cs.RO（2025-07-09）

📊 共 16 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (10) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (10 篇)

#	题目	一句话要点	标签	🔗	⭐
1	ULC: A Unified and Fine-Grained Controller for Humanoid Loco-Manipulation	提出ULC：一种统一精细的人形机器人Loco-Manipulation控制器	humanoid humanoid robot whole-body control
2	LOVON: Legged Open-Vocabulary Object Navigator	LOVON：用于具身智能开放词汇目标导航框架	legged robot Unitree open-vocabulary
3	KLEIYN : A Quadruped Robot with an Active Waist for Both Locomotion and Wall Climbing	KLEIYN：一种带主动腰部关节的四足机器人，用于运动和墙壁攀爬	quadruped locomotion reinforcement learning
4	Hierarchical Reinforcement Learning for Articulated Tool Manipulation with Multifingered Hand	提出一种用于灵巧手操作铰接工具的分层强化学习框架。	manipulation dexterous hand reinforcement learning
5	Q-STAC: Q-Guided Stein Variational Model Predictive Actor-Critic	Q-STAC：基于Q值引导的Stein变分模型预测Actor-Critic，提升机器人操作任务的样本效率和稳定性。	manipulation MPC model predictive control
6	SkyVLN: Vision-and-Language Navigation and NMPC Control for UAVs in Urban Environments	SkyVLN：融合视觉语言导航与NMPC控制的城市无人机自主导航框架	model predictive control VLN large language model
7	Failure Forecasting Boosts Robustness of Sim2Real Rhythmic Insertion Policies	基于失败预测的强化学习策略提升Sim2Real节律插入任务的鲁棒性	sim-to-real sim2real reinforcement learning
8	Robust signal decompositions on the circle	提出一种鲁棒的圆上信号分解方法，用于估计圆形轨迹上的地标数量和位置。	motion planning
9	Friction Estimation for In-Hand Planar Motion	提出一种在线估计手内平面滑动摩擦参数的方法	manipulation
10	Distributed Fault-Tolerant Multi-Robot Cooperative Localization in Adversarial Environments	提出一种分布式容错多机器人协同定位框架，增强对抗环境下的鲁棒性。	manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
11	Spatial-Temporal Aware Visuomotor Diffusion Policy Learning	提出4D扩散策略DP4，增强机器人视觉模仿学习中的时空感知能力	policy learning imitation learning behavior cloning
12	Graph-Based Complexity Metrics for Multi-Agent Curriculum Learning: A Validated Approach to Task Ordering in Cooperative Coordination Environments	提出基于图的多智能体课程学习复杂度指标，用于合作协调环境中的任务排序。	reinforcement learning curriculum learning
13	Multi-Task Multi-Agent Reinforcement Learning via Skill Graphs	提出基于技能图的多任务多智能体强化学习方法，提升复杂任务中的知识迁移能力。	reinforcement learning	✅
14	Growing Trees with an Agent: Accelerating RRTs with Learned, Multi-Step Episodic Exploration	Episodic RRT：利用强化学习加速采样式运动规划，提升高维空间探索效率	reinforcement learning deep reinforcement learning DRL	✅
15	Bounomodes: the grazing ox algorithm for exploration of clustered anomalies	提出Bounomodes算法，结合弓耕法与强化学习，高效探索聚类异常区域	reinforcement learning deep reinforcement learning

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

#	题目	一句话要点	标签	🔗	⭐
16	MLFM: Multi-Layered Feature Maps for Richer Language Understanding in Zero-Shot Semantic Navigation	提出MLFM多层特征图，增强零样本语义导航中语言理解能力	semantic map open-vocabulary open vocabulary

⬅️ 返回 cs.RO 首页 · 🏠 返回主页