cs.RO（2026-02-24）

📊 共 17 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (15) 支柱四：生成式动作 (Generative Motion) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (15 篇)

#	题目	一句话要点	标签	🔗	⭐
1	HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoning	提出HALO，用于具身多模态链式思考推理的统一视觉-语言-动作模型	manipulation vision-language-action VLA
2	ActionReasoning: Robot Action Reasoning in 3D Space with LLM for Robotic Brick Stacking	ActionReasoning：利用LLM进行3D空间机器人动作推理，实现积木堆叠	manipulation embodied AI vision-language-action
3	IG-RFT: An Interaction-Guided RL Framework for VLA Models in Long-Horizon Robotic Manipulation	提出IG-RFT，用于长时程机器人操作中VLA模型的交互引导强化学习微调	manipulation reinforcement learning offline RL
4	Notes-to-Self: Scratchpad Augmented VLAs for Memory Dependent Manipulation Tasks	提出基于语言暂存器的VLA模型，解决记忆依赖操作任务中的长时序问题。	manipulation dexterous manipulation vision-language-action
5	KCFRC: Kinematic Collision-Aware Foothold Reachability Criteria for Legged Locomotion	提出KCFRC算法，解决腿足机器人运动中高效防碰撞足点可达性验证问题	legged robot legged locomotion locomotion
6	Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics	Squint：面向Sim-to-Real机器人的快速视觉强化学习方法	manipulation sim-to-real domain randomization
7	BFA++: Hierarchical Best-Feature-Aware Token Prune for Multi-View Vision Language Action Model	BFA++：面向多视角VLA模型的分层最佳特征感知Token剪枝	manipulation vision-language-action VLA
8	Task-oriented grasping for dexterous robots using postural synergies and reinforcement learning	提出基于姿态协同和强化学习的灵巧机器人任务导向抓取方法	humanoid humanoid robot manipulation
9	Grasp to Act: Dexterous Grasping for Tool Use in Dynamic Settings	Grasp-to-Act：结合物理优化与强化学习，实现动态环境下工具使用的灵巧抓取	manipulation dexterous hand sim-to-real
10	Cooperative-Competitive Team Play of Real-World Craft Robots	提出基于强化学习的协同-竞争机器人团队控制方法，并解决Sim2Real迁移问题	sim-to-real sim2real reinforcement learning
11	Surface-based Manipulation Using Tunable Compliant Porous-Elastic Soft Sensing	提出基于可调多孔弹性软传感的表面操作方法，实现柔顺精确的物体操控。	manipulation
12	GeCo-SRT: Geometry-aware Continual Adaptation for Robotic Cross-Task Sim-to-Real Transfer	提出GeCo-SRT，通过几何感知持续学习实现机器人跨任务Sim-to-Real迁移。	sim-to-real
13	Robot Local Planner: A Periodic Sampling-Based Motion Planner with Minimal Waypoints for Home Environments	提出一种基于周期采样的机器人局部规划器，用于家庭环境下的快速安全操作	manipulation motion planning
14	Efficient Hierarchical Any-Angle Path Planning on Multi-Resolution 3D Grids	提出一种高效的分层多分辨率三维栅格任意角度路径规划方法	trajectory optimization
15	A Robotic Testing Platform for Pipelined Discovery of Resilient Soft Actuators	提出基于机器人测试平台的介电弹性体驱动器寿命优化流水线	quadruped

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
16	Computer-Aided Design of Rational Motions for 4R and 6R Spatial Mechanism Synthesis	提出基于三次四元数Bezier曲线的七点插值方案，用于4R和6R空间机构的计算机辅助设计。	motion synthesis motion generation

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

#	题目	一句话要点	标签	🔗	⭐
17	LST-SLAM: A Stereo Thermal SLAM System for Kilometer-Scale Dynamic Environments	LST-SLAM：用于千米级动态环境的立体热成像SLAM系统	DROID-SLAM geometric consistency motion tracking

⬅️ 返回 cs.RO 首页 · 🏠 返回主页