cs.RO（2024-09-30）

📊 共 30 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (23) 支柱三：空间感知与语义 (Perception & Semantics) (3) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱五：交互与反应 (Interaction & Reaction) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (23 篇)

#题目一句话要点标签🔗⭐
1 RL-GSBridge: 3D Gaussian Splatting Based Real2Sim2Real Method for Robotic Manipulation Learning 提出RL-GSBridge，利用3D高斯溅射实现机器人操作学习的零样本Sim2Real迁移 manipulation sim-to-real sim2real
2 Opt2Skill: Imitating Dynamically-feasible Whole-Body Trajectories for Versatile Humanoid Loco-Manipulation Opt2Skill：结合轨迹优化与强化学习，实现通用人形机器人灵巧操作 humanoid humanoid robot manipulation
3 Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models DoggyBot：基于腿式机器人和视觉-语言模型实现开放世界物体抓取的系统 quadruped legged robot locomotion
4 WildFusion: Multimodal Implicit 3D Reconstructions in the Wild WildFusion：野外环境下的多模态隐式3D重建，提升机器人导航能力 legged robot scene reconstruction traversability
5 Continuously Improving Mobile Manipulation with Autonomous Real-World RL 提出基于自主真实世界强化学习的移动操作持续改进框架，提升机器人操作能力。 manipulation mobile manipulation policy learning
6 GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation GravMAD：基于空间价值图引导动作扩散的通用3D操作方法 manipulation imitation learning foundation model
7 Playful DoggyBot: Learning Agile and Precise Quadrupedal Locomotion DoggyBot：基于强化学习的敏捷精确四足机器人运动控制 quadruped locomotion reinforcement learning
8 Learning with Less: Optimizing Tactile Sensor Configurations for Dexterous Manipulation 优化触觉传感器配置，以更少传感器实现灵巧操作 manipulation dexterous manipulation
9 Towards Effective Utilization of Mixed-Quality Demonstrations in Robotic Manipulation via Segment-Level Selection and Optimization 提出S2I框架，通过分段选择与优化，有效利用机器人操作中混合质量的演示数据。 manipulation trajectory optimization policy learning
10 Constraining Gaussian Process Implicit Surfaces for Robot Manipulation via Dataset Refinement 提出COGIS方法，通过数据集优化约束高斯过程隐式曲面，提升机器人操作在部分可观测环境下的性能。 manipulation MPC model predictive control
11 Learning to Swim: Reinforcement Learning for 6-DOF Control of Thruster-driven Autonomous Underwater Vehicles 提出基于强化学习的AUV六自由度控制方法，实现零样本迁移 sim-to-real domain randomization reinforcement learning
12 UniAff: A Unified Representation of Affordances for Tool Usage and Articulation with Vision-Language Models UniAff：利用视觉-语言模型统一工具使用和关节运动的 affordance 表示 manipulation affordance
13 A Parallel-in-Time Newton's Method for Nonlinear Model Predictive Control 提出一种时间并行牛顿法，加速非线性模型预测控制的求解。 MPC model predictive control
14 Additively Manufactured Open-Source Quadruped Robots for Multi-Robot SLAM Applications 设计开源增材制造四足机器人Squeaky，用于多机器人SLAM研究 quadruped reinforcement learning
15 Object-Centric Kinodynamic Planning for Nonprehensile Robot Rearrangement Manipulation 提出一种面向非抓取重排列操作的、以物体为中心的运动规划方法 manipulation
16 Micromanipulation System for Microscale Magnetic Component Alignment and Assembly 提出一种基于接触的微操作系统，用于微型磁性元件的精确对准和组装。 manipulation
17 Bi-directional Momentum-based Haptic Feedback and Control System for In-Hand Dexterous Telemanipulation 提出基于双向动量触觉反馈与控制系统，用于灵巧手遥操作 manipulation
18 PC-Planner: Physics-Constrained Self-Supervised Learning for Robust Neural Motion Planning with Shape-Aware Distance Function 提出PC-Planner以解决复杂环境下机器人运动规划问题 motion planning
19 Self-Assessment of Evidential Grid Map Fusion for Robust Motion Planning 提出一种基于证据网格地图融合的自评估方法，用于提升机器人运动规划的鲁棒性 motion planning
20 Bi-stable thin soft robot for in-plane locomotion in narrow space 提出一种新型双稳态薄型软体机器人，用于狭窄空间内的平面运动 locomotion
21 Robot Navigation Using Physically Grounded Vision-Language Models in Outdoor Environments VLM-GroNav：融合物理属性的视觉语言模型用于户外机器人导航 legged robot traversability
22 Design, manufacturing, and inverse dynamic modeling of soft parallel robots actuated by dielectric elastomer actuators 设计并制造基于介电弹性体驱动的软体并联机器人，并建立其逆动力学模型 manipulation
23 A vision-based robotic system for precision pollination of apples 提出基于视觉的机器人授粉系统，实现苹果的精准授粉 motion planning

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
24 Robi Butler: Multimodal Remote Interaction with a Household Robot Assistant Robi Butler：基于多模态交互的家庭服务机器人远程助手 open-vocabulary open vocabulary first-person view
25 Robust Gaussian Splatting SLAM by Leveraging Loop Closure 提出基于高斯溅射和闭环检测的SLAM系统，解决旋转RGB-D相机下的漂移问题。 3D gaussian splatting gaussian splatting splatting
26 Distributed NeRF Learning for Collaborative Multi-Robot Perception 提出分布式NeRF学习框架，用于多机器人协同感知，解决带宽限制下的环境重建问题。 NeRF neural radiance field geometric consistency

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
27 Resolving Positional Ambiguity in Dialogues by Vision-Language Models for Robot Navigation 提出基于视觉-语言模型的对话式机器人导航方法，解决位置歧义问题 large language model foundation model
28 Self-Assessment and Correction of Sensor Synchronization 提出一种基于旋转运动的传感器自同步方法，用于估计和校正时间偏移。 TAMP
29 Benchmarking Adaptive Intelligence and Computer Vision on Human-Robot Collaboration 提出自适应智能与自标记方法，提升人机协作中机器人意图识别的鲁棒性。 TAMP

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
30 Active Listener: Continuous Generation of Listener's Head Motion Response in Dyadic Interactions 提出基于图的跨模态模型，用于生成对话中听者实时的头部运动响应 dyadic interaction ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页