cs.RO（2025-05-26）

📊 共 18 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (15 🔗2) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (15 篇)

#题目一句话要点标签🔗⭐
1 SMAP: Self-supervised Motion Adaptation for Physically Plausible Humanoid Whole-body Control SMAP：用于人型机器人全身控制的自监督运动适配 humanoid humanoid robot whole-body control
2 Real-time Whole-body Model Predictive Control for Bipedal Locomotion with a Novel Kino-dynamic Model and Warm-start Method 提出基于新型运动-动力学模型和Warm-start策略的双足机器人全身模型预测控制方法 bipedal biped whole-body control
3 Heavy lifting tasks via haptic teleoperation of a wheeled humanoid 提出一种基于触觉遥操作的轮式人形机器人重物搬运方案 humanoid humanoid robot whole-body control
4 URPlanner: A Universal Paradigm For Collision-Free Robotic Motion Planning Based on Deep Reinforcement Learning URPlanner：基于深度强化学习的通用机器人无碰撞运动规划框架 motion planning reinforcement learning deep reinforcement learning
5 Extremum Flow Matching for Offline Goal Conditioned Reinforcement Learning 提出基于Extremum Flow Matching的离线目标条件强化学习方法，提升机器人操作任务性能。 humanoid humanoid robot manipulation ✅
6 Integrating emotional intelligence, memory architecture, and gestures to achieve empathetic humanoid robot interaction in an educational setting 集成情商、记忆架构和手势，实现教育场景中具身同理心人机交互 humanoid humanoid robot large language model
7 Whole-body Multi-contact Motion Control for Humanoid Robots Based on Distributed Tactile Sensors 基于分布式触觉传感器的全身多接触人形机器人运动控制 humanoid humanoid robot
8 Collision- and Reachability-Aware Multi-Robot Control with Grounded LLM Planners 提出基于可验证奖励强化学习的LLM多机器人控制方法，解决物理约束违背问题 reachability-aware reinforcement learning large language model
9 GeoPF: Infusing Geometry into Potential Fields for Reactive Planning in Non-trivial Environments GeoPF：融合几何信息的势场法，用于复杂环境下的机器人反应式规划 motion planning motion generation reactive motion
10 RFTF: Reinforcement Fine-tuning for Embodied Agents with Temporal Feedback 提出RFTF：一种基于时序反馈的强化微调方法，提升具身智能体性能。 manipulation behavior cloning vision-language-action
11 EgoZero: Robot Learning from Smart Glasses EgoZero：利用智能眼镜的人类演示数据，实现零样本机器人学习 manipulation policy learning egocentric
12 LLA-MPC: Fast Adaptive Control for Autonomous Racing 提出LLA-MPC，用于解决自动驾驶赛车中快速变化的轮胎-路面交互问题 MPC model predictive control
13 TeViR: Text-to-Video Reward with Diffusion Models for Efficient Reinforcement Learning 提出TeViR，利用文本到视频扩散模型进行高效强化学习的奖励函数设计 manipulation reinforcement learning
14 HAND Me the Data: Fast Robot Adaptation via Hand Path Retrieval HAND：通过手部轨迹检索实现机器人快速适应新任务 manipulation teleoperation
15 Co-Design of Soft Gripper with Neural Physics 提出基于神经物理模型的软体夹爪协同设计框架，优化夹爪刚度分布与抓取姿态。 manipulation ✅

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
16 Embodied AI with Foundation Models for Mobile Service Robots: A Systematic Review 综述：具身智能与移动服务机器人中Foundation Model的应用与挑战 cross-embodiment embodied AI vision-language-action

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

#题目一句话要点标签🔗⭐
17 Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospects 提出链式思维方法以提升自动驾驶系统的推理能力 large language model chain-of-thought ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
18 OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation 提出基于世界模型的单样本视觉模仿学习框架，解决未见任务泛化问题。 imitation learning world model ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页