cs.RO（2024-10-02）

📊 共 17 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (8 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱九：具身大模型 (Embodied Foundation Models) (3)

🔬 支柱一：机器人控制 (Robot Control) (8 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Bi-Level Motion Imitation for Humanoid Robots	提出双层优化模仿学习框架，解决人形机器人运动模仿中物理可行性问题	humanoid humanoid robot imitation learning
2	Run-time Observation Interventions Make Vision-Language-Action Models More Visually Robust	提出BYOVLA，提升VLA模型在复杂视觉环境下的鲁棒性	manipulation vision-language-action VLA	✅
3	$\mathcal{D(R,O)}$ Grasp: A Unified Representation of Robot and Object Interaction for Cross-Embodiment Dexterous Grasping	提出$ extmath{D(R,O)}$ Grasp以解决机器人灵巧抓取问题	manipulation cross-embodiment	✅
4	Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy	提出GemBench基准测试和3D-LOTUS++方法，提升视觉语言机器人操作的泛化能力	manipulation motion planning language conditioned
5	Effective Tuning Strategies for Generalist Robot Manipulation Policies	针对通用机器人操作策略，提出有效的微调策略以提升泛化性能。	manipulation imitation learning
6	Equality Constrained Diffusion for Direct Trajectory Optimization	提出等式约束扩散模型，实现直接轨迹优化，突破非线性约束难题	trajectory optimization
7	Towards Efficient Motion Planning for UAVs: Lazy A* Search with Motion Primitives	提出基于Lazy A*搜索和运动原语的高效无人机运动规划算法	motion planning
8	CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction	提出CANVAS，结合视觉和语言指令，实现常识感知的直观人机交互导航。	sim2real imitation learning

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
9	Open Human-Robot Collaboration using Decentralized Inverse Reinforcement Learning	提出oDec-MDP框架以解决开放人机协作中的灵活性问题	reinforcement learning inverse reinforcement learning
10	Topological mapping for traversability-aware long-range navigation in off-road terrain	提出一种基于拓扑地图和可通行性分析的越野地形长距离自主导航方法	behavior cloning traversability
11	One-Shot Robust Imitation Learning for Long-Horizon Visuomotor Tasks from Unsegmented Demonstrations	提出MiLa框架，通过元学习和自适应动态原语实现长时程无分割示教学习，并增强鲁棒性。	imitation learning
12	Computational Teaching for Driving via Multi-Task Imitation Learning	提出基于多任务模仿学习的计算教学方法，用于高性能驾驶技能自动教学。	imitation learning
13	Robust Imitation Learning for Mobile Manipulator Focusing on Task-Related Viewpoints and Regions	提出一种鲁棒的移动机械臂模仿学习方法，关注任务相关视角和区域，解决遮挡和领域迁移问题。	imitation learning
14	Learning-Based Autonomous Navigation, Benchmark Environments and Simulation Framework for Endovascular Interventions	提出基于深度强化学习的血管内介入自主导航框架stEVE，并验证其在真实环境中的可行性。	reinforcement learning deep reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
15	ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models	ET-Plan-Bench：一个用于具身任务规划，评估大模型时空认知能力的基准测试。	large language model foundation model
16	Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning	Robo-MUTUAL：利用单模态学习实现机器人多模态任务规范	multimodal
17	High and Low Resolution Tradeoffs in Roadside Multimodal Sensing	提出路侧多模态感知评估框架，平衡高低分辨率传感器成本与性能。	multimodal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页