cs.RO（2025-04-02）

📊 共 16 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (10 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱一：机器人控制 (Robot Control) (10 篇)

#题目一句话要点标签🔗⭐
1 Bi-LAT: Bilateral Control-Based Imitation Learning via Natural Language and Action Chunking with Transformers Bi-LAT：基于双边控制、自然语言和动作分块的Transformer模仿学习框架 manipulation bi-manual teleoperation ✅
2 8-DoFs Cable Driven Parallel Robots for Bimanual Teleportation 提出基于缆索驱动并联机器人的8自由度主控制器，用于双臂遥操作 bi-manual dual-arm teleoperation
3 Teaching Robots to Handle Nuclear Waste: A Teleoperation-Based Learning Approach< 提出基于遥操作学习框架，提升机器人核废料处理能力 manipulation teleoperation
4 TransforMerger: Transformer-based Voice-Gesture Fusion for Robust Human-Robot Communication 提出TransforMerger，融合语音和手势，实现鲁棒的人机交互 manipulation scene understanding multimodal
5 RoboAct-CLIP: Video-Driven Pre-training of Atomic Action Understanding for Robotics RoboAct-CLIP：面向机器人原子动作理解的视频驱动预训练模型 manipulation representation learning multimodal
6 Pedestrian-Aware Motion Planning for Autonomous Driving in Complex Urban Scenarios 提出融合社会力与风险感知的运动规划算法，解决复杂城市环境下自动驾驶的行人感知问题。 motion planning ✅
7 Preference-Driven Active 3D Scene Representation for Robotic Inspection in Nuclear Decommissioning 提出基于人类反馈强化学习的主动3D场景表示方法，用于核退役机器人巡检。 manipulation reinforcement learning RLHF
8 Inverse RL Scene Dynamics Learning for Nonlinear Predictive Control in Autonomous Vehicles 提出基于逆强化学习的场景动态学习方法，用于自动驾驶车辆的非线性预测控制。 model predictive control reinforcement learning inverse reinforcement learning
9 The Social Life of Industrial Arms: How Arousal and Attention Shape Human-Robot Interaction 通过唤醒度和注意力机制提升工业机械臂的人机交互体验 humanoid humanoid robot
10 Corner-Grasp: Multi-Action Grasp Detection and Active Gripper Adaptation for Grasping in Cluttered Environments 提出Corner-Grasp方法，解决复杂环境下多功能夹爪的抓取与自适应问题 manipulation

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

#题目一句话要点标签🔗⭐
11 Building Knowledge from Interactions: An LLM-Based Architecture for Adaptive Tutoring and Social Reasoning 提出基于LLM的交互式架构，用于自适应辅导和社交推理机器人 large language model multimodal
12 Let's move on: Topic Change in Robot-Facilitated Group Discussions 提出基于机器学习和视听特征的机器人引导小组讨论中话题切换预测方法 multimodal ✅
13 Slot-Level Robotic Placement via Visual Imitation from Single Human Video SLeRP：基于单视角人类视频模仿的槽位级机器人放置 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🔗⭐
14 ForestVO: Enhancing Visual Odometry in Forest Environments through ForestGlue ForestVO：通过ForestGlue增强森林环境下的视觉里程计 visual odometry TartanVO feature matching
15 LL-Localizer: A Life-Long Localization System based on Dynamic i-Octree LL-Localizer：基于动态i-Octree的终身定位系统，解决多会话环境下的鲁棒定位问题。 LIO ✅

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

#题目一句话要点标签🔗⭐
16 Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity 提出AURORA-XCon，通过无监督质量多样性优化解决控制问题中的欺骗性难题。 reinforcement learning contrastive learning

⬅️ 返回 cs.RO 首页 · 🏠 返回主页