cs.RO（2025-05-14）

📊 共 25 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (17 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗3) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (17 篇)

#题目一句话要点标签🔗⭐
1 VTLA: Vision-Tactile-Language-Action Model with Preference Learning for Insertion Manipulation 提出VTLA模型，通过视觉-触觉-语言融合和偏好学习，提升机器人插入操作的鲁棒性。 manipulation sim2real imitation learning
2 Real2Render2Real: Scaling Robot Data Without Dynamics Simulation or Robot Hardware 提出Real2Render2Real以解决机器人数据收集成本高的问题 teleoperation imitation learning 3D gaussian splatting
3 Latent Theory of Mind: A Decentralized Diffusion Architecture for Cooperative Manipulation 提出LatentToM，一种用于协作操作的去中心化扩散架构。 manipulation bi-manual diffusion policy ✅
4 RT-Cache: Training-Free Retrieval for Real-Time Manipulation RT-Cache：用于实时操作的免训练检索方法 manipulation multimodal ✅
5 Exploring Pose-Guided Imitation Learning for Robotic Precise Insertion 提出基于姿态引导的模仿学习方法，用于机器人高精度插入任务 manipulation imitation learning diffusion policy ✅
6 Neural Network Aided Kalman Filtering with Model Predictive Control Enables Robot-Assisted Drone Recovery on a Wavy Surface 提出基于神经网络辅助卡尔曼滤波与模型预测控制的水面无人机回收方案 model predictive control motion planning
7 Imitation Learning for Adaptive Control of a Virtual Soft Exoglove 提出基于模仿学习的虚拟软外骨骼自适应控制方法，用于补偿手部运动障碍。 manipulation reinforcement learning imitation learning
8 DataMIL: Selecting Data for Robot Imitation Learning with Datamodels DataMIL：基于数据模型的机器人模仿学习数据选择框架 manipulation imitation learning
9 ManipBench: Benchmarking Vision-Language Models for Low-Level Robot Manipulation 提出ManipBench：用于评估视觉-语言模型在机器人底层操作任务中的性能 manipulation
10 Decentralized Nonlinear Model Predictive Control-Based Flock Navigation with Real-Time Obstacle Avoidance in Unknown Obstructed Environments 提出基于分布式NMPC的集群导航方法，实现未知环境下的实时避障 model predictive control
11 Improved Corner Cutting Constraints for Mixed-Integer Motion Planning of a Differential Drive Micro-Mobility Vehicle 针对差速驱动微型移动平台，提出改进的转角切割约束的混合整数运动规划方法 motion planning
12 Learning Rock Pushability on Rough Planetary Terrain 提出一种基于力反馈的岩石可推性学习方法，用于行星表面机器人导航。 manipulation affordance
13 Unfettered Forceful Skill Acquisition with Physical Reasoning and Coordinate Frame Labeling 利用物理推理和坐标系标注，实现VLM驱动的通用力控技能学习 manipulation affordance ✅
14 aUToPath: Unified Planning and Control for Autonomous Vehicles in Urban Environments Using Hybrid Lattice and Free-Space Search aUToPath：融合混合栅格与自由空间搜索的城市自动驾驶统一规划与控制框架 MPC model predictive control
15 Strategic Jenga Play via Graph Based Dynamics Modeling 提出基于图结构的动力学建模方法，用于Jenga游戏中积木的策略性操作。 manipulation model predictive control
16 FoldNet: Learning Generalizable Closed-Loop Policy for Garment Folding via Keypoint-Driven Asset and Demonstration Synthesis FoldNet：通过关键点驱动的资产和演示合成学习服装折叠的通用闭环策略 manipulation imitation learning
17 Grasp EveryThing (GET): 1-DoF, 3-Fingered Gripper with Tactile Sensing for Robust Grasping 提出GET：一种具有触觉传感的单自由度三指夹爪，用于稳健抓取 teleoperation

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
18 Deploying Foundation Model-Enabled Air and Ground Robots in the Field: Challenges and Opportunities SPINE框架：在非结构化环境中部署基于大语言模型的空地机器人 distillation foundation model
19 EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models EWMBench：提出具身世界模型评估基准，关注场景、运动和语义质量 world model physically plausible embodied AI ✅
20 Distilling Realizable Students from Unrealizable Teachers 提出CritiQ_ReTRy，解决特权信息下学生策略从不可实现教师策略蒸馏的问题 reinforcement learning imitation learning teacher-student ✅
21 Mini Diffuser: Fast Multi-task Diffusion Policy Training Using Two-level Mini-batches Mini Diffuser：利用双层Mini-batch加速多任务扩散策略训练，显著降低时间和内存需求。 diffusion policy multimodal
22 Trends in Motion Prediction Toward Deployable and Generalizable Autonomy: A Revisit and Perspectives 针对可部署和泛化的自主系统，重新审视并展望运动预测的趋势 world model human motion ✅
23 Learning Long-Context Diffusion Policies via Past-Token Prediction 提出Past-Token Prediction，解决长序列机器人任务中Diffusion策略的上下文依赖问题。 imitation learning diffusion policy

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

#题目一句话要点标签🔗⭐
24 Air-Ground Collaboration for Language-Specified Missions in Unknown Environments 提出基于LLM的空地协同系统，实现未知环境下自然语言任务规划与执行 semantic mapping semantic map large language model

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

#题目一句话要点标签🔗⭐
25 Bridging Human Oversight and Black-box Driver Assistance: Vision-Language Models for Predictive Alerting in Lane Keeping Assist Systems LKAlert：利用视觉-语言模型实现车道保持辅助系统中的预测性预警 multimodal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页