cs.RO（2025-10-08）

📊 共 17 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (10 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱一：机器人控制 (Robot Control) (10 篇)

#题目一句话要点标签🔗⭐
1 DPL: Depth-only Perceptive Humanoid Locomotion via Realistic Depth Synthesis and Cross-Attention Terrain Reconstruction 提出DPL框架，通过深度信息实现类人机器人在复杂地形上的稳健运动 legged robot humanoid humanoid robot
2 Sampling Strategies for Robust Universal Quadrupedal Locomotion Policies 提出基于配置采样的通用四足机器人鲁棒运动策略，实现零样本迁移 quadruped locomotion locomotion policy
3 GATO: GPU-Accelerated and Batched Trajectory Optimization for Scalable Edge Model Predictive Control GATO：面向边缘模型预测控制的可扩展GPU加速批量轨迹优化 MPC model predictive control trajectory optimization
4 Diffusing Trajectory Optimization Problems for Recovery During Multi-Finger Manipulation 提出基于扩散模型的轨迹优化方法，用于多指灵巧操作中的恢复行为 manipulation trajectory optimization reinforcement learning ✅
5 AVO: Amortized Value Optimization for Contact Mode Switching in Multi-Finger Manipulation AVO：基于价值函数优化的多指灵巧操作接触模式切换方法 manipulation dexterous manipulation trajectory optimization
6 UniFField: A Generalizable Unified Neural Feature Field for Visual, Semantic, and Spatial Uncertainties in Any Scene UniFField：通用、统一且能感知不确定性的神经特征场，适用于任意场景 manipulation scene reconstruction foundation model
7 FLEET: Formal Language-Grounded Scheduling for Heterogeneous Robot Teams FLEET：面向异构机器人团队的基于形式语言的任务调度框架 quadruped world model
8 TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics TIGeR：通过工具集成几何推理，提升视觉-语言模型在机器人领域的精度 manipulation reward design
9 Inspection Planning Primitives with Implicit Models 提出IPIM，利用隐式模型高效解决复杂结构巡检规划中的内存占用问题 motion planning
10 Tailoring materials into kirigami robots 利用剪纸工艺定制材料，实现多功能轻量化机器人 locomotion

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
11 Bring the Apple, Not the Sofa: Impact of Irrelevant Context in Embodied AI Commands on VLA Models 提出LLM过滤框架以提升VLA模型在噪声指令下的鲁棒性 embodied AI vision-language-action VLA
12 Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications VLA模型综述：面向真实机器人应用，整合软硬件，提供实践指导 vision-language-action VLA large language model
13 SanDRA: Safe Large-Language-Model-Based Decision Making for Automated Vehicles Using Reachability Analysis SanDRA：基于可达性分析的自动驾驶车辆安全大语言模型决策框架 large language model
14 Assist-As-Needed: Adaptive Multimodal Robotic Assistance for Medication Management in Dementia Care 提出Assist-As-Needed自适应多模态机器人辅助系统，用于痴呆症患者的药物管理。 multimodal

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

#题目一句话要点标签🔗⭐
15 RLinf-VLA: A Unified and Efficient Framework for VLA+RL Training RLinf-VLA：用于VLA+RL训练的统一高效框架 reinforcement learning PPO vision-language-action
16 Safe Obstacle-Free Guidance of Space Manipulators in Debris Removal Missions via Deep Reinforcement Learning 提出基于TD3的深度强化学习方法，用于空间机械臂安全无碰撞的轨迹规划，助力碎片移除任务。 reinforcement learning deep reinforcement learning TD3

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
17 TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking TrackVLA++：通过增强视觉-语言-动作模型中的推理和记忆能力，实现具身视觉跟踪 egocentric spatiotemporal vision-language-action

⬅️ 返回 cs.RO 首页 · 🏠 返回主页