cs.RO（2024-09-24）

📊 共 35 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 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗2) 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 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (23 篇)

#题目一句话要点标签🔗⭐
1 Autotuning Bipedal Locomotion MPC with GRFM-Net for Efficient Sim-to-Real Transfer 提出基于GRFM-Net的DiffTune方法，实现双足机器人运动MPC的自动调参与高效Sim-to-Real迁移。 humanoid humanoid robot bipedal
2 A Learning Framework for Diverse Legged Robot Locomotion Using Barrier-Based Style Rewards 提出基于Barrier的风格奖励学习框架，实现多样化足式机器人运动控制 quadruped legged robot bipedal
3 Walking with Terrain Reconstruction: Learning to Traverse Risky Sparse Footholds 提出基于局部地形重建的强化学习方法，解决四足机器人稀疏地形上的稳健行走问题 quadruped legged robot locomotion
4 MHRC: Closed-loop Decentralized Multi-Heterogeneous Robot Collaboration with Large Language Models 提出MHRC框架，利用LLM实现多异构机器人分散式协作，完成探索、运输和组织任务。 manipulation mobile manipulation large language model
5 Dynamic Cloth Manipulation Considering Variable Stiffness and Material Change Using Deep Predictive Model with Parametric Bias 提出结合变刚度控制与参数偏置的深度预测模型，用于动态布料操作和材料变化适应。 humanoid manipulation predictive model
6 KinScene: Model-Based Mobile Manipulation of Articulated Scenes KinScene：构建场景级可动模型，实现移动机器人长时程操作 manipulation mobile manipulation ✅
7 Autonomous Wheel Loader Navigation Using Goal-Conditioned Actor-Critic MPC 提出基于目标条件Actor-Critic MPC的自主轮式装载机导航方法 MPC model predictive control trajectory optimization
8 BehAV: Behavioral Rule Guided Autonomy Using VLMs for Robot Navigation in Outdoor Scenes BehAV：利用VLM和行为规则引导户外场景机器人自主导航 quadruped MPC model predictive control
9 Generative Factor Chaining: Coordinated Manipulation with Diffusion-based Factor Graph 提出基于扩散模型的生成式因子链，解决多机械臂协同操作规划难题。 manipulation bi-manual bimanual manipulation
10 MBC: Multi-Brain Collaborative Control for Quadruped Robots 提出多脑协同控制(MBC)系统，提升四足机器人在复杂环境下的鲁棒性。 quadruped locomotion reinforcement learning
11 Whole-body End-Effector Pose Tracking 提出全身RL框架以解决腿式机器人末端执行器姿态跟踪问题 quadruped legged robot manipulation
12 Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation Gen2Act：通过生成新场景下的人类视频，实现机器人操作的泛化 manipulation language conditioned ✅
13 PRESTO: Fast Motion Planning Using Diffusion Models Based on Key-Configuration Environment Representation PRESTO：基于关键配置环境表示的扩散模型快速运动规划 trajectory optimization motion planning ✅
14 TiltXter: CNN-based Electro-tactile Rendering of Tilt Angle for Telemanipulation of Pasteur Pipettes TiltXter：基于CNN的电触觉倾斜角度渲染，用于巴斯德吸管的遥操作 manipulation teleoperation
15 Intent Prediction-Driven Model Predictive Control for UAV Planning and Navigation in Dynamic Environments 提出基于意图预测的MPC无人机规划导航方法，提升动态环境安全性 MPC model predictive control
16 ARCH: Hierarchical Hybrid Learning for Long-Horizon Contact-Rich Robotic Assembly 提出ARCH：用于长时程接触式机器人装配的分层混合学习方法 manipulation teleoperation reinforcement learning
17 AnyCar to Anywhere: Learning Universal Dynamics Model for Agile and Adaptive Mobility AnyCar：学习通用动力学模型，实现轮式机器人敏捷自适应移动 locomotion MPC foundation model
18 SurgIRL: Towards Life-Long Learning for Surgical Automation by Incremental Reinforcement Learning SurgIRL：基于增量强化学习的手术自动化终身学习框架 sim-to-real reinforcement learning
19 Embedded IPC: Fast and Intersection-free Simulation in Reduced Subspace for Robot Manipulation 提出嵌入式IPC方法，用于机器人操作中快速且无干涉的降维子空间仿真 manipulation
20 Articulated Object Manipulation using Online Axis Estimation with SAM2-Based Tracking 提出基于SAM2在线轴估计的铰接物体操作方法，提升交互精度。 manipulation ✅
21 Development of Bidirectional Series Elastic Actuator with Torsion Coil Spring and Implementation to the Legged Robot 开发基于扭力螺旋弹簧的双向串联弹性驱动器，并应用于腿式机器人 legged robot
22 RTAGrasp: Learning Task-Oriented Grasping from Human Videos via Retrieval, Transfer, and Alignment RTAGrasp：通过检索、迁移和对齐从人类视频中学习任务导向抓取 manipulation foundation model
23 MultiTalk: Introspective and Extrospective Dialogue for Human-Environment-LLM Alignment MultiTalk：通过自省和外省对话实现人-环境-LLM对齐的任务规划 manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
24 Learning Multiple Probabilistic Decisions from Latent World Model in Autonomous Driving LatentDriver：提出基于隐变量世界模型的概率决策方法，提升自动驾驶性能 reinforcement learning imitation learning world model ✅
25 Online Planning for Multi-UAV Pursuit-Evasion in Unknown Environments Using Deep Reinforcement Learning 提出基于深度强化学习的多无人机追逃在线规划方法，适用于未知环境。 reinforcement learning deep reinforcement learning
26 Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach 提出基于阶段式奖励塑造的约束多目标强化学习方法，用于解决杂技机器人控制问题。 reinforcement learning reward shaping ✅
27 Safe Navigation for Robotic Digestive Endoscopy via Human Intervention-based Reinforcement Learning 提出基于人类干预的强化学习方法HI-PPO，用于安全机器人消化内窥镜导航 reinforcement learning PPO behavior cloning
28 NavRL: Learning Safe Flight in Dynamic Environments NavRL：基于深度强化学习的安全无人机动态环境导航框架 reinforcement learning deep reinforcement learning PPO
29 Context-Based Meta Reinforcement Learning for Robust and Adaptable Peg-in-Hole Assembly Tasks 提出基于上下文的元强化学习方法，提升机械臂在孔装配任务中的鲁棒性和适应性 reinforcement learning

