Tabris's Blog

Weekly Papers

机器人论文速览

按领域分类展示近期机器人、具身智能、运动控制相关论文

数据来源：arXiv / robotics_arXiv_daily · 每日更新

更新于 2026/06/08 15:07

具身大模型

共 12 篇 · 最新 2026-06-05

  1. Paper ↗

    [en] RhinoVLA Technical Report

    RhinoVLA 技术报告

    #VLA#Manipulation#Foundation Model
  2. Paper ↗

    [en] LARA: Latent Action Representation Alignment for Vision-Language-Action Models

    LARA：视觉-语言-动作模型的潜在动作表示对齐

    #VLA#Manipulation#Foundation Model
  3. Paper ↗

    [MemDreamer] MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism

    MemDreamer：基于层次图记忆和智能体检索机制解耦感知与推理的长视频理解

    #VLM#Foundation Model
  4. Paper ↗

    Self-evolving LLM agents with in-distribution Optimization

    自进化LLM智能体

    #LLM
  5. Paper ↗

    [Socratic-SWE] Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills

    Socratic-SWE：自进化编码智能体

    #LLM
  6. Paper ↗

    [HARP-VLA] HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model

    HARP-VLA：面向视觉-语言-动作模型的人机对齐表征学习

    #VLA#Human-Robot Interaction#Foundation Model

强化学习

共 12 篇 · 最新 2026-06-05

  1. Paper ↗

    [en] Affordance-Based Hierarchical Reinforcement Learning for Quadruped Pedipulation

    基于可供性的四足机器人足部操作层次强化学习

    #Manipulation#Reinforcement Learning#Quadruped
  2. Paper ↗

    [en] Robotic Policy Adaptation via Weight-Space Meta-Learning

    基于权重空间元学习的机器人策略自适应

    #Control#Reinforcement Learning
  3. Paper ↗

    [en] Spline Policy: A Structured Representation for Robot Policies

    样条策略：一种机器人策略的结构化表示

    #Manipulation#Control
  4. Paper ↗

    [en] Learning All-Terrain Locomotion for a Planetary Rover with Actively Articulated Suspension

    行星探测车主动铰接悬架的全地形运动学习

    #Reinforcement Learning#Locomotion
  5. Paper ↗

    [Learning] RDGen: Demonstration Generation for High-Quality Robot Learning via Reinforcement Learning

    RDGen：基于强化学习的高质量机器人学习演示生成

    #Reinforcement Learning#Imitation Learning#Dataset
  6. Paper ↗

    [Don't Fool Me Twice] Don't Fool Me Twice: Adapting to Adversity in the Wild with Experience-Driven Reasoning

    别再骗我两次：基于经验驱动推理的野外环境适应性

    #Embodied Reasoning#Safety

运动规划

共 8 篇 · 最新 2026-06-05

  1. Paper ↗

    [en] Predictive Style Matching: Natural and Robust Humanoid Locomotion

    预测风格匹配：自然且鲁棒的人形机器人运动

    #Control#Locomotion#Humanoid
  2. Paper ↗

    [en] Rapid co-design of Buoyancy-assisted robots for Challenging Locomotion using Gaussian Evolutionary Specialists

    基于高斯进化专家的浮力辅助机器人快速协同设计

    #Locomotion#Simulation
  3. Paper ↗

    [en] Three-dimensional hydro-cluttered locomotion by an undulatory robot

    波动机器人的三维水下杂乱环境运动

    #Locomotion
  4. Paper ↗

    Learning Terrain-Aware Whole-Body Control for Perceptive Legged Loco-Manipulation

    学习地形感知的全身控制以用于感知式足式移动操作

    #Manipulation#Whole-Body Control#Locomotion
  5. Paper ↗

    Actuator-Aware Inverse Kinematics with Joint-Limit Admissibility for Torque-Controlled Redundant Robots

    面向扭矩控制冗余机器人的关节极限容许执行器感知逆运动学

    #Manipulation#Whole-Body Control#Control
  6. Paper ↗

    [IDOL] IDOL: Inverse-Dynamics-Guided Future Prediction for End-to-End Autonomous Driving

