cs.RO（2024-10-21）

📊 共 18 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (12 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (12 篇)

#题目一句话要点标签🔗⭐
1 Automated Planning Domain Inference for Task and Motion Planning 提出一种自动规划领域推断方法，通过少量演示轨迹为任务和运动规划生成领域模型。 motion planning behavior cloning task and motion planning
2 A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLM 提出双过程VLA框架，利用VLM高效实现机器人操作 manipulation vision-language-action VLA
3 Online Optimization of Central Pattern Generators for Quadruped Locomotion 提出基于贝叶斯优化的CPG在线优化框架，实现四足机器人快速适应地形与负载变化。 quadruped legged locomotion locomotion
4 Task-oriented Robotic Manipulation with Vision Language Models 提出一种结合视觉语言模型与空间推理的机器人操作框架，提升任务导向操作性能。 manipulation spatial relationship large language model
5 MSGField: A Unified Scene Representation Integrating Motion, Semantics, and Geometry for Robotic Manipulation 提出MSGField，融合运动、语义和几何信息的统一场景表示，用于机器人操作。 manipulation gaussian splatting splatting ✅
6 ARCADE: Scalable Demonstration Collection and Generation via Augmented Reality for Imitation Learning ARCADE：利用增强现实技术实现可扩展的示教数据收集与生成，用于模仿学习 manipulation imitation learning
7 Caging in Time: A Framework for Robust Object Manipulation under Uncertainties and Limited Robot Perception 提出时间笼式操作框架，解决单机器人不确定性和有限感知下的鲁棒操作问题 manipulation
8 Hierarchical Search-Based Cooperative Motion Planning 提出一种层级搜索的协作运动规划方法，解决多无人地面车辆在复杂环境下的协同路径规划问题。 motion planning ✅
9 Implicit Contact Diffuser: Sequential Contact Reasoning with Latent Point Cloud Diffusion 提出隐式接触扩散器(ICD)，利用点云扩散模型解决长时程接触操作中的序列接触推理问题。 manipulation MPC
10 Agent-Based Emulation for Deploying Robot Swarm Behaviors 提出基于Agent的机器人集群仿真方法，简化集群行为部署。 sim2real
11 Neural Predictor for Flight Control with Payload 提出基于神经预测器的飞行控制方法，提升负载无人机抗扰动性能 MPC ✅
12 Design of a Flexible Robot Arm for Safe Aerial Physical Interaction 提出一种灵活机器人臂以实现安全的空中物理交互 manipulation

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

#题目一句话要点标签🔗⭐
13 The Duality of Generative AI and Reinforcement Learning in Robotics: A Review 综述生成式AI与强化学习在机器人领域的双重性，并提出未来研究方向。 reinforcement learning embodied AI VLA ✅
14 Diffusion Transformer Policy 提出Diffusion Transformer Policy，利用扩散Transformer模型提升机器人泛化能力。 transformer policy vision-language-action Octo
15 Long-distance Geomagnetic Navigation in GNSS-denied Environments with Deep Reinforcement Learning 提出基于深度强化学习的长距离地磁导航方法，解决GNSS拒止环境下的导航问题 reinforcement learning deep reinforcement learning DRL
16 Learning Quadrotor Control From Visual Features Using Differentiable Simulation 利用可微仿真，从视觉特征中学习四旋翼飞行器控制 reinforcement learning policy learning representation learning
17 Reinforced Imitative Trajectory Planning for Urban Automated Driving 提出强化模仿轨迹规划方法，用于城市自动驾驶多步轨迹规划。 reinforcement learning imitation learning inverse reinforcement learning ✅

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

#题目一句话要点标签🔗⭐
18 CoT-TL: Low-Resource Temporal Knowledge Representation of Planning Instructions Using Chain-of-Thought Reasoning 提出CoT-TL以解决低资源环境下规划指令的知识表示问题 large language model chain-of-thought TAMP ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页