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

#题目一句话要点标签🔗⭐
30 AIR-Embodied: An Efficient Active 3DGS-based Interaction and Reconstruction Framework with Embodied Large Language Model AIR-Embodied：融合具身大语言模型的高效主动3DGS交互与重建框架 3DGS embodied AI large language model
31 Fast Extrinsic Calibration for Multiple Inertial Measurement Units in Visual-Inertial System 提出一种快速外参标定方法，用于融合多惯性测量单元以提升视觉惯性系统的定位精度。 VIO
32 Autonomous Hiking Trail Navigation via Semantic Segmentation and Geometric Analysis 提出一种融合语义分割与几何分析的自主徒步导航方法，提升复杂环境适应性。 traversability

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

#题目一句话要点标签🔗⭐
33 BeSimulator: A Large Language Model Powered Text-based Behavior Simulator 提出BeSimulator，一种基于大语言模型的文本行为模拟器，用于机器人行为逻辑的初步评估。 large language model ✅
34 Long-horizon Embodied Planning with Implicit Logical Inference and Hallucination Mitigation 提出ReLEP框架，通过隐式逻辑推理和幻觉抑制实现长时程具身规划 embodied AI foundation model
35 SYNERGAI: Perception Alignment for Human-Robot Collaboration SYNERGAI：通过感知对齐实现人机协作 large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页