忘问题 large language model chain-of-thought

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

#题目一句话要点标签🔗⭐
27 Data Analogies Enable Efficient Cross-Embodiment Transfer 数据类比提升跨具身迁移效率，解决异构机器人数据利用难题 cross-embodiment embodiment transfer

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

#题目一句话要点标签🔗⭐
28 Multimodal Behavior Tree Generation: A Small Vision-Language Model for Robot Task Planning 提出多模态行为树生成方法，用小型视觉-语言模型进行机器人任务规划。 scene understanding multimodal

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

#题目一句话要点标签🔗⭐
29 Expert Knowledge-driven Reinforcement Learning for Autonomous Racing via Trajectory Guidance and Dynamics Constraints 提出TraD-RL，通过专家知识引导和动态约束强化学习解决自动驾驶赛车中的不稳定性和安全性问题 reinforcement learning policy learning curriculum learning

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

#题目一句话要点标签🔗⭐
30 Improved hopping control on slopes for small robots using spring mass modeling 针对小型跳跃机器人，提出基于弹簧质量模型的斜坡稳定控制方法 PULSE

⬅️ 返回 cs.RO 首页 · 🏠 返回主页