cs.RO（2025-03-05）

📊 共 21 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (14 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (2)

🔬 支柱一：机器人控制 (Robot Control) (14 篇)

#题目一句话要点标签🔗⭐
1 LensDFF: Language-enhanced Sparse Feature Distillation for Efficient Few-Shot Dexterous Manipulation 提出LensDFF，通过语言增强的稀疏特征蒸馏实现高效的少样本灵巧操作 manipulation dexterous manipulation real2sim
2 SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning SafeVLA：通过约束学习实现视觉-语言-动作模型的安全对齐 manipulation mobile manipulation reinforcement learning
3 Olympus: A Jumping Quadruped for Planetary Exploration Utilizing Reinforcement Learning for In-Flight Attitude Control Olympus：基于强化学习姿态控制的行星跳跃四足机器人 quadruped legged robot locomotion
4 Physically-Feasible Reactive Synthesis for Terrain-Adaptive Locomotion via Trajectory Optimization and Symbolic Repair 提出基于轨迹优化和符号修复的四足机器人地形自适应运动规划框架 quadruped locomotion trajectory optimization
5 Social Gesture Recognition in spHRI: Leveraging Fabric-Based Tactile Sensing on Humanoid Robots 提出一种基于织物触觉传感的人形机器人社交手势识别系统，促进自然人机交互。 humanoid humanoid robot
6 AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons AirExo-2：低成本外骨骼助力可泛化机器人模仿学习 manipulation teleoperation policy learning
7 Continuous Control of Diverse Skills in Quadruped Robots Without Complete Expert Datasets 提出PASIST，无需完整专家数据集即可实现四足机器人多样技能的连续控制。 quadruped imitation learning
8 Generative Artificial Intelligence in Robotic Manipulation: A Survey 综述生成式AI在机器人操作中的应用，着重解决数据、规划和泛化挑战。 manipulation policy learning ✅
9 GO-VMP: Global Optimization for View Motion Planning in Fruit Mapping 提出GO-VMP算法，用于果园机器人全局优化视角运动规划，提升水果覆盖率 motion planning
10 Motion Planning and Control with Unknown Nonlinear Dynamics through Predicted Reachability 提出基于预测可达性的运动规划与控制框架，解决未知非线性动力学下的自主导航问题 motion planning
11 A Generative System for Robot-to-Human Handovers: from Intent Inference to Spatial Configuration Imagery 提出一种生成式机器人-人物体交接系统，模拟人类协同交互 motion planning multimodal
12 Endpoint-Explicit Differential Dynamic Programming via Exact Resolution 提出基于精确解的端点显式差分动态规划，解决约束DDP中的端点约束问题 MPC model predictive control
13 Adaptive Negative Damping Control for User-Dependent Multi-Terrain Walking Assistance with a Hip Exoskeleton 提出自适应负阻尼控制，用于髋关节外骨骼在多地形步态辅助中的用户个性化调整。 locomotion
14 Tiny LiDARs for Manipulator Self-Awareness: Sensor Characterization and Initial Localization Experiments 利用微型激光雷达实现机械臂自感知目标定位 manipulation

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

#题目一句话要点标签🔗⭐
15 CREStE: Scalable Mapless Navigation with Internet Scale Priors and Counterfactual Guidance CREStE：利用互联网规模先验知识和反事实指导实现可扩展的无地图导航 reinforcement learning inverse reinforcement learning distillation
16 Causality-Based Reinforcement Learning Method for Multi-Stage Robotic Tasks 提出基于因果关系的强化学习方法，解决多阶段机器人任务中的探索难题。 reinforcement learning deep reinforcement learning
17 Embodied Escaping: End-to-End Reinforcement Learning for Robot Navigation in Narrow Environment 提出一种基于强化学习的端到端机器人脱困模型，用于解决狭窄环境下的自主导航问题。 reinforcement learning

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

#题目一句话要点标签🔗⭐
18 OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction 提出OTTER以解决视觉语言行动模型的特征提取问题 vision-language-action VLA ✅
19 Safe LLM-Controlled Robots with Formal Guarantees via Reachability Analysis 提出基于可达性分析的安全LLM控制机器人框架，保障自主导航任务安全 large language model

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

#题目一句话要点标签🔗⭐
20 Direct Sparse Odometry with Continuous 3D Gaussian Maps for Indoor Environments 提出连续3D高斯地图以解决室内环境下的稀疏视觉里程计问题 visual odometry
21 OpenGV 2.0: Motion prior-assisted calibration and SLAM with vehicle-mounted surround-view systems OpenGV 2.0：提出基于运动先验的车辆环视系统标定与SLAM方案 visual SLAM

⬅️ 返回 cs.RO 首页 · 🏠 返回主页