cs.RO（2025-05-12）

📊 共 19 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) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱一：机器人控制 (Robot Control) (13 篇)

#	题目	一句话要点	标签	🔗	⭐
1	HuB: Learning Extreme Humanoid Balance	HuB：学习极端人形机器人平衡控制，提升抗干扰能力	humanoid humanoid robot humanoid control
2	ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning	ReinboT：通过强化学习增强机器人视觉-语言操作能力	manipulation reinforcement learning offline reinforcement learning
3	Intuitive Human-Robot Interfaces Leveraging on Autonomy Features for the Control of Highly-redundant Robots	提出两种人机交互界面，利用自主功能控制高冗余度机器人	locomotion manipulation loco-manipulation
4	Neural Brain: A Neuroscience-inspired Framework for Embodied Agents	提出神经脑框架，用于驱动具身智能体实现类人适应性。	humanoid humanoid robot embodied AI
5	H$^3$DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learning	提出H$^3$DP，通过三层分级扩散策略增强视觉运动策略学习。	manipulation bi-manual policy learning	✅
6	DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies	DexWild：利用人手交互数据提升机器人泛化操作能力	manipulation dexterous manipulation teleoperation
7	GelFusion: Enhancing Robotic Manipulation under Visual Constraints via Visuotactile Fusion	GelFusion：通过视觉触觉融合增强视觉约束下的机器人操作	manipulation policy learning imitation learning
8	Virtual Holonomic Constraints in Motion Planning: Revisiting Feasibility and Limitations	重新审视虚拟完整约束可行性，扩展欠驱动系统运动规划适用范围	motion planning
9	A Framework for Joint Grasp and Motion Planning in Confined Spaces	提出用于狭窄空间内联合抓取与运动规划的基准测试框架	motion planning
10	Beyond Static Perception: Integrating Temporal Context into VLMs for Cloth Folding	BiFold：融合时序上下文的视觉语言模型用于服装折叠	manipulation language conditioned
11	Guiding Data Collection via Factored Scaling Curves	提出基于分解缩放曲线的数据收集方法，提升通用模仿学习策略在操作任务中的泛化能力。	manipulation imitation learning
12	Improving Trajectory Stitching with Flow Models	提出基于流模型的轨迹拼接方法，提升机器人操作中轨迹规划能力	manipulation
13	CHD: Coupled Hierarchical Diffusion for Long-Horizon Tasks	提出耦合分层扩散(CHD)框架，解决长时程任务中规划不连贯问题。	manipulation

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

#	题目	一句话要点	标签	🔗	⭐
14	What Matters for Batch Online Reinforcement Learning in Robotics?	针对机器人批量在线强化学习，提出一种基于Q函数引导和隐式策略提取的有效方法。	reinforcement learning offline RL imitation learning
15	Average-Reward Maximum Entropy Reinforcement Learning for Global Policy in Double Pendulum Tasks	提出基于平均奖励最大熵强化学习的全局策略，用于双摆任务	reinforcement learning
16	Drive Fast, Learn Faster: On-Board RL for High Performance Autonomous Racing	提出基于车载强化学习的自主赛车框架，实现高性能实时控制	reinforcement learning SAC

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

#	题目	一句话要点	标签	🔗	⭐
17	AcoustoBots: A swarm of robots for acoustophoretic multimodal interactions	AcoustoBots：基于机器人集群的声泳多模态交互系统	multimodal
18	Pixel Motion as Universal Representation for Robot Control	LangToMo：提出基于像素运动预测的通用机器人控制框架	vision-language-action	✅

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
19	TPT-Bench: A Large-Scale, Long-Term and Robot-Egocentric Dataset for Benchmarking Target Person Tracking	提出TPT-Bench：用于评估机器人视角下目标人物跟踪的大规模长期数据集	egocentric embodied AI

⬅️ 返回 cs.RO 首页 · 🏠 返回主页