cs.RO（2025-07-17）

📊 共 17 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) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (12 篇)

#题目一句话要点标签🔗⭐
1 Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities VLN-PE：一个物理现实的VLN平台，用于评估具身智能在物理和视觉差异下的导航性能。 quadruped legged robot humanoid ✅
2 Humanoid Robot Acrobatics Utilizing Complete Articulated Rigid Body Dynamics 提出基于完整刚体动力学的人形机器人杂技控制架构 humanoid humanoid robot whole-body control
3 ZipMPC: Compressed Context-Dependent MPC Cost via Imitation Learning ZipMPC：通过模仿学习压缩上下文相关的MPC成本，加速实时控制 MPC model predictive control imitation learning
4 Evaluating Reinforcement Learning Algorithms for Navigation in Simulated Robotic Quadrupeds: A Comparative Study Inspired by Guide Dog Behaviour 利用强化学习训练四足机器人导航，PPO算法在导盲犬模拟中表现最佳。 quadruped reinforcement learning PPO
5 Refining Motion for Peak Performance: Identifying Optimal Gait Parameters for Energy-Efficient Quadrupedal Bounding 优化步态参数提升四足机器人能效：探索高效跳跃运动的关键 quadruped legged robot locomotion
6 Non-differentiable Reward Optimization for Diffusion-based Autonomous Motion Planning 提出基于强化学习的扩散模型训练方法，优化自动驾驶运动规划中的非可微奖励。 motion planning reinforcement learning
7 Learning to Predict Mobile Robot Stability in Off-Road Environments 提出IMUnet，利用轻量级神经网络预测移动机器人在非结构化环境中的稳定性。 manipulation mobile manipulation SSM
8 Few-shot transfer of tool-use skills using human demonstrations with proximity and tactile sensing 提出一种基于触觉和近邻感知的人类演示少样本工具使用技能迁移框架 manipulation sim-to-real multimodal
9 DEMONSTRATE: Zero-shot Language to Robotic Control via Multi-task Demonstration Learning DEMONSTRATE：基于多任务示教学习的零样本语言到机器人控制 manipulation teleoperation large language model
10 FFI-VTR: Lightweight and Robust Visual Teach and Repeat Navigation based on Feature Flow Indicator and Probabilistic Motion Planning 提出基于特征流指示器和概率运动规划的轻量级鲁棒视觉Teach and Repeat导航方法 motion planning ✅
11 Signal Temporal Logic Compliant Co-design of Planning and Control 提出一种基于强化学习和时序逻辑的机器人运动规划与控制协同设计方法 quadruped motion planning reinforcement learning
12 Public Evaluation on Potential Social Impacts of Fully Autonomous Cybernetic Avatars for Physical Support in Daily-Life Environments: Large-Scale Demonstration and Survey at Avatar Land 通过大规模公众演示与调查评估全自主控制化身在日常生活中的社会影响 teleoperation ✅

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

#题目一句话要点标签🔗⭐
13 Aligning Humans and Robots via Reinforcement Learning from Implicit Human Feedback 提出基于脑电信号的隐式人机协作强化学习框架，解决机器人任务中奖励函数设计难题。 reinforcement learning policy learning RLHF
14 Latent Policy Steering with Embodiment-Agnostic Pretrained World Models 提出基于具身无关预训练世界模型的潜在策略引导方法，提升机器人模仿学习效率。 world model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
15 osmAG-LLM: Zero-Shot Open-Vocabulary Object Navigation via Semantic Maps and Large Language Models Reasoning 提出osmAG-LLM，利用语义地图和LLM推理实现零样本开放词汇物体导航 semantic map open-vocabulary open vocabulary

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

#题目一句话要点标签🔗⭐
16 ERR@HRI 2.0 Challenge: Multimodal Detection of Errors and Failures in Human-Robot Conversations ERR@HRI 2.0挑战赛：多模态检测人机对话中的错误与失败 large language model multimodal

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
17 MoCap2GT: A High-Precision Ground Truth Estimator for SLAM Benchmarking Based on Motion Capture and IMU Fusion MoCap2GT：基于运动捕捉与IMU融合的高精度SLAM基准真值估计器 spatiotemporal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页