cs.RO（2025-12-03）

📊 共 23 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (15 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱三：空间感知 (Perception & SLAM) (3 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (15 篇)

#题目一句话要点标签🔗⭐
1 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)，提升自动驾驶运动规划的安全性与性能。 MPC model predictive control motion planning
2 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
3 Cross-embodied Co-design for Dexterous Hands 提出一种跨具身协同设计框架，用于灵巧手形态与控制策略的联合优化 manipulation dexterous hand dexterous manipulation
4 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
5 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机器人自主控制 sim2real reinforcement learning curriculum learning
6 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。 grasping grasp
7 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
8 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能力 motion planning navigation ✅
9 ResponsibleRobotBench: Benchmarking Responsible Robot Manipulation using Multi-modal Large Language Models 提出ResponsibleRobotBench，利用多模态大语言模型评估负责任的机器人操作。 manipulation
10 MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving MPCFormer：基于物理信息与数据驱动的可解释社会感知自动驾驶方法 MPC reinforcement learning social interaction
11 A Novel Approach to Tomato Harvesting Using a Hybrid Gripper with Semantic Segmentation and Keypoint Detection 提出一种基于混合夹爪的番茄采摘系统，结合语义分割与关键点检测实现精准采摘。 grasping grasp localization
12 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
13 CRAFT-E: A Neuro-Symbolic Framework for Embodied Affordance Grounding CRAFT-E：用于具身可供性接地的神经符号框架 grasp
14 Artificial Microsaccade Compensation: Stable Vision for an Ornithopter 提出人工微眼跳补偿方法，稳定扑翼飞行器剧烈抖动下的视频 running
15 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运动规划方案，用于自动化实验室操作。 motion planning

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
16 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
17 RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RL RoboScape-R：通过统一奖励-观测世界模型提升机器人强化学习的泛化能力 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：基于强化学习的国际空间站Astrobee机器人自主装配 reinforcement learning PPO actor-critic
19 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泛化性差的问题 reinforcement learning world model latent dynamics
20 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 (Perception & SLAM) (3 篇)

#题目一句话要点标签🔗⭐
21 MDE-AgriVLN: Agricultural Vision-and-Language Navigation with Monocular Depth Estimation MDE-AgriVLN：提出单目深度估计的农业视觉语言导航方法 depth estimation monocular depth navigation ✅
22 MSG-Loc: Multi-Label Likelihood-based Semantic Graph Matching for Object-Level Global Localization 提出基于多标签似然语义图匹配的物体级全局定位方法 pose estimation localization
23 Training-Free Robot Pose Estimation using Off-the-Shelf Foundational Models 利用现成视觉-语言模型实现免训练机器人姿态估计 pose estimation

⬅️ 返回 cs.RO 首页 · 🏠 返回主页