cs.RO（2026-08-26）

📊 共 23 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (20 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (20 篇)

#题目一句话要点标签🔗⭐
1 PRISM: Projection-Integrated Sampling-Based MPC with Bayesian Cost Tuning for Bimanual Manipulation 提出PRISM框架以解决双臂操控中的运动协调问题 manipulation bi-manual dual-arm
2 GaussianDream++: Efficient 3D Gaussian World Modeling for Robotic Manipulation 提出GaussianDream++以提升机器人操作中的3D建模效率 manipulation world model world models
3 MA-VLA: Multi-Arm Vision-Language-Action Model for Collaboration and Compositional Generalization 提出MA-VLA以解决多臂协作中的行为分配问题 manipulation dual-arm vision-language-action ✅
4 LAC: Linear and Angular Compliance for Humanoid Whole-body Control 提出LAC以解决人形机器人全身控制中的线性与角度柔顺性问题 humanoid whole-body control manipulation
5 One Policy, Many Embodiments: Unified Camera-Centric Action Geometry Pre-training for Heterogeneous Embodied Manipulation 提出UCAG-P以解决异构体态操控中的数据不匹配问题 humanoid manipulation human-to-robot
6 RA-VLA: Retrieval-Augmented VLA for Test-Time Adaptation 提出RA-VLA以解决机器人适应新任务分布的脆弱性问题 manipulation imitation learning vision-language-action
7 $R^3$: Training Robots to Reason in Natural Language via Reinforcement Learning 提出$R^3$以解决机器人自然语言推理问题 manipulation bi-manual reinforcement learning ✅
8 A Tendon-Driven Five-Fingered Hand with Distributed Tactile Perception for Dexterous Manipulation 提出一种新型腱驱动五指手以解决灵巧操作中的触觉感知问题 manipulation dexterous manipulation
9 Leveraging Inter-object Affordances for Efficient Planning in Contact-rich Tasks 提出统一任务与运动规划方法以解决接触丰富任务中的规划效率问题 motion planning affordance TAMP
10 Anytime Global Tensor Motion Planning 提出全局张量运动规划以解决高效路径规划问题 manipulation trajectory optimization motion planning
11 VISTA: Visually Inferred Spatial ConTact Attention for Contact-Rich Manipulation 提出VISTA-Policy以解决接触丰富操作中的反馈不足问题 manipulation imitation learning diffusion policy
12 LM-X: Explainable Action Modeling with Progress, Event, and Uncertainty Prediction for Generalist Robot Manipulation 提出LM-X以解决通用机器人操控中的可解释性与可靠性问题 manipulation VLA
13 Advantage-Driven Explicit Memory for Social Navigation 提出非参数记忆以提升社交导航中的机器人决策能力 sim-to-real PPO imitation learning
14 Towards safe and optimal flight: Viability Kernel MPC for Fully Actuated Multirotor 提出基于可行性核的MPC方法以解决多旋翼飞行安全问题 MPC model predictive control
15 RAEM: Robust Autonomous Exploration for Multi-Floor Environments with a Quadruped Robot 提出RAEM框架以解决多层环境中四足机器人自主探索问题 quadruped traversability
16 Fast Generative Grasping via Lie Group-Constrained MeanFlow 提出基于李群约束的MeanFlow方法以实现快速生成抓取 manipulation flow matching multimodal
17 Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization 提出Zero-WAM以解决机器人学习中的零-shot跨任务泛化问题 manipulation large language model
18 TacForcing: Streaming Action Generation with Execution-Time Tactile Feedback 提出TacForcing以解决接触丰富操作中的时效性反馈问题 manipulation vision-language-action
19 EgoNav: Bridging Learned Waypoints and Geometry-Aware Local Control for Robust Indoor Navigation 提出EgoNav以解决室内导航中的几何约束问题 humanoid humanoid robot
20 SUPER ODOMETRY 2.0: Resilient Odometry via Hierarchical Adaptation 提出超级里程计以解决复杂环境下的鲁棒性问题 legged robot

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
21 ConfAL-WM: Confidence-Guided Active Learning for Action-Conditioned World Models 提出ConfAL-WM框架以提升行动条件下世界模型的学习效率 world model world models spatiotemporal

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

#题目一句话要点标签🔗⭐
22 A Taxonomy of Construction Task Activities for Robot Workers 提出TARCAT以解决建筑机器人任务活动分类问题 vision-language-action ✅

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

#题目一句话要点标签🔗⭐
23 When Obstacles Bend: Modeling Vegetation Deformation in the context of Field Robotics 提出基于植物机械特性建模的障碍物变形方法以解决机器人导航问题 traversability

⬅️ 返回 cs.RO 首页 · 🏠 返回主页