cs.RO（2025-03-07）

📊 共 26 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (19 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (4 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱一：机器人控制 (Robot Control) (19 篇)

#题目一句话要点标签🔗⭐
1 Kinodynamic Model Predictive Control for Energy Efficient Locomotion of Legged Robots with Parallel Elasticity 提出基于动理学的模型预测控制，利用并联弹性元件提升腿式机器人能量效率 legged robot locomotion MPC
2 BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities BEHAVIOR Robot Suite：为日常家庭活动简化真实世界全身操作 whole-body control manipulation mobile manipulation
3 Kaiwu: A Multimodal Manipulation Dataset and Framework for Robot Learning and Human-Robot Interaction Kaiwu：用于机器人学习和人机交互的多模态操作数据集与框架 manipulation dexterous manipulation imitation learning
4 Learning High-Fidelity Robot Self-Model with Articulated 3D Gaussian Splatting 提出基于关节3D高斯溅射的机器人高保真自建模方法，解决现有方法建模质量和数据成本问题。 motion planning 3D gaussian splatting gaussian splatting
5 Look Before You Leap: Using Serialized State Machine for Language Conditioned Robotic Manipulation 提出基于序列化状态机的语言条件机器人操作框架，提升长序列任务成功率 manipulation imitation learning language conditioned
6 dARt Vinci: Egocentric Data Collection for Surgical Robot Learning at Scale dARt Vinci：用于大规模外科机器人学习的以自我为中心的数据采集平台 teleoperation reinforcement learning imitation learning
7 Reward-Centered ReST-MCTS: A Robust Decision-Making Framework for Robotic Manipulation in High Uncertainty Environments 提出Reward-Centered ReST-MCTS以解决高不确定性环境下决策问题 manipulation reward shaping chain-of-thought
8 MatchMaker: Automated Asset Generation for Robotic Assembly MatchMaker：用于机器人装配的自动化资产生成，提升多任务学习能力 manipulation sim-to-real policy learning ✅
9 Unity RL Playground: A Versatile Reinforcement Learning Framework for Mobile Robots Unity RL Playground：用于移动机器人多任务运动学习的通用强化学习框架 locomotion reinforcement learning ✅
10 Accelerating db-A* for Kinodynamic Motion Planning Using Diffusion 提出基于扩散模型的db-A*加速方法，提升Kinodynamic运动规划效率与质量。 motion planning
11 Topology-Driven Trajectory Optimization for Modelling Controllable Interactions Within Multi-Vehicle Scenario 提出基于拓扑驱动的轨迹优化方法，实现多车辆场景下可控交互轨迹生成。 trajectory optimization
12 Persistent Object Gaussian Splat (POGS) for Tracking Human and Robot Manipulation of Irregularly Shaped Objects 提出POGS，用于跟踪人机协作中不规则物体的操作与姿态估计 manipulation
13 Joint 3D Point Cloud Segmentation using Real-Sim Loop: From Panels to Trees and Branches 提出基于Real-Sim Loop的联合3D点云分割方法，用于果园场景的面板、树木和树枝分割。 sim2real real2sim
14 Generalizing Robot Trajectories from Single-Context Human Demonstrations: A Probabilistic Approach 提出基于GMM的轨迹泛化方法，从单上下文演示中学习机器人轨迹 dual-arm
15 Design, Dynamic Modeling and Control of a 2-DOF Robotic Wrist Actuated by Twisted and Coiled Actuators 提出基于扭曲缠绕驱动器的2自由度机器人腕部设计与动态模型控制方法 model predictive control
16 Enhancing Thin-Film Wafer Inspection With A Multi-Sensor Array And Robot Constraint Maintenance 提出基于多传感器阵列和机器人约束维护的薄膜晶圆检测增强方案 manipulation
17 CoinRobot: Generalized End-to-end Robotic Learning for Physical Intelligence CoinRobot：面向物理智能的通用端到端机器人学习框架 manipulation
18 A Helping (Human) Hand in Kinematic Structure Estimation 利用人手先验知识进行运动学结构估计，提升机器人操作安全性 manipulation
19 Safety-Critical Traffic Simulation with Adversarial Transfer of Driving Intentions 提出IntSim，通过对抗性迁移驾驶意图实现安全关键交通场景仿真。 motion planning

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

#题目一句话要点标签🔗⭐
20 LiDAR-enhanced 3D Gaussian Splatting Mapping LiGSM：激光雷达增强的3D高斯溅射建图，提升精度与鲁棒性 3D gaussian splatting 3DGS gaussian splatting
21 GSplatVNM: Point-of-View Synthesis for Visual Navigation Models Using Gaussian Splatting GSplatVNM：利用高斯溅射为视觉导航模型合成视点 3D gaussian splatting 3DGS gaussian splatting
22 THE-SEAN: A Heart Rate Variation-Inspired Temporally High-Order Event-Based Visual Odometry with Self-Supervised Spiking Event Accumulation Networks 提出THE-SEAN，一种基于心率变异启发的事件相机视觉里程计，提升触发效率和精度。 visual odometry
23 Adaptive-LIO: Enhancing Robustness and Precision through Environmental Adaptation in LiDAR Inertial Odometry Adaptive-LIO：面向复杂环境的自适应激光雷达惯性里程计，提升鲁棒性和精度 LIO ✅

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

#题目一句话要点标签🔗⭐
24 Discrete Contrastive Learning for Diffusion Policies in Autonomous Driving 提出基于离散对比学习的扩散策略，用于自动驾驶中模拟多样化人类驾驶行为。 diffusion policy contrastive learning
25 InDRiVE: Intrinsic Disagreement based Reinforcement for Vehicle Exploration through Curiosity Driven Generalized World Model InDRiVE：基于内在差异奖励的车辆探索，通过好奇心驱动的广义世界模型 reinforcement learning world model dreamer
26 Multi-Robot Collaboration through Reinforcement Learning and Abstract Simulation 利用抽象仿真与强化学习实现多机器人协作策略训练与迁移 reinforcement learning

⬅️ 返回 cs.RO 首页 · 🏠 返回主页