    IDOL：面向端到端自动驾驶的逆动力学引导未来预测

    #World Model#Motion Planning

仿真平台

共 6 篇 · 最新 2026-06-05

  1. Paper ↗

    [en] QuadVerse: An Integrated Framework Aligning Visual-Physical Reality for Quadruped Simulation

    QuadVerse：对齐四足机器人仿真视觉与物理现实的集成框架

    #Sim-to-Real#Quadruped#Simulation
  2. Paper ↗

    Amortized Neural Optimization for Pre-Layout Signal Integrity Design Space Exploration using Differentiable Surrogates

    基于可微代理的预布局信号完整性设计空间探索的摊销神经优化

    #Simulation
  3. Paper ↗

    Network Recovery from Cascade Data: A Debiased Jacobian-Based Machine Learning Approach

    从级联数据恢复网络：基于去偏雅可比的机器学习方法

    #Simulation
  4. Paper ↗

    [CoMetaPNS] CoMetaPNS: Continually Meta-learning Personalized Neural Surrogates for Cardiac Electrophysiology Simulations

    CoMetaPNS：用于心脏电生理仿真的持续元学习个性化神经代理模型

    #Simulation
  5. Paper ↗

    [Learning] Batched Differentiable Rigid Body Dynamics in PyTorch for GPU-Accelerated Robot Learning

    PyTorch中面向GPU加速机器人学习的批量可微刚体动力学

    #Reinforcement Learning#Simulation
  6. Paper ↗

    Simulation of collision avoidance behavior in crowd movement by data-driven approach

    基于数据驱动的人群运动避碰行为仿真

    #Navigation#Simulation

具身操作

共 5 篇 · 最新 2026-06-05

  1. Paper ↗

    [en] ActionMap: Robot Policy Learning via Voxel Action Heatmap

    ActionMap：基于体素动作热图的机器人策略学习

    #3D Perception#Manipulation#Imitation Learning
  2. Paper ↗

    [en] Simulation-Driven Imitation Learning for Biosignals-Free Shared-Autonomy Prosthetic Grasping

    仿真驱动的无生物信号共享自主假肢抓取模仿学习

    #Grasping#Imitation Learning#Simulation
  3. Paper ↗

    [Hyper-Dexterous] Surface Constraint Policy for Learning Surface-Constrained and Dynamically Feasible Robot Skills

    超灵巧：面向表面约束与动态可行机器人技能学习的表面约束策略

    #Manipulation#Dexterous Hand#Control
  4. Paper ↗

    [Haptic Sorter] Haptic Sorter: A Unified Planning Framework for Online Shape Estimation and Real-Time Pose Inference

    触觉分拣器：面向在线形状估计与实时位姿推断的统一规划框架

    #Haptic#Manipulation#Grasping
  5. Paper ↗

    Learning Controlled Separation of Small Objects Between Two Fingers with a Tactile Skin

    基于触觉皮肤学习双指间小物体的受控分离

    #Haptic#Manipulation#Dexterous Hand

机器人安全

共 3 篇 · 最新 2026-06-05

  1. Paper ↗

    [en] Shield-Loco: Shielding Locomotion Policies with Predictive Safety Filtering

    Shield-Loco：基于预测安全过滤的运动策略防护

    #Control#Locomotion#Safety
  2. Paper ↗

    [en] Re-imagining ISO 26262 in the Age of Autonomous Vehicles: Enhancing Controllability through Transferability and Predictability

    重新审视自动驾驶时代的ISO 26262

    #Safety
  3. Paper ↗

    [Collision] Probing Collision Grounding in Vision-Language Models for Safe Human-Robot Collaboration

    探究视觉-语言模型在安全人机协作中的碰撞基础

    #VLM#Human-Robot Interaction#Safety

任务规划

共 5 篇 · 最新 2026-06-05

  1. Paper ↗

    [en] CAPE: Contrastive Action-conditioned Parallel Encoding for Embodied Planning

    CAPE：用于具身规划的对比动作条件并行编码

    #Task Planning#Embodied Reasoning
  2. Paper ↗

    [en] Neuro-Symbolic Learning for Long-Horizon Task Planning Under Complex Logical Constraints

    复杂逻辑约束下长时序任务规划的神经符号学习

    #Task Planning
  3. Paper ↗

    On-Device Robotic Planning: Eliminating Inference Redundancy for Efficient Decision-Making

