cs.RO（2023-10-03）

📊 共 15 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (9 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (3 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (9 篇)

#题目一句话要点标签🔗⭐
1 STAMP: Differentiable Task and Motion Planning via Stein Variational Gradient Descent 提出STAMP以解决任务与运动规划中的效率问题 motion planning task and motion planning TAMP
2 Generalizable Long-Horizon Manipulations with Large Language Models 提出利用大型语言模型生成任务条件以解决长时间操作问题 manipulation large language model ✅
3 RETRO: Reactive Trajectory Optimization for Real-Time Robot Motion Planning in Dynamic Environments 提出RETRO以解决动态环境下机器人运动规划问题 manipulation trajectory optimization motion planning
4 A Vision-Based Tactile Sensing System for Multimodal Contact Information Perception via Neural Network 提出基于视觉的触觉传感系统以简化多模态接触信息感知 dexterous hand multimodal
5 What do we learn from a large-scale study of pre-trained visual representations in sim and real environments? 提出大规模研究以优化预训练视觉表征在真实环境中的应用 manipulation policy learning zero-shot transfer
6 How Physics and Background Attributes Impact Video Transformers in Robotic Manipulation: A Case Study on Planar Pushing 提出视频变换器以解决机器人操控中的轨迹预测问题 manipulation
7 Learning and reusing primitive behaviours to improve Hindsight Experience Replay sample efficiency 提出利用原始行为提升Hindsight Experience Replay样本效率的方法 manipulation reinforcement learning ✅
8 Learning Diverse Skills for Local Navigation under Multi-constraint Optimality 提出多约束最优性下的多样化技能学习方法以解决导航问题 quadruped
9 Spherical Rolling Robots Design, Modeling, and Control: A Systematic Literature Review 系统性文献综述揭示球形机器人设计与控制的新方向 locomotion

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
10 Predicting Future Spatiotemporal Occupancy Grids with Semantics for Autonomous Driving 提出基于语义的环境预测框架以解决自动驾驶中的占用网格预测问题 occupancy grid spatiotemporal
11 A 3D Mixed Reality Interface for Human-Robot Teaming 提出混合现实人机协作系统以解决机器人定位与控制问题 visual SLAM ✅
12 Automatic Data Processing for Space Robotics Machine Learning 提出自动数据处理管道以解决火星探测器地形分类问题 traversability

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
13 Event-Enhanced Multi-Modal Spiking Neural Network for Dynamic Obstacle Avoidance 提出事件增强多模态脉冲神经网络以解决动态障碍物规避问题 reinforcement learning deep reinforcement learning DRL
14 Differentially Encoded Observation Spaces for Perceptive Reinforcement Learning 提出差分编码观察空间以解决感知强化学习的内存挑战 reinforcement learning deep reinforcement learning DRL

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

#题目一句话要点标签🔗⭐
15 Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving 提出多模态LLM架构以提升自主驾驶的可解释性与决策能力 large language model multimodal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页