cs.RO（2026-08-07）

📊 共 22 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 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (13 篇)

#题目一句话要点标签🔗⭐
1 CrossTracer: Cross-Embodiment Navigation via VLA Model Reasoning and Trace Residuals Adapting 提出CrossTracer以解决跨实体导航中的移动约束问题 legged robot traversability egocentric
2 Spatiotemporal Agility: Time-Constrained Reinforcement Learning for Vision-Guided Dynamic Quadrupedal Interception 提出时限约束强化学习以解决动态四足机器人捕球问题 quadruped legged robot locomotion
3 C2Dex: Contact-Consistent Reconstruction and Retargeting for Dexterous Manipulation from Monocular Video 提出C2Dex框架以解决单目视频到灵巧操作的重建与重定向问题 manipulation dexterous hand dexterous manipulation ✅
4 Representation Handoffs for OpenArm-Based Laboratory Mobile Manipulation 提出基于OpenArm的移动操控原型以解决实验室自动化问题 manipulation mobile manipulation embodied AI
5 AtlasVLA: Persistent World-Ego State Modeling for Vision-Language-Action Models 提出AtlasVLA以解决视觉-语言-动作模型的反应性限制问题 manipulation embodied AI vision-language-action
6 TEMPO: Semantic-Action Decoupled RL Post-Training for Vision-Language-Action Models 提出TEMPO框架以解决VLA模型后训练中的不稳定性问题 manipulation reinforcement learning vision-language-action
7 Learning Fault-Tolerant Locomotion with Adaptive Gait Timing 提出深度强化学习方法以解决腿部机器人故障容忍行走问题 quadruped legged robot locomotion
8 Decoupling Intention from Trajectory: A Representational Deduction Framework for World Action Models 提出PILOT框架以解决世界行动模型中的表示纠缠问题 manipulation motion planning world action model
9 A Haptic Robot Finger Designed for Guqin Instrument Playing 设计高精度触觉传感手指以演奏古琴 humanoid humanoid robot dexterous hand
10 AutoIntervene: Calibrated Intervention for Action-Chunking Imitation Learning Policies 提出AutoIntervene以解决动作分块模仿学习中的控制转移问题 manipulation bi-manual bimanual manipulation
11 Real-time Whole-Body Motion Planning for Mobile Manipulators Carrying Arbitrarily Shaped Payloads via Kinematically-Coupled SVSDF 提出实时全身运动规划框架以解决移动操控器运输复杂载荷问题 trajectory optimization motion planning
12 Identifying the Key Biomechanical Features of Movement Adaptation during Exoskeleton-Assisted Locomotion 揭示外骨骼辅助运动中个体适应行为的生物力学特征 locomotion
13 R2S-EGO: Dual-Proxy Refinement for Sparse-Capture Real-to-Sim 提出R2S-EGO以解决稀疏捕获下的真实到模拟问题 Unitree

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
14 Depth-Wise Probing and Pruning of the Planning Token in a Driving Vision-Language-Action Model 提出深度探测与剪枝方法以优化驾驶VLA模型的规划令牌 vision-language-action VLA
15 How Should I Pick a Foundation Model for My Robot? In Favor of a Community Evaluation Framework for Social Robots 提出社区评估框架以优化社交机器人基础模型选择 foundation model
16 Unordered Landmark Visual Navigation 提出无序地标视觉导航以解决图像目标导航问题 embodied AI multimodal
17 When Coordination Becomes a Threat: Communication Attacks in LLM-Controlled Multi-Robot Systems 提出通信攻击模型以解决多机器人系统中的安全隐患 large language model

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

#题目一句话要点标签🔗⭐
18 Is Forward Prediction Enough? Physical State Grounding for JEPA World Models 提出PSG-JEPA以解决物理状态识别不足问题 policy learning world model world models
19 Benchmarking and Reasoning Distillation of Large Language Models for Feedback Controller Design in Complex Dynamical Systems 提出CoDyControlBench以解决复杂动态系统反馈控制设计问题 distillation large language model
20 Cross-View Action Consistency for Camera-Robust Vision-Language-Action Policies 提出跨视角动作一致性方法以解决相机鲁棒性问题 flow matching vision-language-action VLA

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
21 M2-SMap: Memory-Efficient Semantic Mapping with Hierarchical Multi-Model Representation 提出M2-SMap以解决资源受限机器人中的语义映射问题 semantic mapping semantic map
22 LifelongCrossNav: Persistent 3D Semantic Memory for Cross-Floor Multi-Object Navigation 提出LifelongCrossNav以解决跨楼层多目标导航问题 semantic map traversability ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页