cs.RO（2024-12-23）

📊 共 11 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (4 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (4 篇)

#题目一句话要点标签🔗⭐
1 Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimicking Mimicking-Bench：通过模仿人类动作学习通用人型机器人与场景交互技能 humanoid humanoid robot imitation learning
2 Sampling-Based Constrained Motion Planning with Products of Experts 提出基于专家乘积的采样约束运动规划方法，提升采样效率和性能。 manipulation MPC model predictive control ✅
3 Online Adaptation for Myographic Control of Natural Dexterous Hand and Finger Movements 提出基于肌电信号在线自适应的自然灵巧手部和手指运动控制方法 dexterous hand reinforcement learning
4 Falsification of Autonomous Systems in Rich Environments 提出基于元规划的自主系统验证方法，提升复杂环境下神经网络控制器的安全性。 motion planning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
5 A Grounded Observer Framework for Establishing Guardrails for Foundation Models in Socially Sensitive Domains 提出基于具身观察者框架，为社会敏感领域的大模型建立行为护栏 foundation model
6 EM-MIAs: Enhancing Membership Inference Attacks in Large Language Models through Ensemble Modeling 提出EM-MIAs，通过集成建模提升大语言模型中的成员推理攻击性能 large language model
7 LMV-RPA: Large Model Voting-based Robotic Process Automation LMV-RPA：基于大模型投票的RPA系统，提升OCR准确率和效率 large language model
8 Multi-Modal Grounded Planning and Efficient Replanning For Learning Embodied Agents with A Few Examples FLARE：基于少量样本的多模态环境感知规划与高效重规划 large language model ✅

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

#题目一句话要点标签🔗⭐
9 ActiveGS: Active Scene Reconstruction Using Gaussian Splatting ActiveGS：利用高斯溅射进行主动场景重建，提升重建质量。 gaussian splatting splatting scene reconstruction

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

#题目一句话要点标签🔗⭐
10 LMD-PGN: Cross-Modal Knowledge Distillation from First-Person-View Images to Third-Person-View BEV Maps for Universal Point Goal Navigation 提出LMD-PGN，通过跨模态知识蒸馏实现通用点目标导航。 reinforcement learning deep reinforcement learning distillation

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
11 End-to-end Generative Spatial-Temporal Ultrasonic Odometry and Mapping Framework 提出端到端生成式时空超声里程计与建图框架，解决低可见度环境下的SLAM问题。 spatiotemporal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页