cs.RO（2024-08-26）

📊 共 10 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (5) 支柱一：机器人控制 (Robot Control) (4) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Optimizing TD3 for 7-DOF Robotic Arm Grasping: Overcoming Suboptimality with Exploration-Enhanced Contrastive Learning	提出EECL模块，优化TD3算法，提升7自由度机械臂抓取策略。	reinforcement learning TD3 contrastive learning
2	Robot Navigation with Entity-Based Collision Avoidance using Deep Reinforcement Learning	提出基于实体类型的深度强化学习机器人导航方法，提升动态环境下的避障安全性。	reinforcement learning deep reinforcement learning
3	Bridging the gap between Learning-to-plan, Motion Primitives and Safe Reinforcement Learning	结合学习规划、运动原语和安全强化学习，解决机器人复杂动力学约束下的轨迹规划问题	reinforcement learning reactive motion
4	Equivariant Reinforcement Learning under Partial Observability	提出部分可观测下的等变强化学习，提升机器人学习的样本效率。	reinforcement learning
5	A Survey on Reinforcement Learning Applications in SLAM	综述性研究：探索强化学习在SLAM中的应用与进展	reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
6	Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning	提出去噪世界模型学习，实现人形机器人在复杂地形的稳健运动控制	humanoid humanoid robot humanoid locomotion
7	Model Predictive Parkour Control of a Monoped Hopper in Dynamically Changing Environments	提出基于模型预测控制的单足跳跃机器人跑酷控制方法，适应动态变化环境	legged robot parkour motion planning
8	Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learning	Re-Mix：通过优化数据混合比例提升大规模模仿学习性能	manipulation imitation learning foundation model
9	CHIGLU: A Modular Hardware for Stepper Motorized Quadruped Robot $\unicode{x2014}$ Design, Analysis, Fabrication, and Validation	设计模块化硬件CHIGLU，用于步进电机驱动的四足机器人控制	quadruped

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

#	题目	一句话要点	标签	🔗	⭐
10	FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry	FAST-LIVO2：一种快速、直接的激光雷达-惯性-视觉里程计，适用于实时机器人应用。	visual odometry NeRF

⬅️ 返回 cs.RO 首页 · 🏠 返回主页