cs.RO（2025-10-20）

📊 共 21 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (16) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱四：生成式动作 (Generative Motion) (2) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱一：机器人控制 (Robot Control) (16 篇)

#题目一句话要点标签🔗⭐
1 Robobench: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models as Embodied Brain RoboBench：用于评估多模态大语言模型作为具身智能大脑的综合基准 manipulation affordance spatiotemporal
2 Bridging Embodiment Gaps: Deploying Vision-Language-Action Models on Soft Robots 提出将视觉-语言-动作模型应用于软机器人以解决安全交互问题 manipulation embodied AI vision-language-action
3 Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey 综述高效视觉-语言-动作模型，解决具身操作中计算资源受限问题 manipulation vision-language-action VLA
4 Humanoid Goalkeeper: Learning from Position Conditioned Task-Motion Constraints 提出基于位置条件任务-运动约束的人形机器人守门员强化学习框架 quadruped humanoid humanoid robot
5 RESample: A Robust Data Augmentation Framework via Exploratory Sampling for Robotic Manipulation RESample：探索式采样增强机器人操作的鲁棒数据增强框架 manipulation reinforcement learning offline reinforcement learning
6 SoftMimic: Learning Compliant Whole-body Control from Examples SoftMimic：从示例中学习柔顺的人形机器人全身控制 humanoid humanoid robot whole-body control
7 Decentralized Real-Time Planning for Multi-UAV Cooperative Manipulation via Imitation Learning 提出基于模仿学习的无人机协同操作分散式实时规划方法 manipulation imitation learning
8 An adaptive hierarchical control framework for quadrupedal robots in planetary exploration 提出一种自适应分层控制框架，用于行星探测四足机器人未知环境导航。 quadruped legged robot
9 Floating-Base Deep Lagrangian Networks 提出FeLaN，结合深度学习与拉格朗日力学，解决浮动基座系统物理约束建模问题 quadruped humanoid physically plausible
10 Distributed Spatial-Temporal Trajectory Optimization for Unmanned-Aerial-Vehicle Swarm 提出基于ADMM和DDP的分布式时空轨迹优化框架，解决无人机集群轨迹规划问题 trajectory optimization
11 OmniVIC: A Self-Improving Variable Impedance Controller with Vision-Language In-Context Learning for Safe Robotic Manipulation OmniVIC：基于视觉语言上下文学习的自提升变阻抗控制器，用于安全机器人操作 manipulation
12 Intent-Driven LLM Ensemble Planning for Flexible Multi-Robot Disassembly: Demonstration on EV Batteries 提出意图驱动的LLM集成规划方法，用于柔性多机器人拆卸电动汽车电池。 manipulation large language model
13 HumanMPC - Safe and Efficient MAV Navigation among Humans HumanMPC：面向人机共存环境的安全高效无人机导航 MPC model predictive control
14 Implicit State Estimation via Video Replanning 提出基于视频重规划的隐式状态估计框架，提升交互式操作任务的适应性。 manipulation spatiotemporal
15 DDBot: Differentiable Physics-based Digging Robot for Unknown Granular Materials DDBot：用于未知颗粒材料的可微物理挖掘机器人 manipulation
16 Learning to Design Soft Hands using Reward Models 提出基于奖励模型的交叉熵方法，高效优化柔性手爪设计。 teleoperation

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

#题目一句话要点标签🔗⭐
17 From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors FALCON：利用空间基础先验增强视觉-语言-动作模型的3D环境泛化能力 vision-language-action VLA foundation model
18 RoboChallenge: Large-scale Real-robot Evaluation of Embodied Policies RoboChallenge：大规模真实机器人环境下的具身策略评估系统 VLA

🔬 支柱四：生成式动作 (Generative Motion) (2 篇)

#题目一句话要点标签🔗⭐
19 DiffVLA++: Bridging Cognitive Reasoning and End-to-End Driving through Metric-Guided Alignment DiffVLA++：通过度量引导对齐桥接认知推理与端到端驾驶 physically plausible vision-language-action VLA
20 Quality Over Quantity: Curating Contact-Based Robot Datasets Improves Learning 提出基于接触感知的机器人数据筛选方法，提升机器人学习效率与确定性 contact-aware

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

#题目一句话要点标签🔗⭐
21 R2BC: Multi-Agent Imitation Learning from Single-Agent Demonstrations R2BC：从单智能体演示中学习多智能体协作策略 imitation learning behavior cloning

⬅️ 返回 cs.RO 首页 · 🏠 返回主页