cs.RO（2026-04-06）

📊 共 32 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (19) 支柱三：空间感知与语义 (Perception & Semantics) (5) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱一：机器人控制 (Robot Control) (19 篇)

#题目一句话要点标签🔗⭐
1 Learning Task-Invariant Properties via Dreamer: Enabling Efficient Policy Transfer for Quadruped Robots DreamTIP：通过学习任务不变性提升四足机器人策略迁移效率 quadruped locomotion sim-to-real
2 Open-Loop Planning, Closed-Loop Verification: Speculative Verification for VLA 提出SV-VLA框架，结合开环规划与闭环验证，提升VLA控制效率与鲁棒性。 manipulation vision-language-action VLA
3 A Rapid Instrument Exchange System for Humanoid Robots in Minimally Invasive Surgery 针对人型机器人微创手术，提出快速器械交换系统。 humanoid humanoid robot dual-arm
4 Safety-Critical Centralized Nonlinear MPC for Cooperative Payload Transportation by Two Quadrupedal Robots 提出基于CBF的集中式非线性MPC，用于双足式机器人协同负载运输，确保安全。 quadruped MPC model predictive control
5 Learning Locomotion on Complex Terrain for Quadrupedal Robots with Foot Position Maps and Stability Rewards 提出基于足部位置图和稳定性奖励的强化学习方法，提升四足机器人复杂地形运动能力 quadruped locomotion reinforcement learning
6 The Compression Gap: Why Discrete Tokenization Limits Vision-Language-Action Model Scaling 揭示离散token化限制VLA模型扩展的原因：压缩瓶颈理论 manipulation diffusion policy vision-language-action
7 Failure Mechanisms and Risk Estimation for Legged Robot Locomotion on Granular Slopes 针对腿式机器人沙坡行走，提出基于力学建模的失效风险评估方法 legged robot locomotion penetration
8 FSUNav: A Cerebrum-Cerebellum Architecture for Fast, Safe, and Universal Zero-Shot Goal-Oriented Navigation FSUNav：基于大脑-小脑架构的快速、安全、通用零样本目标导向导航 quadruped humanoid reinforcement learning
9 ARM: Advantage Reward Modeling for Long-Horizon Manipulation 提出优势奖励建模以解决长时间机器人操控中的稀疏奖励问题 manipulation reinforcement learning offline RL
10 Tune to Learn: How Controller Gains Shape Robot Policy Learning 控制器增益影响机器人策略学习，需针对学习范式优化 manipulation sim-to-real reinforcement learning
11 ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation ROPA：用于RGB-D双臂操作数据增强的合成机器人姿态生成方法 manipulation bi-manual bimanual manipulation
12 MFE: A Multimodal Hand Exoskeleton with Interactive Force, Pressure and Thermo-haptic Feedback MFE：一种具有交互式力、压力和热触觉反馈的多模态手部外骨骼 teleoperation multimodal
13 Differentiable SpaTiaL: Symbolic Learning and Reasoning with Geometric Temporal Logic for Manipulation Tasks 提出可微SpaTiaL，用于操作任务中基于几何时序逻辑的符号学习与推理。 manipulation trajectory optimization
14 UniCon: A Unified System for Efficient Robot Learning Transfers UniCon：一种用于高效机器人学习迁移的统一系统 sim-to-real UniCon
15 F2F-AP: Flow-to-Future Asynchronous Policy for Real-time Dynamic Manipulation 提出F2F-AP，利用预测光流解决动态操作中异步策略的时延问题 manipulation contrastive learning
16 Multi-View Video Diffusion Policy: A 3D Spatio-Temporal-Aware Video Action Model 提出MV-VDP多视角视频扩散策略，用于数据高效的3D时空感知机器人操作。 manipulation diffusion policy
17 A Dynamic Toolkit for Transmission Characteristics of Precision Reducers with Explicit Contact Geometry 提出一种动态工具包，用于分析精密减速器的传动特性，显式考虑接触几何。 quadruped humanoid humanoid robot
18 Goal-Conditioned Neural ODEs with Guaranteed Safety and Stability for Learning-Based All-Pairs Motion Planning 提出基于目标条件神经ODE的安全稳定全配对运动规划方法 motion planning
19 From Impact to Insight: Dynamics-Aware Proprioceptive Terrain Sensing on Granular Media 提出动力学感知的足端触觉方法，用于高速运动中沙土地形的稳健估计 locomotion

🔬 支柱三：空间感知与语义 (Perception & Semantics) (5 篇)

#题目一句话要点标签🔗⭐
20 Flash-Mono: Feed-Forward Accelerated Gaussian Splatting Monocular SLAM Flash-Mono：基于前馈加速高斯溅射的单目SLAM，显著提升效率与精度。 3D gaussian splatting gaussian splatting splatting
21 An Open-Source LiDAR and Monocular Off-Road Autonomous Navigation Stack 提出开源的激光雷达与单目视觉越野自主导航方案，无需特定任务训练。 depth estimation monocular depth metric depth
22 ALIVE-LIO: Degeneracy-Aware Learning of Inertial Velocity for Enhancing ESKF-Based LiDAR-Inertial Odometry ALIVE-LIO：基于学习的退化感知惯性速度估计，增强ESKF的激光雷达惯性里程计 LIO motion estimation
23 Vision-Based End-to-End Learning for UAV Traversal of Irregular Gaps via Differentiable Simulation 提出基于视觉和可微仿真的无人机复杂缝隙穿越端到端学习框架 traversability differentiable simulation
24 Terra: Hierarchical Terrain-Aware 3D Scene Graph for Task-Agnostic Outdoor Mapping Terra：面向任务无关户外建图的分层地形感知3D场景图 traversability

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
25 OMNI-PoseX: A Fast Vision Model for 6D Object Pose Estimation in Embodied Tasks OMNI-PoseX：用于具身任务的快速6D物体姿态估计视觉模型 flow matching open-vocabulary open vocabulary
26 Look, Zoom, Understand: The Robotic Eyeball for Embodied Perception 提出EyeVLA，解决具身智能中语言引导的主动视觉感知问题 reinforcement learning embodied AI vision-language-action
27 Behavior-Constrained Reinforcement Learning with Receding-Horizon Credit Assignment for High-Performance Control 提出基于Receding-Horizon Credit Assignment的Behavior-Constrained强化学习，用于高性能控制。 reinforcement learning imitation learning
28 A Flow Matching Framework for Soft-Robot Inverse Dynamics 提出流匹配框架以解决软机器人逆动力学问题 flow matching
29 Lightweight Learning from Actuation-Space Demonstrations via Flow Matching for Whole-Body Soft Robotic Grasping 提出基于流匹配的轻量级驱动空间学习方法，用于软体机器人全身抓取 flow matching

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
30 V2X-QA: A Comprehensive Reasoning Dataset and Benchmark for Multimodal Large Language Models in Autonomous Driving Across Ego, Infrastructure, and Cooperative Views 提出V2X-QA数据集与基准，评估多模态大模型在自动驾驶中跨视角推理能力。 large language model multimodal
31 Learning Structured Robot Policies from Vision-Language Models via Synthetic Neuro-Symbolic Supervision 利用合成神经符号监督，从视觉语言模型学习结构化机器人策略 foundation model multimodal

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

#题目一句话要点标签🔗⭐
32 Joint Prediction of Human Motions and Actions in Human-Robot Collaboration 提出MA-HERP框架以解决人机协作中的运动与动作预测问题 human motion motion prediction

⬅️ 返回 cs.RO 首页 · 🏠 返回主页