cs.RO（2026-05-25）

📊 共 17 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (12 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (12 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Safety-Critical Whole-Body Control for Humanoid Robots via Input-to-State Safe Control Barrier Functions	提出基于ISSf-CBF的人形机器人安全关键全身控制框架，提升复杂环境下的安全性。	humanoid humanoid robot whole-body control	✅
2	ParkourFormer: Integrating Predictive Supervision and Sequence Modeling into Parkour Locomotion	ParkourFormer：融合预测监督和序列建模，提升人形机器人跑酷运动能力	humanoid humanoid robot humanoid locomotion
3	HumanFlow -- Diffusion-Driven MAV Navigation Among Humans via Tightly-Coupled Motion Tracking, Forecasting, and Control	HumanFlow：基于扩散模型的无人机人群导航，实现紧耦合的运动跟踪、预测与控制	motion tracking MPC flow matching
4	EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models	EXPO-FT：面向视觉-语言-动作模型的高效强化学习微调	manipulation reinforcement learning vision-language-action
5	OASIS: Observation-Action Space Alignment via SE(3) Trajectory Prediction for Robotic Manipulation	OASIS：通过SE(3)轨迹预测对齐观察-动作空间，提升机器人操作性能	manipulation world action model world action models	✅
6	FOUND-IT: Foundation-model-first Task-driven 3D Scene Graphs with Granularity on Demand	FOUND-IT：基于几何基础模型的按需粒度任务驱动3D场景图构建	manipulation loco-manipulation traversability
7	RepSAM: Bridging Foundation Models to Robotic Vision via Representation-Guided Adaptation	RepSAM：通过表征引导的适配，桥接基础模型与机器人视觉	manipulation foundation model
8	Prior Policy Guided Dual-Agent Coordinated Manipulation Planning of Spacecraft-Manipulator System	提出先验策略引导的双智能体协同操作规划框架，解决航天器-机械臂系统姿态稳定控制问题	manipulation reinforcement learning deep reinforcement learning	✅
9	Compliant Non-Prehensile Pushing Manipulation	提出一种基于模型预测控制的柔顺非抓取推物操作方法，用于人机协作环境。	manipulation model predictive control
10	TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulation	TapSampling：结合任务理解的推理时采样，提升机器人操作性能	manipulation
11	Parallel Differentiable Reachability for Learning and Planning with Certified Neural Dynamics and Controllers	提出并行可微可达性框架，用于学习和规划具有认证神经动力学和控制器的系统	manipulation reachability-aware MPC
12	When Search Becomes Memory: Turning Robot Design Trials into Transferable Skills	Auto-Robotist：将机器人设计经验转化为可迁移技能，提升进化搜索效率	locomotion 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	🔗	⭐
13	Decision-Making with Lightweight Confidence-Aware Language Model for Autonomous Driving	提出轻量级置信度感知语言模型，用于自动驾驶决策	distillation large language model multimodal
14	How to Mitigate the Distribution Shift Problem in Robotics Control: A Robust and Adaptive Approach Based on Offline to Online Imitation Learning	提出一种鲁棒自适应的离线到在线模仿学习框架，缓解机器人控制中的分布偏移问题	imitation learning

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

#	题目	一句话要点	标签	🔗	⭐
15	G-DRAGON: Geospatial Reasoning and Dynamic Planning for Retrieval-Augmented Outdoor Navigation	G-DRAGON：用于检索增强户外导航的地理空间推理与动态规划	open-vocabulary open vocabulary VLN
16	Implicit Null-space Manifold Generation for Redundant Robotic Systems	提出基于隐式零空间的流形生成方法，用于冗余机器人系统。	implicit representation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
17	RePlan-Bot: Multi-Level Replanning for Embodied Instruction Following	RePlan-Bot：面向具身指令跟随的多层次重规划方法	instruction following

⬅️ 返回 cs.RO 首页 · 🏠 返回主页