cs.RO（2025-02-21）

📊 共 10 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (6 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1) 支柱四：生成式动作 (Generative Motion) (1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱一：机器人控制 (Robot Control) (6 篇)

#题目一句话要点标签🔗⭐
1 Reduced-Order Model Guided Contact-Implicit Model Predictive Control for Humanoid Locomotion 结合降阶模型与接触隐式MPC的人形机器人运动控制 humanoid humanoid robot humanoid locomotion
2 Discovery and Deployment of Emergent Robot Swarm Behaviors via Representation Learning and Real2Sim2Real Transfer 提出基于自监督表征学习和Real2Sim2Real迁移的机器人集群涌现行为发现与部署方法 sim2real real2sim representation learning
3 Pick-and-place Manipulation Across Grippers Without Retraining: A Learning-optimization Diffusion Policy Approach 提出基于学习-优化的扩散策略，实现机器人跨gripper的零样本抓取放置操作。 manipulation imitation learning diffusion policy ✅
4 Enhanced Probabilistic Collision Detection for Motion Planning Under Sensing Uncertainty 提出增强概率碰撞检测方法，解决机器人运动规划中感知不确定性问题 sim2real real2sim motion planning
5 Learning Long-Horizon Robot Manipulation Skills via Privileged Action 提出基于特权行动的强化学习框架，解决长时程机器人操作技能学习难题 manipulation reinforcement learning curriculum learning
6 A Simulation Pipeline to Facilitate Real-World Robotic Reinforcement Learning Applications 提出一种机器人强化学习仿真流程，降低仿真与现实差距，加速真实机器人部署。 sim-to-real reinforcement learning

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

#题目一句话要点标签🔗⭐
7 Exploring Embodied Multimodal Large Models: Development, Datasets, and Future Directions 探索具身多模态大模型：发展、数据集与未来方向综述 large language model multimodal

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

#题目一句话要点标签🔗⭐
8 DynamicGSG: Dynamic 3D Gaussian Scene Graphs for Environment Adaptation DynamicGSG：利用动态3D高斯场景图实现环境自适应 gaussian splatting splatting open-vocabulary ✅

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
9 Towards Autonomous Navigation of Neuroendovascular Tools for Timely Stroke Treatment via Contact-aware Path Planning 提出基于接触感知的神经血管工具自主导航方法，用于及时治疗卒中 contact-aware

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

#题目一句话要点标签🔗⭐
10 BOSS: Benchmark for Observation Space Shift in Long-Horizon Task 提出BOSS基准测试，用于评估长时任务中观察空间偏移问题 imitation learning OpenVLA

⬅️ 返回 cs.RO 首页 · 🏠 返回主页