cs.RO（2024-09-16）

📊 共 31 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (23 🔗5) 支柱三：空间感知与语义 (Perception & Semantics) (4 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (23 篇)

#题目一句话要点标签🔗⭐
1 SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splatting SplatSim：利用高斯溅射实现RGB操作策略的零样本Sim2Real迁移 manipulation sim2real gaussian splatting
2 Real-Time Whole-Body Control of Legged Robots with Model-Predictive Path Integral Control 提出基于模型预测路径积分控制的腿式机器人全身实时控制方法 legged robot whole-body control locomotion
3 Safety-critical Locomotion of Biped Robots in Infeasible Paths: Overcoming Obstacles during Navigation toward Destination 提出一种安全关键的足式机器人运动控制框架，用于在复杂环境中导航和避障 legged robot bipedal biped
4 BEINGS: Bayesian Embodied Image-goal Navigation with Gaussian Splatting 提出BEINGS，利用高斯溅射和贝叶斯方法实现高效图像目标导航。 model predictive control 3D gaussian splatting gaussian splatting
5 Robots with Attitude: Singularity-Free Quaternion-Based Model-Predictive Control for Agile Legged Robots 提出基于四元数的模型预测控制，解决腿式机器人大角度旋转时的奇异性问题。 quadruped legged robot humanoid
6 Embedded Image-to-Image Translation for Efficient Sim-to-Real Transfer in Learning-based Robot-Assisted Soft Manipulation 提出基于嵌入式图像转换的Sim-to-Real方法，提升软体机器人辅助手术学习效率。 manipulation sim-to-real
7 Uncovering the Secrets of Human-Like Movement: A Fresh Perspective on Motion Planning 提出基于生物力学的最优控制框架，实现机器人臂类人运动规划 humanoid humanoid robot motion planning
8 Benchmarking Sim2Real Gap: High-fidelity Digital Twinning of Agile Manufacturing 针对敏捷制造，构建高保真数字孪生并评估Sim2Real差距 sim2real domain randomization curriculum learning
9 Catch It! Learning to Catch in Flight with Mobile Dexterous Hands 提出基于移动灵巧手的两阶段强化学习框架，解决空中物体抓取问题 whole-body control dexterous hand reinforcement learning ✅
10 Real-time Coupled Centroidal Motion and Footstep Planning for Biped Robots 提出一种快速的质心运动与足端规划算法，用于弹簧负载倒立摆式双足机器人。 bipedal biped
11 ASMA: An Adaptive Safety Margin Algorithm for Vision-Language Drone Navigation via Scene-Aware Control Barrier Functions 提出ASMA算法，通过场景感知控制屏障函数提升视觉语言无人机导航安全性。 MPC model predictive control VLN
12 Know your limits! Optimize the robot's behavior through self-awareness 提出基于自感知（SAW）的深度学习模型，优化人型机器人在复杂环境中的行为控制。 humanoid humanoid robot motion generation ✅
13 Learning Agile Swimming: An End-to-End Approach without CPGs 提出基于深度强化学习的端到端控制框架，实现仿生机器鱼的敏捷游泳。 sim-to-real reinforcement learning deep reinforcement learning
14 Safe Interval Motion Planning for Quadrotors in Dynamic Environments 提出基于安全区间的四旋翼动态环境运动规划方法 motion planning
15 A Non-Linear Model Predictive Task-Space Controller Satisfying Shape Constraints for Tendon-Driven Continuum Robots 提出基于模型预测控制的肌腱驱动连续体机器人任务空间控制器，满足形状约束。 MPC model predictive control teleoperation
16 Towards Real-Time Generation of Delay-Compensated Video Feeds for Outdoor Mobile Robot Teleoperation 提出一种基于学习的模块化视觉流水线，为户外移动机器人遥操作实时生成延迟补偿视频流。 teleoperation
17 E2Map: Experience-and-Emotion Map for Self-Reflective Robot Navigation with Language Models 提出E2Map，利用经验和情感指导语言模型在随机环境中进行自反思机器人导航。 manipulation large language model ✅
18 Digital Twins Meet the Koopman Operator: Data-Driven Learning for Robust Autonomy 提出基于数字孪生与Koopman算子的数据驱动方法，提升越野自主导航的鲁棒性。 sim2real motion planning
19 Safe and Real-Time Consistent Planning for Autonomous Vehicles in Partially Observed Environments via Parallel Consensus Optimization 提出CPTO方法，解决自动驾驶在部分观测环境下安全和一致性规划问题 trajectory optimization spatiotemporal
20 CtRNet-X: Camera-to-Robot Pose Estimation in Real-world Conditions Using a Single Camera CtRNet-X：提出单目相机下的相机-机器人位姿估计方法，解决部分遮挡问题 manipulation
21 Highly dynamic physical interaction for robotics: design and control of an active remote center of compliance 提出一种新型主动遥控柔顺中心(ARCC)设计与控制方法，提升机器人高动态物理交互性能。 manipulation
22 RPC: A Modular Framework for Robot Planning, Control, and Deployment RPC：用于机器人规划、控制和部署的模块化框架 legged robot ✅
23 ViewActive: Active viewpoint optimization from a single image ViewActive：基于单张图像的主动视角优化方法，提升机器人场景感知能力 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🔗⭐
24 HiFi-CS: Towards Open Vocabulary Visual Grounding For Robotic Grasping Using Vision-Language Models HiFi-CS：面向机器人抓取的开放词汇视觉定位方法 open-vocabulary open vocabulary visual grounding ✅
25 Point2Graph: An End-to-end Point Cloud-based 3D Open-Vocabulary Scene Graph for Robot Navigation 提出Point2Graph，仅用点云数据生成3D开放词汇场景图，用于机器人导航。 open-vocabulary open vocabulary
26 3D-TAFS: A Training-free Framework for 3D Affordance Segmentation 提出3D-TAFS免训练框架，用于3D可供性分割，提升人机交互。 affordance multimodal
27 Embodiment-Agnostic Action Planning via Object-Part Scene Flow 提出基于物体部件场景流的机器人动作规划方法，实现与具体机器人无关的策略。 scene flow

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

#题目一句话要点标签🔗⭐
28 LLM-as-BT-Planner: Leveraging LLMs for Behavior Tree Generation in Robot Task Planning LLM-as-BT-Planner：利用大型语言模型生成机器人任务规划的行为树 large language model
29 Securing the Future: Exploring Privacy Risks and Security Questions in Robotic Systems 探讨机器人系统中隐私风险与安全问题，展望未来发展趋势 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
30 Disentangling Uncertainty for Safe Social Navigation using Deep Reinforcement Learning 提出基于不确定性解耦的深度强化学习方法，用于安全社交导航。 reinforcement learning deep reinforcement learning DRL

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
31 LiLoc: Lifelong Localization using Adaptive Submap Joining and Egocentric Factor Graph LiLoc：基于自适应子地图拼接和自我中心因子图的终身定位框架 egocentric ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页