    端侧机器人规划：消除推理冗余以实现高效决策

    #Motion Planning#Task Planning
  4. Paper ↗

    [HypoAgent] HypoAgent: An Agentic Framework for Interactive Abductive Hypothesis Generation over Knowledge Graphs

    HypoAgent：基于知识图谱的交互式溯因假设生成智能体框架

    #LLM
  5. Paper ↗

    [AutoSci] AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle

    AutoSci：面向完整科学研究生命周期的以内存为中心的智能体系统

    #LLM

具身交互

共 5 篇 · 最新 2026-06-05

  1. Paper ↗

    [en] A Multi-Operator Mixed-Reality Interface for Multi-Robot Control and Coordination: Co-Located and Private Workspace Collaboration

    多操作员混合现实接口用于多机器人控制与协调

    #Human-Robot Interaction#Teleoperation#Multi-Agent
  2. Paper ↗

    [en] What Is My Robot Thinking? Design Considerations for Transparent and Trustworthy Shared Autonomy

    我的机器人在想什么？透明可信共享自主性设计考量

    #Human-Robot Interaction
  3. Paper ↗

    A study on a Real-Time VR-Based Teleoperation Framework for Manipulator in Dynamic Environment

    动态环境下基于VR的机械臂实时遥操作框架研究

    #Human-Robot Interaction#Teleoperation#Manipulation
  4. Paper ↗

    [en] Shaft-integrated Force Sensing with Transformer-based Dynamics Compensation for Telesurgery

    面向远程手术的基于Transformer动力学补偿的轴集成力传感

    #Teleoperation#Haptic#Control
  5. Paper ↗

    Toward Accessible Mobile Money: A Voice-Driven, Biometrically Secured USSD Automation Framework for Visually Impaired Users

    面向无障碍移动支付：面向视障用户的语音驱动生物识别安全USSD自动化框架

    #Human-Robot Interaction

环境感知

共 7 篇 · 最新 2026-06-05

  1. Paper ↗

    [en] Does Appearance Help? A Systematic Study of Image-Based Re-Identification in Online 3D Multi-Pedestrian Tracking

    外观助益吗？基于图像的在线3D多行人跟踪重识别系统研究

    #3D Perception
  2. Paper ↗

    Impact of Synthetic Lesional MR Images in Automated Focal Cortical Dysplasia Detection in Low-Data Scenarios

    合成病变MR图像影响

    #Reinforcement Learning
  3. Paper ↗

    Video-Based Prediction of In-Flight Particle Characteristics in Atmospheric Plasma Spraying

    基于视频的大气等离子喷涂飞行粒子特性预测

    #Reinforcement Learning
  4. Paper ↗

    Mitosis Detection in the Wild: Multi-Tumor and Context-Aware Generalization in the MIDOG 2025 Challenge

    野外有丝分裂检测

    #Reinforcement Learning
  5. Paper ↗

    Triangle Splatting SLAM

    三角形泼溅SLAM

    #SLAM#Mapping#3D Perception
  6. Paper ↗

    [VolFill] VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching

    VolFill：基于体积流匹配的单视图非模态3D场景重建

    #Mapping#3D Perception

基础理论

共 17 篇 · 最新 2026-06-05

  1. Paper ↗

    Supervision versus Demonstration-Based In-Context Learning for Multiword Expression Classification

    多词表达分类的上下文学习

    #LLM
  2. Paper ↗

    Automatic, Debiased, and Invariant Counterfactual Generation under General Interventions

    一般干预下的自动、去偏与不变反事实生成

    #Embodied Reasoning
  3. Paper ↗

    How AI Agents Reshape Knowledge Work: Autonomy, Efficiency, and Scope

    AI智能体如何重塑知识工作

    #Embodied Reasoning
  4. Paper ↗

    Unsupervised Continual Clustering via Forward-Backward Knowledge Distillation

    无监督连续聚类

    #Reinforcement Learning
  5. Paper ↗

    Covariance Shrinkage via Stochastic Interpolation

    通过随机插值的协方差收缩

    #Human-Robot Interaction
  6. Paper ↗

    Vision-Language Models Suppress Female Representations Under Ambiguous Input

    视觉语言模型在模糊输入下抑制女性表征

    #VLM

世界模型

共 1 篇 · 最新 2026-05-29

  1. