cs.RO（2025-09-29）

📊 共 35 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (27 🔗5) 支柱三：空间感知与语义 (Perception & Semantics) (4 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱一：机器人控制 (Robot Control) (27 篇)

#题目一句话要点标签🔗⭐
1 Preference-Based Long-Horizon Robotic Stacking with Multimodal Large Language Models 提出基于偏好的多模态大语言模型，用于长时程机器人堆叠任务 humanoid humanoid robot manipulation
2 World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training 提出World-Env，利用世界模型作为VLA模型后训练的虚拟环境，提升数据稀缺场景性能。 manipulation reinforcement learning imitation learning ✅
3 AIRoA MoMa Dataset: A Large-Scale Hierarchical Dataset for Mobile Manipulation AIRoA MoMa：用于移动操作的大规模分层数据集，助力通用机器人 manipulation mobile manipulation generalist agent ✅
4 Unlocking the Potential of Soft Actor-Critic for Imitation Learning 提出AMP+SAC模仿学习框架，提升四足机器人运动生成的数据效率与泛化性 quadruped PPO SAC
5 IA-VLA: Input Augmentation for Vision-Language-Action models in settings with semantically complex tasks 提出IA-VLA框架，利用大型视觉语言模型增强VLA在语义复杂任务中的表现 manipulation vision-language-action VLA
6 Towards Tighter Convex Relaxation of Mixed-integer Programs: Leveraging Logic Network Flow for Task and Motion Planning 提出逻辑网络流框架，通过更紧的凸松弛加速任务与运动规划 quadruped motion planning task and motion planning ✅
7 CoTaP: Compliant Task Pipeline and Reinforcement Learning of Its Controller with Compliance Modulation 提出CoTaP框架，通过强化学习和柔顺控制实现人型机器人全身运动控制。 humanoid humanoid robot locomotion
8 Stabilizing Humanoid Robot Trajectory Generation via Physics-Informed Learning and Control-Informed Steering 提出一种融合物理信息学习与控制引导的人形机器人轨迹生成方法，提升轨迹稳定性和物理可行性。 humanoid humanoid robot locomotion
9 JuggleRL: Mastering Ball Juggling with a Quadrotor via Deep Reinforcement Learning JuggleRL：基于深度强化学习的四旋翼飞行器空中杂耍控制 sim-to-real domain randomization reinforcement learning
10 Learning to Sample: Reinforcement Learning-Guided Sampling for Autonomous Vehicle Motion Planning 提出基于强化学习引导采样的运动规划方法，提升自动驾驶在复杂城市环境中的决策效率。 motion planning reinforcement learning world model ✅
11 CEDex: Cross-Embodiment Dexterous Grasp Generation at Scale from Human-like Contact Representations 提出CEDex以解决跨躯体灵巧抓取生成问题 manipulation cross-embodiment
12 Annotation-Free One-Shot Imitation Learning for Multi-Step Manipulation Tasks 提出一种免标注的单样本模仿学习方法，用于多步操作任务 manipulation imitation learning
13 ViReSkill: Vision-Grounded Replanning with Skill Memory for LLM-Based Planning in Lifelong Robot Learning ViReSkill：基于视觉的技能记忆重规划，提升LLM在终身机器人学习中的规划能力 sim-to-real motion planning reinforcement learning
14 Parallel Heuristic Search as Inference for Actor-Critic Reinforcement Learning Models 提出PACHS算法，利用Actor-Critic模型进行高效并行启发式搜索，提升机器人操作任务性能。 manipulation motion planning reinforcement learning
15 Memory Transfer Planning: LLM-driven Context-Aware Code Adaptation for Robot Manipulation 提出Memory Transfer Planning，利用LLM上下文学习实现机器人操作代码的跨环境迁移。 manipulation large language model
16 SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation 提出SARM：用于长时程机器人操作的阶段感知奖励建模 manipulation imitation learning behavior cloning
17 MSG: Multi-Stream Generative Policies for Sample-Efficient Robotic Manipulation 提出多流生成策略MSG，提升机器人操作任务的样本效率和泛化能力。 manipulation policy learning flow matching
18 SRMP: Search-Based Robot Motion Planning Library SRMP：面向机器人操作的、基于搜索的运动规划库，提升可预测性和一致性。 manipulation motion planning
19 U-DiT Policy: U-shaped Diffusion Transformers for Robotic Manipulation 提出U-DiT Policy，融合U-Net和Transformer优势，提升机器人操作任务的扩散策略性能。 manipulation diffusion policy
20 SafeFlowMatcher: Safe and Fast Planning using Flow Matching with Control Barrier Functions SafeFlowMatcher：结合流匹配与控制障碍函数的安全快速规划框架 locomotion flow matching
21 PoseDiff: A Unified Diffusion Model Bridging Robot Pose Estimation and Video-to-Action Control PoseDiff：统一扩散模型桥接机器人姿态估计与视频到动作控制 manipulation world model embodied AI ✅
22 A Novel Model for 3D Motion Planning for a Generalized Dubins Vehicle with Pitch and Yaw Rate Constraints 提出一种考虑俯仰和偏航速率约束的广义Dubins车辆3D运动规划新模型 motion planning
23 From Code to Action: Hierarchical Learning of Diffusion-VLM Policies 提出基于扩散-VLM策略的分层学习框架，提升机器人操作模仿学习的泛化性和数据效率 manipulation imitation learning diffusion policy
24 Crop Spirals: Re-thinking the field layout for future robotic agriculture 提出螺旋形农田布局，优化机器人导航，提升农业自动化效率 MPC model predictive control
25 APREBot: Active Perception System for Reflexive Evasion Robot APREBot：用于反射性避障机器人的主动感知系统 quadruped sim-to-real
26 Game Theory to Study Cooperation in Human-Robot Mixed Groups: Exploring the Potential of the Public Good Game 利用公共物品博弈研究人机混合群体中的合作行为 humanoid humanoid robot
27 Trajectory Prediction via Bayesian Intention Inference under Unknown Goals and Kinematics 提出一种自适应贝叶斯算法，用于未知目标和运动学条件下的实时轨迹预测。 quadruped

