cs.RO（2025-10-10）

📊 共 16 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (13 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱二：RL算法与架构 (RL & Architecture) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (13 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Model-Based Lookahead Reinforcement Learning for in-hand manipulation	提出基于模型的Lookahead强化学习方法，提升灵巧手部操作性能	manipulation in-hand manipulation model predictive control
2	HANDO: Hierarchical Autonomous Navigation and Dexterous Omni-loco-manipulation	HANDO：用于腿式机器人复杂操作的分层自主导航框架	legged robot whole-body control manipulation
3	Glovity: Learning Dexterous Contact-Rich Manipulation via Spatial Wrench Feedback Teleoperation System	Glovity：通过空间力/力矩反馈遥操作系统学习灵巧的接触丰富操作	manipulation dexterous manipulation teleoperation
4	Enhancing Diffusion Policy with Classifier-Free Guidance for Temporal Robotic Tasks	提出基于无分类器引导的扩散策略CFG-DP，提升机器人时序任务的性能。	humanoid humanoid robot diffusion policy
5	Dynamic Quadrupedal Legged and Aerial Locomotion via Structure Repurposing	提出一种基于结构重用的动态四足腿式与空中混合运动机器人	quadruped legged locomotion locomotion
6	PLEXUS Hand: Lightweight Four-Motor Prosthetic Hand Enabling Precision-Lateral Dexterous Manipulation	PLEXUS Hand：轻量化四电机假肢手，实现精确横向灵巧操作	manipulation dexterous manipulation in-hand manipulation
7	iMoWM: Taming Interactive Multi-Modal World Model for Robotic Manipulation	提出iMoWM，利用交互式多模态世界模型提升机器人操作性能	manipulation reinforcement learning imitation learning	✅
8	Guiding Energy-Efficient Locomotion through Impact Mitigation Rewards	通过冲击缓解奖励引导能量高效的机器人运动	locomotion reinforcement learning imitation learning
9	Flow-Opt: Scalable Centralized Multi-Robot Trajectory Optimization with Flow Matching and Differentiable Optimization	Flow-Opt：基于流匹配和可微优化的可扩展集中式多机器人轨迹优化	trajectory optimization flow matching
10	Obstacle Avoidance using Dynamic Movement Primitives and Reinforcement Learning	提出基于DMP和强化学习的障碍物避障方法，仅需单次演示即可快速生成近优轨迹。	motion planning reinforcement learning	✅
11	Real-time Mixed-Integer Quadratic Programming for Driving Behavior-Inspired Speed Bump Optimal Trajectory Planning	提出基于MIQP的速度凸起最优轨迹规划方法，提升自动驾驶车辆舒适性	MPC model predictive control
12	When a Robot is More Capable than a Human: Learning from Constrained Demonstrators	从受限示教者学习：机器人超越人类示教策略的学习方法	sim-to-real imitation learning
13	Parametrized Topological Complexity for a Multi-Robot System with Variable Tasks	针对多机器人变任务系统，提出参数化拓扑复杂度的运动规划方法	motion planning

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

#	题目	一句话要点	标签	🔗	⭐
14	FOGMACHINE -- Leveraging Discrete-Event Simulation and Scene Graphs for Modeling Hierarchical, Interconnected Environments under Partial Observations from Mobile Agents	FOGMACHINE：利用离散事件仿真和场景图建模移动Agent部分观测下的层级互联环境	embodied AI
15	Placeit! A Framework for Learning Robot Object Placement Skills	Placeit!：用于学习机器人物体放置技能的进化计算框架	foundation model

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

#	题目	一句话要点	标签	🔗	⭐
16	Failure Prediction at Runtime for Generative Robot Policies	FIPER：用于生成式机器人策略的运行时故障预测框架	imitation learning flow matching distillation	✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页