cs.RO（2024-09-17）

📊 共 20 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (14 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (14 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Efficient Computation of Whole-Body Control Utilizing Simplified Whole-Body Dynamics via Centroidal Dynamics	提出基于质心动力学的简化全身动力学方法，高效计算人形机器人全身控制	humanoid humanoid robot whole-body control
2	PLATO: Planning with LLMs and Affordances for Tool Manipulation	PLATO：利用LLM和可供性进行工具操作的机器人规划系统	manipulation affordance large language model
3	TacDiffusion: Force-domain Diffusion Policy for Precise Tactile Manipulation	TacDiffusion：力域扩散策略实现高精度触觉操作	manipulation diffusion policy zero-shot transfer
4	Agile Continuous Jumping in Discontinuous Terrains	提出一种分层学习控制框架，实现四足机器人在非连续地形上的敏捷连续跳跃。	quadruped parkour sim-to-real	✅
5	SDP: Spiking Diffusion Policy for Robotic Manipulation with Learnable Channel-Wise Membrane Thresholds	提出基于脉冲神经网络和可学习阈值的Spiking Diffusion Policy，用于提升机器人操作效率。	manipulation diffusion policy
6	RoadRunner M&M -- Learning Multi-range Multi-resolution Traversability Maps for Autonomous Off-road Navigation	RoadRunner M&M：学习多范围多分辨率地形图，用于自主越野导航	legged robot elevation map traversability	✅
7	MI-HGNN: Morphology-Informed Heterogeneous Graph Neural Network for Legged Robot Contact Perception	提出MI-HGNN，利用形态学信息异构图神经网络提升腿足机器人接触感知能力	quadruped legged robot	✅
8	CageCoOpt: Enhancing Manipulation Robustness through Caging-Guided Morphology and Policy Co-Optimization	CageCoOpt：通过笼式抓取引导的形态与策略协同优化，提升操作鲁棒性	manipulation reinforcement learning
9	Multi-Floor Zero-Shot Object Navigation Policy	提出多楼层导航策略MFNP，解决零样本物体导航在复杂多楼层环境中的挑战。	quadruped Unitree large language model
10	Three Degree-of-Freedom Soft Continuum Kinesthetic Haptic Display for Telemanipulation Via Sensory Substitution at the Finger	提出一种三自由度软体触觉反馈装置，用于远程操作中手指的触觉替代	manipulation
11	Robot Manipulation in Salient Vision through Referring Image Segmentation and Geometric Constraints	提出CLIPU$^2$Net，结合几何约束，实现基于显著视觉信息的机器人操作	manipulation
12	A variational approach to geometric mechanics for undulating robotic locomotion	基于变分几何力学的波动机器人运动建模与仿真	locomotion
13	MoDex: Planning High-Dimensional Dexterous Control via Learning Neural Internal Models	MoDex：通过学习神经内部模型规划高维灵巧控制	dexterous hand large language model
14	Use the Force, Bot! -- Force-Aware ProDMP with Event-Based Replanning	提出力感知的ProDMP，结合事件驱动的重规划，用于接触丰富的操作任务	manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
15	Leveraging Symmetry to Accelerate Learning of Trajectory Tracking Controllers for Free-Flying Robotic Systems	利用对称性加速自由漂浮机器人轨迹跟踪控制器学习	reinforcement learning PPO reward design
16	VertiCoder: Self-Supervised Kinodynamic Representation Learning on Vertically Challenging Terrain	VertiCoder：面向垂直地形的自监督运动学表示学习	behavior cloning representation learning
17	UniLCD: Unified Local-Cloud Decision-Making via Reinforcement Learning	UniLCD：通过强化学习实现统一的本地-云端决策，优化移动机器人能耗与延迟。	reinforcement learning

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

#	题目	一句话要点	标签	🔗	⭐
18	Pragmatic Embodied Spoken Instruction Following in Human-Robot Collaboration with Theory of Mind	提出SIFToM模型，利用心智理论提升机器人语音指令跟随的鲁棒性	instruction following
19	P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Task	提出P-RAG，用于具身日常任务中基于规划的渐进式检索增强生成	embodied AI large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
20	GLC-SLAM: Gaussian Splatting SLAM with Efficient Loop Closure	GLC-SLAM：基于高斯溅射的SLAM系统，通过高效回环闭合解决地图漂移问题	3D gaussian splatting 3DGS gaussian splatting

⬅️ 返回 cs.RO 首页 · 🏠 返回主页