cs.RO（2025-12-12）

📊 共 14 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (9 🔗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) (2 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (9 篇)

#题目一句话要点标签🔗⭐
1 UniBYD: A Unified Framework for Learning Robotic Manipulation Across Embodiments Beyond Imitation of Human Demonstrations UniBYD：统一框架，超越模仿人类演示，学习跨形态机器人操作 manipulation reinforcement learning PPO ✅
2 BLURR: A Boosted Low-Resource Inference for Vision-Language-Action Models BLURR：一种加速VLA模型低资源推理的轻量级封装器 manipulation vision-language-action VLA
3 A Review of Learning-Based Motion Planning: Toward a Data-Driven Optimal Control Approach 提出数据驱动的最优控制范式，解决自动驾驶运动规划中透明性与适应性的权衡问题 motion planning reinforcement learning imitation learning
4 AnchorDream: Repurposing Video Diffusion for Embodiment-Aware Robot Data Synthesis AnchorDream：利用视频扩散模型进行具身感知机器人数据合成 sim-to-real teleoperation policy learning
5 Bench-Push: Benchmarking Pushing-based Navigation and Manipulation Tasks for Mobile Robots Bench-Push：移动机器人推碰式导航与操作任务的统一基准测试平台 manipulation ✅
6 Towards Logic-Aware Manipulation: A Knowledge Primitive for VLM-Based Assistants in Smart Manufacturing 提出面向逻辑的操纵知识基元，用于智能制造中基于VLM的助手 manipulation
7 Cross-Entropy Optimization of Physically Grounded Task and Motion Plans 提出基于交叉熵优化的物理引擎驱动的任务与运动规划方法 manipulation TAMP ✅
8 Agile Flight Emerges from Multi-Agent Competitive Racing 基于多智能体竞争强化学习，实现无人机敏捷飞行与策略博弈 sim-to-real reinforcement learning ✅
9 Untethered thin dielectric elastomer actuated soft robot 提出一种无线薄型介电弹性体驱动软体机器人，适用于狭窄空间操作。 locomotion

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

#题目一句话要点标签🔗⭐
10 Seeing to Act, Prompting to Specify: A Bayesian Factorization of Vision Language Action Policy 提出BayesVLA，通过贝叶斯分解解决VLA模型中的模态不平衡和泛化问题 vision-language-action VLA foundation model ✅
11 An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges 对视觉-语言-动作模型进行解剖，剖析模块、里程碑与挑战 generalist agent vision-language-action VLA ✅
12 Architecting Large Action Models for Human-in-the-Loop Intelligent Robots 构建可验证神经符号LAM，提升人机协作机器人智能 large language model 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🔗⭐
13 ProbeMDE: Uncertainty-Guided Active Proprioception for Monocular Depth Estimation in Surgical Robotics ProbeMDE：不确定性引导的主动触觉单目深度估计，用于手术机器人 depth estimation monocular depth ✅
14 A Stochastic Approach to Terrain Maps for Safe Lunar Landing 提出基于双阶段高斯过程的月球地形随机地图生成方法，提升月球安全着陆能力。 elevation map

⬅️ 返回 cs.RO 首页 · 🏠 返回主页