cs.RO（2025-04-14）

📊 共 17 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (8 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱一：机器人控制 (Robot Control) (8 篇)

#题目一句话要点标签🔗⭐
1 PPF: Pre-training and Preservative Fine-tuning of Humanoid Locomotion via Model-Assumption-based Regularization 提出基于模型假设正则化的预训练与保持性微调方法，提升人形机器人复杂地形运动能力 humanoid humanoid robot humanoid locomotion
2 GenTe: Generative Real-world Terrains for General Legged Robot Locomotion Control GenTe：生成式真实地形，提升通用足式机器人运动控制能力 legged robot bipedal biped
3 Flying Hand: End-Effector-Centric Framework for Versatile Aerial Manipulation Teleoperation and Policy Learning 提出以末端执行器为中心的空中操作框架，实现通用遥操作和策略学习。 manipulation model predictive control teleoperation ✅
4 Teacher Motion Priors: Enhancing Robot Locomotion over Challenging Terrain 提出基于教师先验的框架，提升人形机器人在复杂地形上的稳健运动能力 humanoid humanoid robot locomotion
5 Look-to-Touch: A Vision-Enhanced Proximity and Tactile Sensor for Distance and Geometry Perception in Robotic Manipulation 提出视觉增强型近触觉双模态传感器，用于机器人操作中的距离和几何感知 manipulation dexterous manipulation
6 Toward Aligning Human and Robot Actions via Multi-Modal Demonstration Learning 提出多模态示教学习框架，对齐人机动作以解决协作任务中的决策问题。 manipulation imitation learning multimodal
7 HyRRT-Connect: Bidirectional Motion Planning for Hybrid Dynamical Systems 提出HyRRT-Connect算法，解决混合动力系统双向运动规划问题 motion planning
8 Siamese Network with Dual Attention for EEG-Driven Social Learning: Bridging the Human-Robot Gap in Long-Tail Autonomous Driving 提出双注意力Siamese网络，用于脑电驱动的社交学习，解决长尾自动驾驶人机交互问题。 quadruped humanoid shared control

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

#题目一句话要点标签🔗⭐
9 Efficient Task-specific Conditional Diffusion Policies: Shortcut Model Acceleration and SO(3) Optimization 提出基于捷径模型加速和SO(3)优化的高效任务特定条件扩散策略 imitation learning diffusion policy classifier-free guidance
10 Vision based driving agent for race car simulation environments 提出基于视觉的深度强化学习赛车控制，实现轮胎抓地力极限下的最优驾驶 reinforcement learning deep reinforcement learning DRL
11 A Human-Sensitive Controller: Adapting to Human Ergonomics and Physical Constraints via Reinforcement Learning 提出基于强化学习的人机协作机器人控制，优化人体工学并适应个体差异。 reinforcement learning
12 Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Models 提出NaviBridger，利用去噪扩散桥模型提升视觉导航性能 imitation learning multimodal ✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
13 NeRF-Based Transparent Object Grasping Enhanced by Shape Priors 提出基于NeRF和形状先验的透明物体抓取方法，提升机器人操作性能 NeRF grasp prediction
14 Communication-aware Hierarchical Map Compression of Time-Varying Environments for Mobile Robots 提出通信感知的动态环境分层地图压缩框架，用于移动机器人。 occupancy grid

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

#题目一句话要点标签🔗⭐
15 LangPert: Detecting and Handling Task-level Perturbations for Robust Object Rearrangement LangPert：用于鲁棒物体重排列的任务级扰动检测与处理框架 large language model chain-of-thought
16 NaviDiffusor: Cost-Guided Diffusion Model for Visual Navigation NaviDiffusor：面向视觉导航的代价引导扩散模型，实现零样本迁移 zero-shot transfer ✅

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
17 KeyMPs: One-Shot Vision-Language Guided Motion Generation by Sequencing DMPs for Occlusion-Rich Tasks 提出KeyMPs以解决多模态输入下的复杂运动生成问题 motion generation multimodal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页