cs.RO（2026-09-15）

📊 共 32 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (19 🔗4) 支柱三：空间感知与语义 (Perception & Semantics) (5 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱八：物理动画 (Physics-based Animation) (1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱一：机器人控制 (Robot Control) (19 篇)

#题目一句话要点标签🔗⭐
1 Weave: Learning Whole-Body Dexterous Loco-Manipulation from Human-Object Interactions 提出Weave框架以解决人形机器人与物体交互的协调问题 humanoid humanoid robot locomotion ✅
2 WholeBodyWAM: Generalizing Pre-trained World-Action Priors to Humanoid Loco-Manipulation via WBC-Grounded Coordination 提出WholeBodyWAM以解决人形机器人全身协调问题 humanoid whole-body control WBC ✅
3 SAVLA: Symmetry-Aware Vision-Language-Action Models for Robotic Manipulation 提出SAVLA模型以解决机器人操作中的空间能力不足问题 manipulation policy learning flow matching
4 FluxVLA Engine: A One-Stop VLA Engineering Platform for Embodied Intelligence 提出FluxVLA引擎以解决机器人系统工程瓶颈问题 dual-arm reinforcement learning offline reinforcement learning ✅
5 World Models for Embodied Intelligence: From Plausible to Controllable to Actionable 提出世界模型以提升具身智能的行为预测能力 locomotion manipulation world model
6 Fingers as Legs: Learning Self-Supported Locomotion and Manipulation with an Anthropomorphic Hand 提出一种人形手以实现自我支持的移动与操控 quadruped locomotion manipulation
7 Residual Fault Adaptation for Dexterous In-Hand Manipulation Under Runtime Joint Faults 提出残余故障适应方法以解决灵巧手操作中的运行时关节故障问题 manipulation dexterous hand in-hand manipulation
8 ProxiDex: Learning Dynamics-Guided Proximity Policy for Dexterous Manipulation 提出ProxiDex以解决多指灵巧操作中的接触不确定性问题 manipulation dexterous manipulation teleoperation ✅
9 UniDex-ViTac: Learning Unified Visuo-Tactile Dexterous Manipulation Policy from Human Video Data 提出UniDex-ViTac以解决机器人操作中的触觉与视觉融合问题 manipulation dexterous manipulation reinforcement learning
10 SWIM: Vision-Language-Grounded Soft Whole-Body Interactive Manipulation 提出SWIM框架以解决视觉语言驱动的软体机器人交互操控问题 manipulation vision-language-action VLA
11 TEMPO: Learning Temporal Context for Dynamic Robot Manipulation 提出TEMPO以解决动态机器人操作中的时间上下文缺失问题 manipulation vision-language-action VLA
12 XPACE: Joint World and Action Modeling from Heterogeneous Experience 提出XPACE以解决机器人多样经验学习与模拟问题 humanoid humanoid robot world model
13 Optimized Wrench Polytope Analysis for Real-Time Stability Control of Legged Robots in Complex Multi-Contact Configurations 提出优化算法以解决复杂多接触配置下的机器人稳定性问题 legged robot
14 Motion planning in high dimensional spaces hybridizing RRT and HAR via position-direction decoupling 提出一种新方法结合RRT与HAR解决高维空间路径规划问题 motion planning
15 Beyond Gestures: Estimating Full Hand Pose and Contact Forces from Wrist-Worn Pressure Sensor Array 提出基于腕部压力传感器的全手姿态与接触力估计方法 manipulation MAE egocentric
16 Modality-Autoregressive World-Action Models 提出ModAR以解决多模态世界动作模型的融合问题 bi-manual
17 Hamilton-Jacobi Reachability for Hybrid Systems: Unified Goal-Driven Control with Safety Guarantees 扩展哈密顿-雅可比可达性分析以实现混合系统的安全控制 quadruped
18 CAD-Based Relation Learning and Geometric-Symbolic Planning for Robotic Assembly 提出基于CAD的关系学习与几何符号规划以解决机器人装配问题 manipulation
19 The Latent That Never Was: A Forensic Re-run of the CVAE Ablation in Action Chunking Transformer 重新审视条件变分自编码器在动作分块变换器中的作用 manipulation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (5 篇)

#题目一句话要点标签🔗⭐
20 HuMemSLAM: Efficient Human-Inspired Semantic Place Recognition for Robust Visual SLAM 提出HuMemSLAM以解决视觉SLAM中的场所识别问题 visual SLAM geometric consistency
21 TIO-Former: Ultra-Lightweight 6-Directional ToF-Inertial Odometry for Nano-UAVs via a Streaming Causal Transformer 提出TIO-Former以解决纳米无人机的6自由度运动估计问题 optical flow motion estimation ✅
22 Continual Learning for Traversability Prediction with Uncertainty-Aware Adaptation 提出持续学习框架以解决可通行性预测中的灾难性遗忘问题 traversability
23 Seeing What Matters: Visual Cue Guided Video Planning for Generalizable Robot Navigation 提出CueNav以解决机器人导航中的长时间规划问题 scene reconstruction egocentric
24 BRAVE-6D: Benchmark for Robotic Active Vision in 6DOF Pose Estimation 提出BRAVE-6D基准以解决机器人主动视觉中的物体姿态估计问题 3DGS

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
25 The Robot Data Factory 提出机器人数据工厂以解决物理人工智能中的数据生成问题 world model world models embodied AI
26 CorrRisk-WM: Corridor-Conditioned Risk World Modeling for Safety-Critical Trajectory Planning 提出CorrRisk-WM以解决安全关键的轨迹规划问题 world model world models
27 Artificial Intelligence-Enabled Space Robot Operations: Technologies, Challenges and Prospects 提出人工智能驱动的空间机器人操作框架以应对自主性挑战 policy learning foundation model multimodal
28 IL-ACT: Imitation Learning with Adaptive Cartesian Tracking Control for a 30-ton Excavator 提出IL-ACT以解决30吨挖掘机自主控制问题 imitation learning

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

#题目一句话要点标签🔗⭐
29 Intrinsic Robot Rewarding: Reusing VLA Representations for Autonomous Evaluation and Policy Improvement 提出内在机器人奖励机制以提升自主评估与策略改进 vision-language-action VLA
30 Dense to MoE Adaptation for Compact Vision Language Action Policies 提出AdaDE以解决资源受限机器人平台的VLA策略部署问题 vision-language-action VLA

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

#题目一句话要点标签🔗⭐
31 LOTUSim-Energy: A Maritime Simulator for Human-Drone Interaction in Autonomous Offshore Operation \& Maintenance 提出LOTUSim-Energy以解决海上无人机协作维护问题 AMP

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
32 Rethinking Visual Embodiment Dependence in Visuomotor Policies 提出视觉体现依赖结构化方法以提升机器人控制能力 human-to-robot

⬅️ 返回 cs.RO 首页 · 🏠 返回主页