cs.RO（2024-03-04）

📊 共 13 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (8) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (8 篇)

#题目一句话要点标签🔗⭐
1 ZSL-RPPO: Zero-Shot Learning for Quadrupedal Locomotion in Challenging Terrains using Recurrent Proximal Policy Optimization 提出ZSL-RPPO以解决四足机器人在复杂地形中的零样本学习问题 quadruped locomotion domain randomization
2 Demonstrating a Robust Walking Algorithm for Underactuated Bipedal Robots in Non-flat, Non-stationary Environments 提出一种新算法以提升非平坦环境下的双足机器人行走能力 bipedal biped MPC
3 An Efficient Model-Based Approach on Learning Agile Motor Skills without Reinforcement 提出高效模型驱动方法以解决强化学习样本效率低下问题 quadruped locomotion sim-to-real
4 Twisting Lids Off with Two Hands 提出双手扭开瓶盖的深度强化学习方法以解决机器人操控挑战 manipulation bi-manual sim-to-real
5 Skater: A Novel Bi-modal Bi-copter Robot for Adaptive Locomotion in Air and Diverse Terrain 提出Skater以解决多地形适应性移动问题 locomotion model predictive control
6 Cross Domain Policy Transfer with Effect Cycle-Consistency 提出无配对数据的跨域策略转移方法以解决样本效率问题 locomotion manipulation reinforcement learning
7 Tac-Man: Tactile-Informed Prior-Free Manipulation of Articulated Objects 提出Tac-Man以解决关节物体操控中的不确定性问题 manipulation
8 LiSTA: Geometric Object-Based Change Detection in Cluttered Environments 提出LiSTA以解决复杂环境中的物体级变化检测问题 quadruped

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

#题目一句话要点标签🔗⭐
9 Pseudo-Labeling and Contextual Curriculum Learning for Online Grasp Learning in Robotic Bin Picking 提出SSL-ConvSAC以解决动态抓取学习问题 reinforcement learning curriculum learning grasp prediction
10 RT-H: Action Hierarchies Using Language 提出RT-H以解决机器人模仿学习中的任务语义多样性问题 imitation learning language conditioned
11 Offline Goal-Conditioned Reinforcement Learning for Safety-Critical Tasks with Recovery Policy 提出基于恢复策略的离线目标条件强化学习以解决安全关键任务 reinforcement learning ✅

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

#题目一句话要点标签🔗⭐
12 NatSGD: A Dataset with Speech, Gestures, and Demonstrations for Robot Learning in Natural Human-Robot Interaction 提出NatSGD数据集以解决人机交互中的多模态理解问题 multimodal

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

#题目一句话要点标签🔗⭐
13 AiSDF: Structure-aware Neural Signed Distance Fields in Indoor Scenes 提出AiSDF以解决室内场景3D重建中的结构感知问题 scene reconstruction

⬅️ 返回 cs.RO 首页 · 🏠 返回主页