cs.RO（2024-10-04）

📊 共 17 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (11 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (11 篇)

#题目一句话要点标签🔗⭐
1 Learning Humanoid Locomotion over Challenging Terrain 提出基于Transformer的强化学习方法，实现复杂地形下人形机器人稳健运动控制 humanoid humanoid robot humanoid locomotion
2 Residual Policy Learning for Perceptive Quadruped Control Using Differentiable Simulation 提出基于可微仿真的残差策略学习方法，提升四足机器人感知控制性能 quadruped locomotion reinforcement learning
3 Latent Action Priors for Locomotion with Deep Reinforcement Learning 提出基于隐空间动作先验的深度强化学习方法，提升机器人运动控制的自然性和鲁棒性 locomotion reinforcement learning deep reinforcement learning
4 STREAMS: An Assistive Multimodal AI Framework for Empowering Biosignal Based Robotic Controls STREAMS：一种辅助性多模态AI框架，用于增强基于生物信号的机器人控制 sim-to-real reinforcement learning deep reinforcement learning
5 Autoregressive Action Sequence Learning for Robotic Manipulation 提出基于分块因果Transformer的自回归策略网络ARP，用于解决机器人操作中的通用策略设计问题。 manipulation Aloha ✅
6 GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMs GenSim2：利用多模态推理LLM扩展机器人数据生成，实现零样本迁移。 sim-to-real language conditioned zero-shot transfer
7 Sampling-Based Model Predictive Control for Volumetric Ablation in Robotic Laser Surgery 提出基于采样的模型预测控制，用于机器人激光手术中的体积消融。 MPC model predictive control
8 Improving Efficiency of Sampling-based Motion Planning via Message-Passing Monte Carlo 通过消息传递蒙特卡洛方法提升采样基础运动规划效率 motion planning
9 Multi-Robot Motion Planning with Diffusion Models 提出MMD算法，利用单机器人数据和扩散模型解决大规模多机器人运动规划问题 motion planning ✅
10 GAP-RL: Grasps As Points for RL Towards Dynamic Object Grasping 提出GAP-RL框架，通过将抓取表示为点，实现动态环境中物体的强化学习抓取 manipulation sim-to-real reinforcement learning
11 Compact LED-Based Displacement Sensing for Robot Fingers 提出一种紧凑型LED位移传感器，用于感知机器人手指的接触力与力矩。 manipulation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
12 Multi-Objective Risk Assessment Framework for Exploration Planning Using Terrain and Traversability Analysis 提出多目标风险评估框架以解决探索规划中的不确定性问题 traversability
13 Collision-Aware Traversability Analysis for Autonomous Vehicles in the Context of Agricultural Robotics 提出一种基于多光谱信息的农业机器人碰撞感知地形分析方法 traversability

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

#题目一句话要点标签🔗⭐
14 LeLaN: Learning A Language-Conditioned Navigation Policy from In-the-Wild Videos LeLaN：从无标注视频学习语言条件下的机器人导航策略 egocentric foundation model language conditioned

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

#题目一句话要点标签🔗⭐
15 HMT-Grasp: A Hybrid Mamba-Transformer Approach for Robot Grasping in Cluttered Environments 提出HMT-Grasp，融合Mamba和Transformer，提升复杂环境下机器人抓取性能。 Mamba

🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)

#题目一句话要点标签🔗⭐
16 MO-DDN: A Coarse-to-Fine Attribute-based Exploration Agent for Multi-object Demand-driven Navigation 提出基于粗细粒度属性探索的C2FAgent，解决多目标需求驱动导航问题。 embodied AI

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
17 Learning Object Properties Using Robot Proprioception via Differentiable Robot-Object Interaction 利用可微机器人-物体交互，通过机器人自身感知学习物体属性 differentiable simulation

⬅️ 返回 cs.RO 首页 · 🏠 返回主页