🔬 支柱三：空间感知与语义 (Perception & Semantics) (4 篇)

#题目一句话要点标签🔗⭐
28 PhysiAgent: An Embodied Agent Framework in Physical World PhysiAgent：一个物理世界中的具身智能体框架，提升VLM与VLA协同 scene understanding vision-language-action VLA
29 Safe Planning in Unknown Environments using Conformalized Semantic Maps 提出基于Conformalized Semantic Maps的安全规划方法，解决未知环境下的语义导航问题 semantic map
30 PROFusion: Robust and Accurate Dense Reconstruction via Camera Pose Regression and Optimization PROFusion：结合相机位姿回归与优化的鲁棒精确稠密重建 scene reconstruction ✅
31 SONAR: Semantic-Object Navigation with Aggregated Reasoning through a Cross-Modal Inference Paradigm SONAR：融合语义地图与视觉语言模型的跨模态推理导航方法 semantic map

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
32 DynaMIC: Dynamic Multimodal In-Context Learning Enabled Embodied Robot Counterfactual Resistance Ability DynaMIC：动态多模态上下文学习赋能具身机器人反事实抵抗能力 multimodal
33 AdaNav: Adaptive Reasoning with Uncertainty for Vision-Language Navigation AdaNav：面向视觉-语言导航，基于不确定性的自适应推理框架 vision-language-navigation VLN ✅
34 LLM-Handover:Exploiting LLMs for Task-Oriented Robot-Human Handovers LLM-Handover：利用大语言模型实现面向任务的人机物体交接 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
35 Curriculum Imitation Learning of Distributed Multi-Robot Policies 提出课程模仿学习方法，解决多机器人系统长期协同控制问题 imitation learning curriculum learning egocentric

⬅️ 返回 cs.RO 首页 · 🏠 返回主页