cs.RO（2025-10-13）

📊 共 27 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (18 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱一：机器人控制 (Robot Control) (18 篇)

#题目一句话要点标签🔗⭐
1 DemoHLM: From One Demonstration to Generalizable Humanoid Loco-Manipulation DemoHLM：基于单次模拟演示实现通用人形机器人移动操作 humanoid humanoid robot whole-body control
2 NaviGait: Navigating Dynamically Feasible Gait Libraries using Deep Reinforcement Learning NaviGait：利用深度强化学习导航动态可行步态库，实现稳健的双足机器人运动控制。 bipedal biped locomotion
3 Phys2Real: Fusing VLM Priors with Interactive Online Adaptation for Uncertainty-Aware Sim-to-Real Manipulation Phys2Real：融合VLM先验与交互式在线自适应，实现不确定性感知的Sim-to-Real操作 manipulation sim-to-real domain randomization
4 Ego-Vision World Model for Humanoid Contact Planning 提出基于自中心视觉世界模型的类人机器人接触规划方法 humanoid humanoid robot MPC
5 Path and Motion Optimization for Efficient Multi-Location Inspection with Humanoid Robots 提出一种高效的人形机器人多点巡检路径与运动优化框架 humanoid humanoid robot MPC
6 Towards a Unified Understanding of Robot Manipulation: A Comprehensive Survey 机器人操作的统一理解：全面的综述，涵盖方法、瓶颈与应用。 manipulation policy learning affordance ✅
7 ManiAgent: An Agentic Framework for General Robotic Manipulation ManiAgent：一种用于通用机器人操作的Agent框架，解决复杂推理和长时程任务规划问题。 manipulation vision-language-action VLA ✅
8 Simultaneous Calibration of Noise Covariance and Kinematics for State Estimation of Legged Robots via Bi-level Optimization 提出双层优化框架，同步标定腿式机器人状态估计中的噪声协方差与运动学参数 quadruped legged robot humanoid
9 PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System PhysHSI：面向真实世界可泛化和自然的人形机器人场景交互系统 humanoid humanoid robot policy learning
10 Constraint-Aware Reinforcement Learning via Adaptive Action Scaling 提出基于自适应动作缩放的约束感知强化学习方法，提升安全性和性能。 locomotion reinforcement learning SAC
11 A Modular AIoT Framework for Low-Latency Real-Time Robotic Teleoperation in Smart Cities 提出基于AIoT的模块化低延迟机器人遥操作框架，应用于智慧城市。 manipulation teleoperation
12 Design and Koopman Model Predictive Control of A Soft Exoskeleton Based on Origami-Inspired Pneumatic Actuator for Knee Rehabilitation 提出基于折纸气动软体外骨骼的Koopman模型预测控制方法，用于膝关节康复。 MPC model predictive control
13 More than A Point: Capturing Uncertainty with Adaptive Affordance Heatmaps for Spatial Grounding in Robotic Tasks RoboMAP：提出自适应Affordance热图，提升机器人空间定位任务的鲁棒性与效率 manipulation affordance
14 HiMaCon: Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data HiMaCon：从无标注多模态数据中发现分层操作概念，提升机器人操作泛化性 manipulation representation learning
15 Unveiling Uncertainty-Aware Autonomous Cooperative Learning Based Planning Strategy 提出基于不确定性感知的自主协同学习规划策略，提升多车交互的安全性和有效性。 motion planning reinforcement learning deep reinforcement learning
16 SCOOP'D: Learning Mixed-Liquid-Solid Scooping via Sim2Real Generative Policy SCOOP'D：基于Sim2Real生成策略学习混合液体-固体抓取 sim2real ✅
17 Into the Unknown: Towards using Generative Models for Sampling Priors of Environment Uncertainty for Planning in Configuration Spaces 提出基于生成模型的采样方法，用于配置空间规划中环境不确定性的先验估计。 motion planning
18 An Adaptive Transition Framework for Game-Theoretic Based Takeover 提出基于博弈论的自适应过渡框架，优化自动驾驶系统中的控制权切换 shared control

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

#题目一句话要点标签🔗⭐
19 A Primer on SO(3) Action Representations in Deep Reinforcement Learning 提出SO(3)动作表示以解决机器人控制中的方向性问题 reinforcement learning deep reinforcement learning PPO
20 Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling Flow Planner：基于流匹配的自动驾驶规划，提升复杂交互行为建模能力 imitation learning flow matching classifier-free guidance
21 Coordinated Strategies in Realistic Air Combat by Hierarchical Multi-Agent Reinforcement Learning 提出一种分层多智能体强化学习框架，用于解决复杂空战环境中的协同策略问题。 reinforcement learning curriculum learning
22 Game-Theoretic Risk-Shaped Reinforcement Learning for Safe Autonomous Driving 提出博弈论风险塑造强化学习框架GTR2L，用于安全自动驾驶。 reinforcement learning world model ✅
23 XGrasp: Gripper-Aware Grasp Detection with Multi-Gripper Data Generation XGrasp：提出一种支持多夹爪的实时、gripper感知的抓取检测框架。 contrastive learning foundation model

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

#题目一句话要点标签🔗⭐
24 J-ORA: A Framework and Multimodal Dataset for Japanese Object Identification, Reference, Action Prediction in Robot Perception J-ORA：用于机器人感知的日语物体识别、指代和动作预测的多模态数据集与框架 affordance multimodal ✅
25 GRIP: A Unified Framework for Grid-Based Relay and Co-Occurrence-Aware Planning in Dynamic Environments GRIP：动态环境中基于网格的中继与共现感知统一规划框架 open-vocabulary open vocabulary occupancy grid

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

#题目一句话要点标签🔗⭐
26 RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Model RoVer：利用机器人奖励模型作为测试时验证器，提升视觉-语言-动作模型的性能 vision-language-action VLA

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
27 Robot Soccer Kit: Omniwheel Tracked Soccer Robots for Education 提出一种基于外部跟踪系统的全向轮足球机器人教育套件 egocentric

⬅️ 返回 cs.RO 首页 · 🏠 返回主页