cs.RO（2024-11-27）

📊 共 18 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (11 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (3 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (11 篇)

#题目一句话要点标签🔗⭐
1 DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation DexHandDiff：交互感知扩散规划，实现灵巧手自适应操作 manipulation dexterous manipulation large language model
2 G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation G3Flow：用于姿态感知和可泛化物体操作的生成式3D语义流 manipulation imitation learning diffusion policy
3 DextrAH-RGB: Visuomotor Policies to Grasp Anything with Dexterous Hands DextrAH-RGB：基于RGB图像的灵巧手抓取任意物体视觉运动策略 dexterous hand sim2real reinforcement learning
4 Prediction with Action: Visual Policy Learning via Joint Denoising Process PAD：通过联合去噪过程实现视觉策略学习，提升机器人操作性能。 manipulation policy learning imitation learning
5 Dynamic Non-Prehensile Object Transport via Model-Predictive Reinforcement Learning 提出基于模型预测强化学习的动态非抓取物体搬运方法 manipulation MPC reinforcement learning
6 Optimizing energy consumption for legged robot by adapting equilibrium position and stiffness of a parallel torsion spring 提出自适应扭转弹簧机制，优化腿式机器人能耗 legged robot locomotion
7 GAPartManip: A Large-scale Part-centric Dataset for Material-Agnostic Articulated Object Manipulation GAPartManip：大规模部件中心数据集，用于材质无关的可动对象操作 manipulation depth estimation ✅
8 Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policy 提出Safety-as-Policy，解决机器人操作中安全风险问题，实现负责任的机器人操作。 manipulation world model
9 Reference-Steering via Data-Driven Predictive Control for Hyper-Accurate Robotic Flying-Hopping Locomotion 提出基于数据驱动预测控制的参考轨迹修正方法，实现机器人飞行跳跃运动的超高精度控制。 locomotion
10 At First Contact: Stiffness Estimation Using Vibrational Information for Prosthetic Grasp Modulation 利用振动信息进行刚度估计，实现假肢抓握力度的精确调节 manipulation multimodal
11 OSU-Wing PIC Phase I Evaluation: Baseline Workload and Situation Awareness Results OSU-Wing合作研究表明增加无人机数量不一定会降低飞行员表现 manipulation

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

#题目一句话要点标签🔗⭐
12 HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction HI-SLAM2：基于几何感知的快速单目场景重建高斯SLAM 3D gaussian splatting 3DGS gaussian splatting ✅
13 Online Knowledge Integration for 3D Semantic Mapping: A Survey 综述：面向三维语义地图构建的在线知识集成方法 semantic mapping semantic map
14 ORB-SLAM3AB: Augmenting ORB-SLAM3 to Counteract Bumps with Optical Flow Inter-frame Matching ORB-SLAM3AB：结合光流增强ORB-SLAM3，提升崎岖路面下的鲁棒性 optical flow

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

#题目一句话要点标签🔗⭐
15 MLLM-Search: A Zero-Shot Approach to Finding People using Multimodal Large Language Models 提出MLLM-Search，利用多模态大语言模型零样本解决机器人寻人问题 large language model multimodal chain-of-thought
16 Embodied Red Teaming for Auditing Robotic Foundation Models 提出具身红队测试方法，用于评估机器人基础模型的安全性和有效性 foundation model language conditioned ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
17 ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics ELEMENTAL：结合演示学习与视觉-语言模型，交互式机器人奖励函数设计 reinforcement learning policy learning inverse reinforcement learning
18 Monocular Obstacle Avoidance Based on Inverse PPO for Fixed-wing UAVs 提出基于逆向PPO的单目视觉固定翼无人机避障方法，适用于未知环境下的高速飞行。 reinforcement learning deep reinforcement learning DRL ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页