cs.RO（2025-05-24）

📊 共 13 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (12 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (12 篇)

#题目一句话要点标签🔗⭐
1 One Policy but Many Worlds: A Scalable Unified Policy for Versatile Humanoid Locomotion DreamPolicy：一种可扩展的通用人形机器人运动策略，通过离线数据和扩散模型实现零样本泛化。 humanoid humanoid control humanoid locomotion
2 VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning 提出VLA-RL框架，利用强化学习提升视觉-语言-动作模型在机器人操作任务中的泛化性。 manipulation reinforcement learning vision-language-action
3 YOPO-Rally: A Sim-to-Real Single-Stage Planner for Off-Road Terrain 提出YOPO-Rally，用于在复杂地形中实现零样本迁移的单阶段端到端导航。 sim-to-real MPC behavior cloning
4 Mobile Manipulation Planning for Tabletop Rearrangement 针对桌面重排，提出一种高效的移动操作规划方法 manipulation mobile manipulation
5 ManiFeel: Benchmarking and Understanding Visuotactile Manipulation Policy Learning ManiFeel：提出一个用于视觉触觉操作策略学习的基准测试，解决视觉受限场景下的操作难题。 manipulation policy learning
6 DiffusionRL: Efficient Training of Diffusion Policies for Robotic Grasping Using RL-Adapted Large-Scale Datasets 提出基于强化学习增强数据集的扩散策略，高效训练机器人抓取任务 manipulation dexterous manipulation reinforcement learning
7 Genie Centurion: Accelerating Scalable Real-World Robot Training with Human Rewind-and-Refine Guidance Genie Centurion：基于人类回溯与精炼指导，加速可扩展的真实世界机器人训练 teleoperation vision-language-action VLA
8 Grounding Bodily Awareness in Visual Representations for Efficient Policy Learning 提出ICon，通过对比学习提升机器人操作策略学习的效率和泛化性 manipulation policy learning contrastive learning ✅
9 S2R-Bench: A Sim-to-Real Evaluation Benchmark for Autonomous Driving S2R-Bench：面向自动驾驶的Sim-to-Real评估基准，关注感知算法在真实场景下的鲁棒性 sim-to-real ✅
10 Canonical Policy: Learning Canonical 3D Representation for SE(3)-Equivariant Policy 提出Canonical Policy，通过学习规范3D表示提升机器人操作策略的泛化性。 manipulation policy learning imitation learning ✅
11 Coordinated guidance and control for multiple parafoil system landing 提出一种协同制导与控制方法，解决多伞翼机系统着陆的碰撞避免和计算效率问题。 model predictive control trajectory optimization
12 On the Dual-Use Dilemma in Physical Reasoning and Force 研究物理推理中VLM控制机器人力交互的安全性与功能性对立问题 manipulation

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

#题目一句话要点标签🔗⭐
13 Applying Ontologies and Knowledge Augmented Large Language Models to Industrial Automation: A Decision-Making Guidance for Achieving Human-Robot Collaboration in Industry 5.0 为工业5.0人机协作提供基于本体和知识增强大语言模型的决策指导 large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页