cs.RO（2026-04-24）

📊 共 12 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (8 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱一：机器人控制 (Robot Control) (8 篇)

#题目一句话要点标签🔗⭐
1 False Feasibility in Variable Impedance MPC for Legged Locomotion 揭示变阻抗MPC在腿足运动中存在的虚假可行性问题，并提出解决方案 legged locomotion locomotion actuator dynamics
2 CodeGraphVLP: Code-as-Planner Meets Semantic-Graph State for Non-Markovian Vision-Language-Action Models 提出CodeGraphVLP以解决非马尔可夫长时序任务的视觉语言行动问题 manipulation vision-language-action VLA
3 GazeVLA: Learning Human Intention for Robotic Manipulation GazeVLA：学习人类意图以用于机器人操作 manipulation egocentric foundation model
4 ATRS: Adaptive Trajectory Re-splitting via a Shared Neural Policy for Parallel Optimization ATRS：基于共享神经策略的自适应轨迹重分割，用于并行优化。 sim-to-real trajectory optimization motion planning
5 QDTraj: Exploration of Diverse Trajectory Primitives for Articulated Objects Robotic Manipulation QDTraj：探索多样化轨迹基元，用于操作铰接物体 manipulation
6 LeHome: A Simulation Environment for Deformable Object Manipulation in Household Scenarios LeHome：面向家庭场景下可变形物体操作的综合模拟环境 manipulation
7 GCImOpt: Learning efficient goal-conditioned policies by imitating optimal trajectories GCImOpt：通过模仿优化轨迹学习高效的目标条件策略 trajectory optimization imitation learning ✅
8 Learning-augmented robotic automation for real-world manufacturing 提出Learning-Augmented Robotic Automation，解决实际生产中机器人自动化难题 manipulation

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

#题目一句话要点标签🔗⭐
9 RedVLA: Physical Red Teaming for Vision-Language-Action Models RedVLA：为视觉-语言-动作模型构建物理红队测试框架，保障部署安全 vision-language-action VLA
10 An LLM-Driven Closed-Loop Autonomous Learning Framework for Robots Facing Uncovered Tasks in Open Environments 提出基于LLM的闭环自主学习框架，解决机器人开放环境下的未知任务处理问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
11 dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model dWorldEval：通过离散扩散世界模型实现可扩展的机器人策略评估 world model world models spatiotemporal
12 Learning Control Policies to Provably Satisfy Hard Affine Constraints for Black-Box Hybrid Dynamical Systems 提出强化学习策略以满足黑箱混合动态系统的严格约束 reinforcement learning reward shaping

⬅️ 返回 cs.RO 首页 · 🏠 返回主页