cs.RO（2025-05-27）

📊 共 22 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (14) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱一：机器人控制 (Robot Control) (14 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Gait-Conditioned Reinforcement Learning with Multi-Phase Curriculum for Humanoid Locomotion	提出步态条件强化学习框架，实现人型机器人站立、行走、跑步及平滑过渡。	humanoid humanoid robot humanoid control
2	Learning a Unified Policy for Position and Force Control in Legged Loco-Manipulation	提出一种用于腿足机器人定位与力控的统一策略，无需力传感器。	quadruped legged robot humanoid
3	PartInstruct: Part-level Instruction Following for Fine-grained Robot Manipulation	PartInstruct：提出用于细粒度机器人操作的部件级指令跟随基准	manipulation policy learning instruction following
4	Spatial RoboGrasp: Generalized Robotic Grasping Control Policy	Spatial RoboGrasp：基于空间感知的通用机器人抓取控制策略	manipulation imitation learning depth estimation
5	Convergent Functions, Divergent Forms	LOKI：一种高效的形态与控制策略协同设计框架，可泛化至未知任务。	quadruped bipedal biped
6	EquAct: An SE(3)-Equivariant Multi-Task Transformer for Open-Loop Robotic Manipulation	提出EquAct，一种SE(3)等变Transformer，用于开放式机器人操作任务。	manipulation geometric consistency language conditioned
7	CLAMP: Crowdsourcing a LArge-scale in-the-wild haptic dataset with an open-source device for Multimodal robot Perception	CLAMP：众包大规模真实场景触觉数据集，用于多模态机器人感知	manipulation multimodal
8	Interactive OT Gym: A Reinforcement Learning-Based Interactive Optical tweezer (OT)-Driven Microrobotics Simulation Platform	提出Interactive OT Gym平台，用于强化学习辅助的光镊微操作机器人交互仿真。	manipulation shared control reinforcement learning
9	Collision Probability Estimation for Optimization-based Vehicular Motion Planning	提出基于多圆近似的碰撞概率估计方法，用于优化型车辆运动规划。	model predictive control motion planning
10	Learning Generalizable Robot Policy with Human Demonstration Video as a Prompt	提出一种基于人类演示视频提示的通用机器人策略学习框架，无需额外数据和模型微调。	manipulation dexterous manipulation teleoperation
11	Fast and Cost-effective Speculative Edge-Cloud Decoding with Early Exits	提出基于早退机制的快速低成本边缘-云推测解码框架，加速LLM在边缘设备的应用	quadruped Unitree large language model
12	COM Adjustment Mechanism Control for Multi-Configuration Motion Stability of Unmanned Deformable Vehicle	针对无人变形车辆多构型运动稳定性，提出基于质心调整机制的控制方法	legged robot humanoid
13	ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-Making	ManiTaskGen：用于具身决策智能体评估与提升的综合任务生成器	manipulation mobile manipulation
14	MIND-Stack: Modular, Interpretable, End-to-End Differentiability for Autonomous Navigation	MIND-Stack：用于自主导航的模块化、可解释、端到端可微框架	sim-to-real

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
15	Hume: Introducing System-2 Thinking in Visual-Language-Action Model	Hume：在视觉-语言-动作模型中引入系统2思维，提升机器人灵巧控制能力	vision-language-action VLA large language model
16	FM-Planner: Foundation Model Guided Path Planning for Autonomous Drone Navigation	FM-Planner：基于大模型的无人机自主导航路径规划方法	large language model foundation model	✅
17	GET: Goal-directed Exploration and Targeting for Large-Scale Unknown Environments	GET：面向大规模未知环境的目标导向探索与定位	large language model
18	BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation	提出基于3D体素置信地图的BeliefMapNav，用于零样本物体导航。	large language model
19	Automating eHMI Action Design with LLMs for Automated Vehicle Communication	提出基于LLM的eHMI动作自动设计流程，提升自动驾驶车辆通信的适应性。	large language model

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

#	题目	一句话要点	标签	🔗	⭐
20	EgoWalk: A Multimodal Dataset for Robot Navigation in the Wild	EgoWalk：用于机器人野外导航的多模态数据集	imitation learning traversability multimodal
21	Object-Centric Action-Enhanced Representations for Robot Visuo-Motor Policy Learning	提出基于对象中心和动作增强的视觉表示学习方法，用于提升机器人视觉运动策略学习。	policy learning imitation learning

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
22	G-DReaM: Graph-conditioned Diffusion Retargeting across Multiple Embodiments	提出G-DReaM，用于跨多种机器人形态的图条件扩散运动重定向	motion generation motion retargeting cross-embodiment

⬅️ 返回 cs.RO 首页 · 🏠 返回主页