cs.RO（2025-05-13）

📊 共 31 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (20 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱六：视频提取与匹配 (Video Extraction) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱七：动作重定向 (Motion Retargeting) (1 🔗1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱一：机器人控制 (Robot Control) (20 篇)

#题目一句话要点标签🔗⭐
1 FOCI: Trajectory Optimization on Gaussian Splats FOCI：提出基于高斯球的轨迹优化算法，解决机器人狭窄空间运动规划问题 legged robot trajectory optimization ANYmal
2 Multi-step manipulation task and motion planning guided by video demonstration 提出视频引导的多步操作任务与运动规划方法，解决复杂机器人操作任务 manipulation motion planning task and motion planning
3 End-to-End Multi-Task Policy Learning from NMPC for Quadruped Locomotion 提出基于NMPC专家示教的多任务策略学习框架，用于四足机器人运动控制 quadruped locomotion model predictive control
4 LaDi-WM: A Latent Diffusion-based World Model for Predictive Manipulation 提出LaDi-WM，一种基于潜在扩散的世界模型，用于预测性操作任务。 manipulation diffusion policy world model
5 NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance NavDP：利用特权信息引导，学习从仿真到真实的导航扩散策略 sim-to-real diffusion policy privileged information ✅
6 From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation 提出FSD模型，通过空间关系推理提升机器人操作的泛化性和零样本性能。 manipulation spatial relationship vision-language-action
7 ChicGrasp: Imitation-Learning based Customized Dual-Jaw Gripper Control for Delicate, Irregular Bio-products Manipulation ChicGrasp：基于模仿学习的定制双爪夹持器控制，用于精细、不规则生物产品操作 manipulation teleoperation imitation learning
8 Zero-Shot Sim-to-Real Reinforcement Learning for Fruit Harvesting 提出基于dormant ratio最小化的零样本Sim-to-Real草莓采摘强化学习方案 sim-to-real domain randomization reinforcement learning
9 Augmented Reality for RObots (ARRO): Pointing Visuomotor Policies Towards Visual Robustness ARRO：利用增强现实提升机器人视觉运动策略的鲁棒性 manipulation diffusion policy open-vocabulary
10 Continuous World Coverage Path Planning for Fixed-Wing UAVs using Deep Reinforcement Learning 提出基于深度强化学习的固定翼无人机连续世界覆盖路径规划方法 motion planning reinforcement learning deep reinforcement learning
11 Adaptive Diffusion Policy Optimization for Robotic Manipulation 提出基于Adam的自适应扩散策略优化算法，提升机器人操作任务中的策略微调效率与稳定性。 manipulation reinforcement learning diffusion policy ✅
12 Automatic Curriculum Learning for Driving Scenarios: Towards Robust and Efficient Reinforcement Learning 提出基于自动课程学习的驾驶场景生成框架，提升强化学习自动驾驶的泛化性和效率。 domain randomization reinforcement learning curriculum learning
13 HandCept: A Visual-Inertial Fusion Framework for Accurate Proprioception in Dexterous Hands 提出HandCept框架以解决灵巧手的本体感知问题 manipulation dexterous hand sim-to-real
14 Real-time Capable Learning-based Visual Tool Pose Correction via Differentiable Simulation 提出基于可微仿真的视觉工具姿态校正方法，实现微创手术机器人实时姿态估计。 sim-to-real differentiable simulation
15 CLTP: Contrastive Language-Tactile Pre-training for 3D Contact Geometry Understanding 提出CLTP框架，用于接触几何理解的对比语言-触觉预训练 manipulation large language model multimodal
16 Motion Control of High-Dimensional Musculoskeletal Systems with Hierarchical Model-Based Planning 提出MPC^2算法，用于高维肌肉骨骼系统的零样本近实时运动控制 MPC model predictive control reinforcement learning
17 Rethink Repeatable Measures of Robot Performance with Statistical Query 提出一种轻量级自适应统计查询算法，提升机器人性能评估的可重复性。 humanoid humanoid robot locomotion
18 Extracting Visual Plans from Unlabeled Videos via Symbolic Guidance Vis2Plan：利用符号指导从无标签视频中提取视觉规划，提升机器人操作性能。 manipulation foundation model
19 MA-ROESL: Motion-aware Rapid Reward Optimization for Efficient Robot Skill Learning from Single Videos MA-ROESL：基于运动感知的快速奖励优化，高效地从单视频中学习机器人技能 locomotion reward design
20 Efficiently Manipulating Clutter via Learning and Search-Based Reasoning 提出基于学习与搜索的算法，高效操作杂乱环境中的物体 manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
21 Training Strategies for Efficient Embodied Reasoning 提出高效具身推理训练策略，加速推理并提升机器人策略泛化性 representation learning vision-language-action VLA
22 Scaling Multi Agent Reinforcement Learning for Underwater Acoustic Tracking via Autonomous Vehicles 提出基于蒸馏和Transformer的多智能体强化学习方法，用于水下声学跟踪。 reinforcement learning curriculum learning distillation
23 Parameter Estimation using Reinforcement Learning Causal Curiosity: Limits and Challenges 分析因果好奇强化学习在参数估计中的测量精度、局限与挑战 reinforcement learning
24 Reinforcement Learning-based Fault-Tolerant Control for Quadrotor with Online Transformer Adaptation 提出基于强化学习和Transformer自适应的四旋翼容错控制框架 reinforcement learning

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

#题目一句话要点标签🔗⭐
25 Parameter-Efficient Fine-Tuning of Vision Foundation Model for Forest Floor Segmentation from UAV Imagery 针对无人机林地图像，提出高效参数微调的视觉基础模型用于林地地表分割 foundation model
26 A Social Robot with Inner Speech for Dietary Guidance 提出一种基于内在语言的社交机器人，用于提供更透明和可信赖的膳食指导。 large language model

🔬 支柱六：视频提取与匹配 (Video Extraction) (2 篇)

#题目一句话要点标签🔗⭐
27 HMR-ODTA: Online Diverse Task Allocation for a Team of Heterogeneous Mobile Robots 提出HMR-ODTA算法，解决异构机器人团队在线多样化任务分配问题 HMR
28 A Tightly Coupled IMU-Based Motion Capture Approach for Estimating Multibody Kinematics and Kinetics 提出一种紧耦合的基于IMU的运动捕捉方法，用于估计多体运动学和动力学 IMU-based motion

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

#题目一句话要点标签🔗⭐
29 ORACLE-Grasp: Zero-Shot Task-Oriented Robotic Grasping using Large Multimodal Models ORACLE-Grasp：利用大型多模态模型实现零样本任务导向的机器人抓取 grasp prediction multimodal

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

#题目一句话要点标签🔗⭐
30 UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations UniSkill：通过跨具身技能表征模仿人类视频 cross-embodiment ✅

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
31 Beyond Predefined Actions: Integrating Behavior Trees and Dynamic Movement Primitives for Robot Learning from Demonstration 融合行为树与动态运动原语，实现机器人从演示中学习策略 motion generation

⬅️ 返回 cs.RO 首页 · 🏠 返回主页