cs.RO（2024-12-16）

📊 共 10 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (7) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱一：机器人控制 (Robot Control) (7 篇)

#题目一句话要点标签🔗⭐
1 Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning 提出Emma-X以解决机器人控制任务泛化问题 manipulation reinforcement learning scene understanding
2 Robust Contact-rich Manipulation through Implicit Motor Adaptation 提出隐式运动适应方法，提升接触丰富操作中对不确定参数的鲁棒性 manipulation domain randomization implicit representation
3 Efficient Avoidance of Ellipsoidal Obstacles with Model Predictive Control for Mobile Robots and Vehicles 提出一种基于模型预测控制的移动机器人椭球障碍物高效避障方法 MPC model predictive control motion planning
4 Visual-Based Forklift Learning System Enabling Zero-Shot Sim2Real Without Real-World Data 提出基于视觉的叉车学习系统，实现零样本Sim2Real迁移，无需真实世界数据。 sim2real reinforcement learning deep reinforcement learning
5 Visual IRL for Human-Like Robotic Manipulation 提出Visual IRL，使协作机器人在操作任务中学习并执行类人动作。 manipulation reinforcement learning inverse reinforcement learning
6 What Matters in Learning A Zero-Shot Sim-to-Real RL Policy for Quadrotor Control? A Comprehensive Study SimpleFlight：针对四旋翼无人机零样本Sim-to-Real强化学习控制策略的关键因素研究 sim-to-real PPO
7 Equivariant Action Sampling for Reinforcement Learning and Planning 提出等变动作采样方法，提升强化学习和规划中对称性任务的决策效率 manipulation reinforcement learning

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

#题目一句话要点标签🔗⭐
8 Demonstrating Data-to-Knowledge Pipelines for Connecting Production Sites in the World Wide Lab 提出基于数字孪生网络的Data-to-Knowledge流水线，连接多组织生产站点，提升机器人控制效率。 foundation model
9 ON as ALC: Active Loop Closing Object Goal Navigation 提出ALC-ON，利用目标导航加速长距离主动闭环，解决地图累积误差问题。 embodied AI

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

#题目一句话要点标签🔗⭐
10 UAV-based path planning for efficient localization of non-uniformly distributed weeds using prior knowledge: A reinforcement-learning approach 提出基于深度强化学习的无人机路径规划方法，用于高效定位农田中非均匀分布的杂草。 reinforcement learning deep reinforcement learning

⬅️ 返回 cs.RO 首页 · 🏠 返回主页