cs.RO（2025-10-21）

📊 共 21 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (17) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱四：生成式动作 (Generative Motion) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (17 篇)

#	题目	一句话要点	标签	🔗	⭐
1	PGTT: Phase-Guided Terrain Traversal for Perceptive Legged Locomotion	PGTT：基于相位引导的地形遍历方法，提升感知型足式机器人运动的鲁棒性。	legged robot legged locomotion locomotion
2	MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile Manipulation	MoMaGen：通过软硬约束生成多步双臂移动操作演示数据	manipulation mobile manipulation bi-manual
3	Online Object-Level Semantic Mapping for Quadrupeds in Real-World Environments	针对四足机器人，提出一种实时的、对象级别的语义地图构建方法	quadruped semantic mapping semantic map
4	MoTVLA: A Vision-Language-Action Model with Unified Fast-Slow Reasoning	提出MoTVLA模型，融合快慢推理，提升机器人视觉-语言-动作策略的语言可控性和效率。	manipulation policy learning scene understanding
5	Towards An Adaptive Locomotion Strategy For Quadruped Rovers: Quantifying When To Slide Or Walk On Planetary Slopes	针对行星斜坡地形，提出四足机器人自适应行走/滑行策略	quadruped legged locomotion locomotion
6	MPC-based motion planning for non-holonomic systems in non-convex domains	针对非完整约束系统，提出一种在非凸域中基于MPC的运动规划方法	MPC model predictive control motion planning
7	Towards Proprioceptive Terrain Mapping with Quadruped Robots for Exploration in Planetary Permanently Shadowed Regions	面向行星阴影区探索，提出基于四足机器人本体感受的地形建图方法	quadruped legged robot locomotion
8	Quadrupeds for Planetary Exploration: Field Testing Control Algorithms on an Active Volcano	在活火山上测试四足机器人控制算法，用于行星探索	quadruped legged robot locomotion
9	VITA-E: Natural Embodied Interaction with Concurrent Seeing, Hearing, Speaking, and Acting	VITA-E：提出并发视听言行交互框架，实现具身智能体实时中断与动态响应。	humanoid vision-language-action VLA
10	Efficient Model-Based Reinforcement Learning for Robot Control via Online Learning	提出一种高效的在线模型强化学习算法，用于直接控制复杂机器人系统。	sim-to-real reinforcement learning
11	Safe Active Navigation and Exploration for Planetary Environments Using Proprioceptive Measurements	提出SAEGT，利用本体感知实现行星环境下腿式机器人安全自主导航与探索	legged robot locomotion traversability
12	Motion Planning and Control of an Overactuated 4-Wheel Drive with Constrained Independent Steering	针对4WIS机器人，提出考虑转向约束的运动规划与控制方法	motion planning
13	SHRUMS: Sensor Hallucination for Real-time Underwater Motion Planning with a Compact 3D Sonar	SHRUMS：用于水下机器人实时运动规划的3D声呐传感器幻觉方法	motion planning
14	MADR: MPC-guided Adversarial DeepReach	MADR：提出MPC引导的对抗深度可达性方法，解决高维零和博弈中的安全策略问题。	MPC
15	Kinematic Analysis and Integration of Vision Algorithms for a Mobile Manipulator Employed Inside a Self-Driving Laboratory	针对自动驾驶实验室，提出移动机械臂的运动学分析与视觉算法集成方案	manipulation
16	$\nabla$-SDF: Learning Euclidean Signed Distance Functions Online with Gradient-Augmented Octree Interpolation and Neural Residual	提出$ abla$-SDF以解决在线大规模SDF重建问题	motion planning
17	Sharing the Load: Distributed Model-Predictive Control for Precise Multi-Rover Cargo Transport	提出一种分布式模型预测控制方法，用于多机器人协同精确货物运输。	MPC

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

#	题目	一句话要点	标签	🔗	⭐
18	A Compositional Paradigm for Foundation Models: Towards Smarter Robotic Agents	提出基于持续学习和组合性的范式，提升具身智能体在动态环境中的适应性	foundation model
19	EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval	EfficientNav：面向端侧对象目标导航，通过导航地图缓存与检索实现高效LLM导航。	large language model	✅

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
20	A Cross-Environment and Cross-Embodiment Path Planning Framework via a Conditional Diffusion Model	提出GADGET，一种基于条件扩散模型的跨环境和机器人路径规划框架	classifier-free guidance cross-embodiment zero-shot transfer

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

#	题目	一句话要点	标签	🔗	⭐
21	Event-Grounding Graph: Unified Spatio-Temporal Scene Graph from Robotic Observations	提出事件-锚定图（EGG），用于机器人观测中的统一时空场景表示	scene understanding	✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页