cs.RO（2025-03-13）

📊 共 22 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (15 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1) 支柱四：生成式动作 (Generative Motion) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (15 篇)

#题目一句话要点标签🔗⭐
1 AhaRobot: A Low-Cost Open-Source Bimanual Mobile Manipulator for Embodied AI AhaRobot：一种低成本开源双臂移动操作机器人，用于具身智能研究。 manipulation mobile manipulation bi-manual
2 KUDA: Keypoints to Unify Dynamics Learning and Visual Prompting for Open-Vocabulary Robotic Manipulation KUDA：融合动力学学习与视觉提示，实现开放词汇机器人操作 manipulation open-vocabulary open vocabulary
3 Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic Manipulation 提出KStar Diffuser，解决双臂机器人操作中物理结构约束和运动学一致性问题 manipulation bi-manual imitation learning
4 NuExo: A Wearable Exoskeleton Covering all Upper Limb ROM for Outdoor Data Collection and Teleoperation of Humanoid Robots NuExo：用于户外数据采集和人形机器人遥操作的全上肢外骨骼系统 humanoid humanoid robot teleoperation
5 An Real-Sim-Real (RSR) Loop Framework for Generalizable Robotic Policy Transfer with Differentiable Simulation 提出基于可微仿真的Real-Sim-Real循环框架，提升机器人策略迁移的泛化性 manipulation sim-to-real reinforcement learning
6 Safe Continual Domain Adaptation after Sim2Real Transfer of Reinforcement Learning Policies in Robotics 提出基于安全强化学习的持续域适应方法，解决机器人Sim2Real迁移后的策略优化问题 sim2real domain randomization reinforcement learning ✅
7 Learning Robotic Policy with Imagined Transition: Mitigating the Trade-off between Robustness and Optimality 提出基于想象转换的强化学习框架，提升四足机器人运动策略的鲁棒性和最优性 quadruped locomotion sim2real
8 Mapless Collision-Free Flight via MPC using Dual KD-Trees in Cluttered Environments 提出基于双KD树和MPC的无地图碰撞避免飞行方法，提升复杂环境下的四旋翼飞行速度和安全性。 MPC model predictive control imitation learning ✅
9 ES-Parkour: Advanced Robot Parkour with Bio-inspired Event Camera and Spiking Neural Network 提出基于仿生事件相机和脉冲神经网络的四足机器人跑酷方法 quadruped parkour reinforcement learning
10 IMPACT: Intelligent Motion Planning with Acceptable Contact Trajectories via Vision-Language Models IMPACT：利用视觉-语言模型进行可接受接触轨迹的智能运动规划 motion planning contact-aware ✅
11 Fusion of Indirect Methods and Iterative Learning for Persistent Velocity Trajectory Optimization of a Sustainably Powered Autonomous Surface Vessel 提出结合间接方法与迭代学习的优化策略以提升自主水面船的速度轨迹 model predictive control trajectory optimization
12 Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback 提出TrajHF框架，通过人类反馈强化学习学习个性化驾驶风格。 motion planning reinforcement learning imitation learning
13 Transferring Kinesthetic Demonstrations across Diverse Objects for Manipulation Planning 提出基于运动传递框架的操纵规划方法，实现跨异构物体的动作迁移 manipulation
14 Compliant Control of Quadruped Robots for Assistive Load Carrying 提出基于顺应控制的四足机器人负载辅助方法，提升负载运输性能并保障安全。 quadruped
15 CODEI: Resource-Efficient Task-Driven Co-Design of Perception and Decision Making for Mobile Robots Applied to Autonomous Vehicles CODEI：面向自动驾驶车辆的移动机器人感知与决策协同设计框架 motion planning

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
16 LUMOS: Language-Conditioned Imitation Learning with World Models LUMOS：基于世界模型的语言条件模仿学习框架，实现机器人零样本迁移 imitation learning world model language conditioned
17 SCOOP: A Framework for Proactive Collaboration and Social Continual Learning through Natural Language Interaction andCausal Reasoning SCOOP框架通过自然语言交互和因果推理，实现主动协作和社会持续学习。 world model large language model multimodal
18 Enhanced View Planning for Robotic Harvesting: Tackling Occlusions with Imitation Learning 提出基于模仿学习的视角规划方法，解决机器人采摘中的遮挡问题 imitation learning

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

#题目一句话要点标签🔗⭐
19 GS-SDF: LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and Reconstruction GS-SDF：利用激光雷达增强的高斯溅射和神经SDF，实现几何一致的渲染与重建 gaussian splatting splatting ✅
20 Stratified Topological Autonomy for Long-Range Coordination (STALC) 提出STALC：一种用于长程协同的多机器人分层拓扑自主规划方法 traversability

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
21 RMG: Real-Time Expressive Motion Generation with Self-collision Avoidance for 6-DOF Companion Robotic Arms 提出RMG，用于6-DOF协作机械臂的实时、具象、自碰撞避免运动生成。 motion generation

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

#题目一句话要点标签🔗⭐
22 SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigation SmartWay：增强航点预测与回溯的零样本视觉语言导航方法 VLN large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页