cs.RO（2025-12-03）

📊 共 23 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (13 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱三：空间感知与语义 (Perception & Semantics) (4 🔗2)

🔬 支柱一：机器人控制 (Robot Control) (13 篇)

#	题目	一句话要点	标签	🔗	⭐
1	What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models	综述：机器人3D场景表示方法，从几何到Foundation Model的演进与展望	manipulation 3D gaussian splatting 3DGS
2	Safety Reinforced Model Predictive Control (SRMPC): Improving MPC with Reinforcement Learning for Motion Planning in Autonomous Driving	提出安全强化学习增强的模型预测控制(SRMPC)，用于自动驾驶运动规划。	MPC model predictive control motion planning
3	AdaPower: Specializing World Foundation Models for Predictive Manipulation	AdaPower：通过自适应世界模型提升预测性操作的性能	manipulation model predictive control world model
4	ResponsibleRobotBench: Benchmarking Responsible Robot Manipulation using Multi-modal Large Language Models	提出ResponsibleRobotBench，用于评估多模态大模型在负责任机器人操作中的性能。	manipulation embodied AI large language model
5	GrOMP: Grasped Object Manifold Projection for Multimodal Imitation Learning of Manipulation	提出GrOMP以解决模仿学习中的复合误差问题	manipulation imitation learning multimodal
6	Hierarchical Vision Language Action Model Using Success and Failure Demonstrations	提出VINE模型，利用成功与失败演示提升视觉-语言-动作模型的鲁棒性	manipulation teleoperation reinforcement learning
7	Prediction-Driven Motion Planning: Route Integration Strategies in Attention-Based Prediction Models	提出基于注意力机制的预测模型，融合导航信息以提升自动驾驶车辆交互	motion planning motion prediction	✅
8	Multimodal Control of Manipulators: Coupling Kinematics and Vision for Self-Driving Laboratory Operations	针对冗余机械臂，提出基于雅可比矩阵的多模态运动规划方案，用于自动化实验室操作。	motion planning multimodal
9	ContactRL: Safe Reinforcement Learning based Motion Planning for Contact based Human Robot Collaboration	ContactRL：基于强化学习的安全运动规划，用于人机协作中的接触任务	motion planning reinforcement learning
10	Cross-embodied Co-design for Dexterous Hands	提出灵巧手协同设计框架，实现任务导向的形态与控制策略优化	manipulation dexterous hand dexterous manipulation	✅
11	Crossing the Sim2Real Gap Between Simulation and Ground Testing to Space Deployment of Autonomous Free-flyer Control	首次在国际空间站验证基于强化学习的自由飞行器自主控制	sim2real reinforcement learning curriculum learning
12	Bayesian Optimization for Automatic Tuning of Torque-Level Nonlinear Model Predictive Control	提出基于贝叶斯优化的力矩级非线性模型预测控制自动调参框架	MPC model predictive control
13	PerFACT: Motion Policy with LLM-Powered Dataset Synthesis and Fusion Action-Chunking Transformers	PerFACT：利用LLM驱动的数据集合成和融合动作分块Transformer提升机器人运动策略	motion planning large language model

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

#	题目	一句话要点	标签	🔗	⭐
14	World Models for Autonomous Navigation of Terrestrial Robots from LIDAR Observations	提出基于DreamerV3和MLP-VAE的世界模型，提升激光雷达数据驱动的机器人自主导航性能。	reinforcement learning SAC TD3
15	Digital Twin-based Control Co-Design of Full Vehicle Active Suspensions via Deep Reinforcement Learning	提出基于数字孪生和深度强化学习的全车主动悬架控制协同设计框架	reinforcement learning deep reinforcement learning DRL
16	Driving Beyond Privilege: Distilling Dense-Reward Knowledge into Sparse-Reward Policies	提出奖励特权世界模型蒸馏，解决自动驾驶中稠密奖励与稀疏目标不匹配问题	reinforcement learning world model dreamer
17	RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RL	RoboScape-R：提出基于世界模型的通用奖励机制，提升机器人强化学习的泛化性	reinforcement learning policy learning imitation learning
18	Autonomous Planning In-space Assembly Reinforcement-learning free-flYer (APIARY) International Space Station Astrobee Testing	APIARY实验首次在国际空间站利用强化学习控制Astrobee机器人	reinforcement learning PPO
19	Autonomous Reinforcement Learning Robot Control with Intel's Loihi 2 Neuromorphic Hardware	提出基于Loihi 2神经形态硬件的自主强化学习机器人控制方案	reinforcement learning

🔬 支柱三：空间感知与语义 (Perception & Semantics) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
20	MDE-AgriVLN: Agricultural Vision-and-Language Navigation with Monocular Depth Estimation	提出MDE-AgriVLN，利用单目深度估计提升农业机器人视觉语言导航性能	depth estimation monocular depth VLN	✅
21	OmniDexVLG: Learning Dexterous Grasp Generation from Vision Language Model-Guided Grasp Semantics, Taxonomy and Functional Affordance	OmniDexVLG：提出基于视觉语言模型引导的灵巧抓取生成框架，实现语义可控的抓取合成。	affordance multimodal chain-of-thought
22	CRAFT-E: A Neuro-Symbolic Framework for Embodied Affordance Grounding	提出CRAFT-E框架以解决助理机器人物体功能理解问题	affordance
23	Surfel-LIO: Fast LiDAR-Inertial Odometry with Pre-computed Surfels and Hierarchical Z-order Voxel Hashing	提出Surfel-LIO以解决LiDAR惯性测程中的效率问题	LIO	✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页