cs.RO（2025-10-30）

📊 共 25 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (16 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱一：机器人控制 (Robot Control) (16 篇)

#题目一句话要点标签🔗⭐
1 SpikeATac: A Multimodal Tactile Finger with Taxelized Dynamic Sensing for Dexterous Manipulation SpikeATac：用于灵巧操作的多模态触觉手指，具有可分割的动态传感 manipulation dexterous manipulation in-hand manipulation ✅
2 PHUMA: Physically-Grounded Humanoid Locomotion Dataset 提出PHUMA：一个物理约束的人形机器人运动数据集，提升运动模仿性能。 humanoid humanoid locomotion locomotion ✅
3 Kinodynamic Task and Motion Planning using VLM-guided and Interleaved Sampling 提出基于VLM引导和交错采样的运动学任务与运动规划方法 motion planning task and motion planning TAMP
4 Cooperative Task Spaces for Multi-Arm Manipulation Control based on Similarity Transformations 提出基于相似变换的协作任务空间，用于多臂操作控制 humanoid operational space control manipulation
5 Hybrid Consistency Policy: Decoupling Multi-Modal Diversity and Real-Time Efficiency in Robotic Manipulation 提出混合一致性策略HCP，解耦机器人操作中的多模态多样性和实时效率。 manipulation policy learning imitation learning
6 Human-in-the-loop Online Rejection Sampling for Robotic Manipulation 提出Hi-ORS，通过在线拒绝采样提升机器人操作的强化学习稳定性与鲁棒性 manipulation reinforcement learning imitation learning
7 Morphology-Aware Graph Reinforcement Learning for Tensegrity Robot Locomotion 提出一种形态感知图强化学习方法，用于张拉整体机器人运动控制。 locomotion reinforcement learning SAC
8 Real-DRL: Teach and Learn in Reality Real-DRL框架：在真实环境中安全地训练深度强化学习智能体 quadruped sim2real reinforcement learning
9 Leveraging Foundation Models for Enhancing Robot Perception and Action 利用Foundation模型增强机器人感知与行动能力 manipulation foundation model
10 Reinforcement Learning for Robotic Safe Control with Force Sensing 提出基于力感知的强化学习方法，提升机器人安全控制和Sim2Real迁移能力 manipulation sim-to-real reinforcement learning
11 Thor: Towards Human-Level Whole-Body Reactions for Intense Contact-Rich Environments Thor框架：实现人型机器人在强接触环境中类人全身反应 humanoid humanoid control Unitree
12 Adaptive Inverse Kinematics Framework for Learning Variable-Length Tool Manipulation in Robotics 提出自适应逆运动学框架，用于机器人学习变长工具操作 manipulation
13 Beyond the Uncanny Valley: A Mixed-Method Investigation of Anthropomorphism in Protective Responses to Robot Abuse 研究类人机器人受虐待时，不同程度的拟人化如何影响人类的保护反应。 humanoid humanoid robot PULSE
14 NaviTrace: Evaluating Embodied Navigation of Vision-Language Models NaviTrace：提出视觉-语言模型具身导航评测基准，解决真实机器人导航评估难题 legged robot foundation model ✅
15 Heuristic Adaptation of Potentially Misspecified Domain Support for Likelihood-Free Inference in Stochastic Dynamical Systems 提出三种启发式LFI变体，自适应调整领域支持，提升随机动力系统中的无似然推理性能 manipulation policy learning
16 Embodied Intelligence for Advanced Bioinspired Microrobotics: Examples and Insights 基于具身智能的微型机器人设计，实现高效自主运动与导航 locomotion

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
17 Hybrid DQN-TD3 Reinforcement Learning for Autonomous Navigation in Dynamic Environments 提出混合DQN-TD3强化学习方法，用于动态环境中自主导航。 reinforcement learning TD3 reward shaping
18 Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail 提出Alpamayo-R1，通过因果推理和轨迹规划提升长尾场景下自动驾驶的泛化能力。 reinforcement learning imitation learning vision-language-action
19 Towards Reinforcement Learning Based Log Loading Automation 提出基于强化学习的木材装载自动化方法，提升林业作业效率 reinforcement learning curriculum learning
20 Accelerating Real-World Overtaking in F1TENTH Racing Employing Reinforcement Learning Methods 提出基于强化学习的F1TENTH赛车超车算法，提升真实场景超车成功率 reinforcement learning

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

#题目一句话要点标签🔗⭐
21 A Multi-Modal Neuro-Symbolic Approach for Spatial Reasoning-Based Visual Grounding in Robotics 提出一种多模态神经符号方法，用于机器人中基于空间推理的视觉定位 embodied AI visual grounding
22 RoboOS-NeXT: A Unified Memory-based Framework for Lifelong, Scalable, and Robust Multi-Robot Collaboration RoboOS-NeXT：面向终身学习、可扩展和鲁棒多机器人协作的统一内存框架 vision-language-action VLA ✅
23 Running VLAs at Real-time Speed 提出加速策略，单GPU实现30Hz多视角VLA实时运行，赋能动态机器人任务 VLA ✅

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

#题目一句话要点标签🔗⭐
24 AgriGS-SLAM: Orchard Mapping Across Seasons via Multi-View Gaussian Splatting SLAM AgriGS-SLAM：基于多视角高斯溅射的果园跨季节建图SLAM 3D gaussian splatting 3DGS gaussian splatting

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
25 Adaptive Trajectory Refinement for Optimization-based Local Planning in Narrow Passages 提出自适应轨迹优化算法，解决移动机器人在狭窄通道中的局部规划问题 penetration

⬅️ 返回 cs.RO 首页 · 🏠 返回主页