cs.RO（2024-10-10）

📊 共 25 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (20 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱一：机器人控制 (Robot Control) (20 篇)

#题目一句话要点标签🔗⭐
1 RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation 提出RDT-1B：用于双臂操作的扩散模型，解决多模态动作分布和数据稀缺问题。 manipulation bi-manual bimanual manipulation ✅
2 Online DNN-driven Nonlinear MPC for Stylistic Humanoid Robot Walking with Step Adjustment 提出基于DNN驱动的非线性MPC方法，实现具有步态调整的拟人机器人风格化行走 humanoid humanoid robot locomotion
3 Constrained Skill Discovery: Quadruped Locomotion with Unsupervised Reinforcement Learning 提出基于距离约束的无监督强化学习方法，实现四足机器人零样本步态控制 quadruped locomotion ANYmal
4 Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation RoboDual：协同通用与专用策略，提升机器人操作性能与效率 manipulation cross-embodiment vision-language-action
5 Guiding Collision-Free Humanoid Multi-Contact Locomotion using Convex Kinematic Relaxations and Dynamic Optimization 提出基于凸松弛和动态优化的方法，引导人形机器人实现无碰撞多接触运动 humanoid humanoid robot locomotion
6 LucidGrasp: Robotic Framework for Autonomous Manipulation of Laboratory Equipment with Different Degrees of Transparency via 6D Pose Estimation LucidGrasp：基于6D位姿估计的透明实验室设备自主操作机器人框架 manipulation teleoperation 6D pose estimation
7 The Power of Input: Benchmarking Zero-Shot Sim-To-Real Transfer of Reinforcement Learning Control Policies for Quadrotor Control 四旋翼无人机强化学习控制策略零样本迁移：输入空间配置基准分析 sim-to-real reinforcement learning deep reinforcement learning
8 ForceMimic: Force-Centric Imitation Learning with Force-Motion Capture System for Contact-Rich Manipulation ForceMimic：提出力觉引导的模仿学习框架，用于接触丰富的操作任务。 manipulation teleoperation imitation learning
9 From CAD to URDF: Co-Design of a Jet-Powered Humanoid Robot Including CAD Geometry 提出一种CAD协同设计的喷气动力人形机器人优化框架，提升控制性能与机械设计。 humanoid humanoid robot
10 FusionSense: Bridging Common Sense, Vision, and Touch for Robust Sparse-View Reconstruction FusionSense：融合常识、视觉和触觉，实现稳健的稀疏视角三维重建 manipulation 3D gaussian splatting gaussian splatting
11 On the Evaluation of Generative Robotic Simulations 提出生成式机器人仿真评估框架，解决自主生成任务的评估难题。 sim-to-real world model large language model
12 Streamlined shape of cyborg cockroach promotes traversability in confined environments by gap negotiation 仿生蟑螂流线型设计提升狭窄环境下的通过性 locomotion traversability
13 Imitation Learning with Limited Actions via Diffusion Planners and Deep Koopman Controllers 提出基于扩散规划器和Deep Koopman控制器的模仿学习方法，提升有限动作数据下的学习效率。 manipulation imitation learning
14 Safe and Dynamically-Feasible Motion Planning using Control Lyapunov and Barrier Functions 提出C-CLF-CBF-RRT算法，为控制仿射系统生成安全且动态可行的运动规划路径。 motion planning
15 Modular Adaptive Aerial Manipulation under Unknown Dynamic Coupling Forces 提出一种模块化自适应控制方法，解决未知动态耦合力下的空中操作难题。 manipulation
16 Dynamic Object Catching with Quadruped Robot Front Legs 提出一种基于四足机器人前腿的动态物体抓取框架，解决运动物体拦截问题。 quadruped
17 Stop-N-Go: Search-based Conflict Resolution for Motion Planning of Multiple Robotic Manipulators 提出基于搜索的冲突消解方法Stop-N-Go，解决多机器人协作运动规划问题 motion planning
18 PokeFlex: A Real-World Dataset of Volumetric Deformable Objects for Robotics PokeFlex：用于机器人操作的真实世界体积可变形物体数据集 manipulation multimodal
19 DTactive: A Vision-Based Tactile Sensor with Active Surface DTactive：一种具有主动表面的视觉触觉传感器，用于灵巧手内操作。 manipulation in-hand manipulation
20 CE-MRS: Contrastive Explanations for Multi-Robot Systems 提出CE-MRS：一种多机器人系统的对比解释方法，提升用户问题解决能力。 motion planning

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

#题目一句话要点标签🔗⭐
21 Multimodal Perception System for Real Open Environment 提出一种用于真实开放环境的多模态感知系统，提升户外行走可靠性。 multimodal
22 G$^{2}$TR: Generalized Grounded Temporal Reasoning for Robot Instruction Following by Combining Large Pre-trained Models G²TR：结合预训练模型，实现机器人指令跟随中的广义时序推理 instruction following ✅

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

#题目一句话要点标签🔗⭐
23 Neural Semantic Map-Learning for Autonomous Vehicles 提出基于神经语义地图学习的自动驾驶车辆地图构建方法 scene reconstruction semantic map
24 LiPO: LiDAR Inertial Odometry for ICP Comparison LiPO：用于ICP方法比较的激光雷达惯性里程计框架 LIO

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

#题目一句话要点标签🔗⭐
25 Mastering Contact-rich Tasks by Combining Soft and Rigid Robotics with Imitation Learning 结合软硬机器人与模仿学习，实现高泛化性的接触密集型任务 imitation learning

⬅️ 返回 cs.RO 首页 · 🏠 返回主页