cs.RO（2024-07-26）

📊 共 8 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (6) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱一：机器人控制 (Robot Control) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	PANDORA: The Open-Source, Structurally Elastic Humanoid Robot	PANDORA：一种基于3D打印柔性材料的开源结构弹性人形机器人	humanoid humanoid robot whole-body control
2	Learning a Shape-Conditioned Agent for Purely Tactile In-Hand Manipulation of Various Objects	提出基于触觉反馈和形状信息的机械手灵巧操作学习框架	manipulation in-hand manipulation reinforcement learning
3	PP-TIL: Personalized Planning for Autonomous Driving with Instance-based Transfer Imitation Learning	PP-TIL：基于实例迁移模仿学习的自动驾驶个性化规划	motion planning reinforcement learning imitation learning
4	HRP: Human Affordances for Robotic Pre-Training	提出基于人类行为Affordance的机器人预训练方法，提升机器人泛化能力	dexterous hand affordance
5	Lessons from Learning to Spin "Pens"	提出一种基于强化学习和真实数据微调的笔状物原地操作学习方法	manipulation in-hand manipulation reinforcement learning
6	Real-time Uncertainty-Aware Motion Planning for Magnetic-based Navigation	提出基于磁导航的实时不确定性感知运动规划算法，提升GPS拒止环境下的导航精度。	motion planning

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

#	题目	一句话要点	标签	🔗	⭐
7	ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments	提出ReALFRED，一个基于真实场景的具身智能指令跟随基准	instruction following

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

#	题目	一句话要点	标签	🔗	⭐
8	FH-DRL: Exponential-Hyperbolic Frontier Heuristics with DRL for accelerated Exploration in Unknown Environments	FH-DRL：结合指数双曲前沿启发式与深度强化学习，加速未知环境探索	DRL TD3

⬅️ 返回 cs.RO 首页 · 🏠 返回主页