cs.RO（2026-05-18）

📊 共 19 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (12 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱三：空间感知与语义 (Perception & Semantics) (2)

🔬 支柱一：机器人控制 (Robot Control) (12 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Dexora: Open-source VLA for High-DoF Bimanual Dexterity	Dexora：首个开源双臂双手机器人高自由度灵巧操作的VLA系统	manipulation dexterous hand bi-manual
2	Unified Walking, Running, and Recovery for Humanoids via State-Dependent Adversarial Motion Priors	提出统一强化学习框架以实现人形机器人行走、奔跑与恢复	humanoid humanoid robot locomotion
3	TacSE3: Equivariant SE(3) Motion Estimation from Low-Texture Visuotactile Images for In-Gripper Tracking and Compensation	TacSE3：基于低纹理触觉图像的SE(3)等变运动估计，用于夹持器内跟踪与补偿	motion tracking manipulation in-hand manipulation
4	Key-Gram: Extensible World Knowledge for Embodied Manipulation	提出Key-Gram框架以解决语言知识与视觉推理耦合问题	manipulation dual-arm vision-language-action
5	CosFly-Track: A Large-Scale Multi-Modal Dataset for UAV Visual Tracking via Multi-Constraint Trajectory Optimization	CosFly-Track：提出大规模无人机视觉跟踪多模态数据集，通过多约束轨迹优化实现。	trajectory optimization metric depth VLN	✅
6	A Dexterous and Compliant Gripper With Soft Hydraulic Actuation for Microgravity Manipulation	提出DexCoHand：一种用于微重力环境灵巧操作的柔性液压机械手	manipulation dexterous manipulation
7	ManiSoft: Towards Vision-Language Manipulation for Soft Continuum Robotics	ManiSoft：面向软体连续机器人的视觉-语言操控基准	manipulation reinforcement learning	✅
8	DexHoldem: Playing Texas Hold'em with Dexterous Embodied System	DexHoldem：构建德州扑克灵巧操作的具身系统基准	manipulation dexterous hand dexterous manipulation	✅
9	Dynamic robotic cloth folding with efficient Koopman operator-based model predictive control	提出基于Koopman算子的模型预测控制，实现高效动态机器人叠衣	model predictive control
10	Data-Driven Dynamic Modeling of a Tendon-Actuated Continuum Robot	针对腱驱动连续体机器人，提出基于数据的动态建模方法，并应用于模型预测控制。	model predictive control
11	Virtues of Ordered Chaos: Planning with Topple Actions in Tabletop Stack Rearrangement	提出基于Topple动作的规划方法，加速桌面物体堆叠重排任务	manipulation
12	Optimal Knock-Pick Planning for Tightly Packed Tabletop Blocks With Parallel Grippers	提出基于方向性敲击的优化拣选规划算法，解决紧密排列桌面块的并行夹爪操作问题	manipulation

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

#	题目	一句话要点	标签	🔗	⭐
13	WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform	WorldArena 2.0：扩展具身世界模型基准测试，覆盖模态、功能和平台	world model world models multimodal
14	Robo-Cortex: A Self-Evolving Embodied Agent via Dual-Grain Cognitive Memory and Autonomous Knowledge Induction	Robo-Cortex：通过双粒度认知记忆和自主知识归纳实现自进化具身智能体	world model world models multimodal
15	Transfer Learning for Customized Car Racing Environments	利用迁移学习加速定制赛车环境中的强化学习智能体训练	reinforcement learning deep reinforcement learning zero-shot transfer

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

#	题目	一句话要点	标签	🔗	⭐
16	On Improving Multimodal Pedestrian Trajectory Prediction with CVAE: A Study on Benchmark and Robot Data	基于CVAE的Social-STGCNN用于提升多模态行人轨迹预测，适用于基准数据集和机器人数据。	multimodal
17	REBAR: Reference Ethical Benchmark for Autonomy Readiness	提出REBAR框架以解决自主系统伦理评估问题	embodied AI large language model

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

#	题目	一句话要点	标签	🔗	⭐
18	RGB-only Active 3D Scene Graph Generation for Indoor Mobile Robots	提出一种仅使用RGB图像的主动3D场景图生成方法，用于室内移动机器人。	3D reconstruction
19	FUSE: A Framework for Unified State Estimation in Robotic SLAM Systems	FUSE：用于机器人SLAM系统中统一状态估计的框架	LIO

⬅️ 返回 cs.RO 首页 · 🏠 返回主页