cs.RO（2026-04-21）

📊 共 18 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (13 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱八：物理动画 (Physics-based Animation) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (13 篇)

#题目一句话要点标签🔗⭐
1 UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling UniT：面向人-人形机器人策略学习和世界建模的统一物理语言 humanoid policy learning world model
2 Multi-Gait Learning for Humanoid Robots Using Reinforcement Learning with Selective Adversarial Motion Prior 提出选择性对抗运动先验的多步态强化学习方法，提升人形机器人运动能力。 humanoid humanoid robot locomotion
3 GenerativeMPC: VLM-RAG-guided Whole-Body MPC with Virtual Impedance for Bimanual Mobile Manipulation GenerativeMPC：VLM-RAG引导的双臂移动操作机器人全身MPC与虚拟阻抗控制 manipulation mobile manipulation bi-manual
4 Assessing VLM-Driven Semantic-Affordance Inference for Non-Humanoid Robot Morphologies 评估视觉语言模型驱动的非人形机器人语义可供性推理能力 humanoid humanoid robot manipulation
5 VLA Foundry: A Unified Framework for Training Vision-Language-Action Models 提出VLA Foundry以统一训练视觉-语言-动作模型 manipulation vision-language-action VLA ✅
6 Reinforcement Learning Enabled Adaptive Multi-Task Control for Bipedal Soccer Robots 提出基于强化学习的自适应多任务控制框架，用于双足足球机器人。 bipedal biped fall recovery
7 Quadruped Parkour Learning: Sparsely Gated Mixture of Experts with Visual Input 提出基于视觉输入的稀疏门控混合专家模型，提升四足机器人跑酷性能。 quadruped locomotion parkour
8 RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation RoboWM-Bench：用于评估机器人操作中世界模型的基准测试 manipulation world model world models
9 AeroBridge-TTA: Test-Time Adaptive Language-Conditioned Control for UAVs AeroBridge-TTA：面向无人机的测试时自适应语言条件控制 domain randomization PPO language conditioned
10 Learning Hybrid-Control Policies for High-Precision In-Contact Manipulation Under Uncertainty 提出MATCH算法，学习混合控制策略，提升不确定性下高精度接触操作性能 manipulation sim-to-real reinforcement learning
11 Wrench-Aware Admittance Control for Unknown-Payload Manipulation 提出力矩感知的 admittance 控制，用于未知负载的机械臂操作。 manipulation
12 AI-Enabled Image-Based Hybrid Vision/Force Control of Tendon-Driven Aerial Continuum Manipulators 提出AI驱动的图像-力混合控制框架，用于肌腱驱动空中连续体机械臂与环境的自主交互。 manipulation
13 Gated Memory Policy 提出门控记忆策略(GMP)，解决机器人操作任务中非马尔可夫决策问题。 manipulation ✅

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

#题目一句话要点标签🔗⭐
14 Mask World Model: Predicting What Matters for Robust Robot Policy Learning 提出Mask World Model以解决机器人政策学习中的过拟合问题 policy learning world model world models
15 M$^{2}$GRPO: Mamba-based Multi-Agent Group Relative Policy Optimization for Biomimetic Underwater Robots Pursuit 提出基于Mamba的多智能体群组相对策略优化算法，解决仿生水下机器人协同追逐问题 policy learning Mamba

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

#题目一句话要点标签🔗⭐
16 Multimodal embodiment-aware navigation transformer 提出ViLiNT，一种多模态融合的导航Transformer，提升机器人零样本迁移能力和避障鲁棒性。 multimodal zero-shot transfer

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
17 A Gesture-Based Visual Learning Model for Acoustophoretic Interactions using a Swarm of AcoustoBots 提出基于手势的视觉学习模型，实现对AcoustoBot集群声操控的直观控制。 motion tracking multimodal

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

#题目一句话要点标签🔗⭐
18 RoomRecon: High-Quality Textured Room Layout Reconstruction on Mobile Devices RoomRecon：移动端高质量纹理房间布局重建 3D reconstruction scene understanding

⬅️ 返回 cs.RO 首页 · 🏠 返回主页