cs.RO（2026-01-30）

📊 共 13 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (9) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (9 篇)

#题目一句话要点标签🔗⭐
1 Robust and Generalized Humanoid Motion Tracking 提出基于动态条件命令聚合的人形机器人运动跟踪方法，实现零样本迁移和鲁棒的sim2real迁移。 humanoid humanoid robot whole-body control
2 RoboStriker: Hierarchical Decision-Making for Autonomous Humanoid Boxing RoboStriker：提出一种分层决策框架，实现自主人形机器人拳击 humanoid humanoid robot humanoid control
3 Temporally Coherent Imitation Learning via Latent Action Flow Matching for Robotic Manipulation 提出LG-Flow Policy，通过潜在动作流匹配实现机器人操作任务的时序一致模仿学习。 manipulation imitation learning flow matching
4 Learning Geometrically-Grounded 3D Visual Representations for View-Generalizable Robotic Manipulation 提出基于几何感知的3D视觉表征学习框架，提升机器人操作的视角泛化能力 manipulation policy learning distillation
5 End-to-end Optimization of Belief and Policy Learning in Shared Autonomy Paradigms BRACE：端到端优化信念与策略学习，提升共享自主系统人机协作性能 manipulation policy learning
6 FlyAware: Inertia-Aware Aerial Manipulation via Vision-Based Estimation and Post-Grasp Adaptation FlyAware：基于视觉估计和后抓取自适应的惯性感知空中操作 manipulation
7 Robust Rigid Body Assembly via Contact-Implicit Optimal Control with Exact Second-Order Derivatives 提出基于接触隐式最优控制的刚体装配方法，提升规划效率与鲁棒性 sim-to-real trajectory optimization reinforcement learning
8 Postural Virtual Fixtures for Ergonomic Physical Interactions with Supernumerary Robotic Bodies 提出基于姿态虚拟夹具的控制框架，提升超 संख्या机器人协同作业的人体工学性 manipulation loco-manipulation
9 MOSAIC: Modular Scalable Autonomy for Intelligent Coordination of Heterogeneous Robotic Teams 提出MOSAIC框架，实现异构机器人团队在复杂环境下的自主科考与高效协同 teleoperation

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

#题目一句话要点标签🔗⭐
10 Self-Imitated Diffusion Policy for Efficient and Robust Visual Navigation 提出自模仿扩散策略SIDP，提升视觉导航效率与鲁棒性 imitation learning diffusion policy curriculum learning
11 MTDrive: Multi-turn Interactive Reinforcement Learning for Autonomous Driving MTDrive：用于自动驾驶的多轮交互式强化学习 reinforcement learning large language model
12 Adapting Reinforcement Learning for Path Planning in Constrained Parking Scenarios 提出基于深度强化学习的路径规划框架，解决约束泊车场景下的实时规划问题。 reinforcement learning deep reinforcement learning DRL ✅

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

#题目一句话要点标签🔗⭐
13 CARE: Multi-Task Pretraining for Latent Continuous Action Representation in Robot Control CARE：用于机器人控制中潜在连续动作表示的多任务预训练 vision-language-action VLA

⬅️ 返回 cs.RO 首页 · 🏠 返回主页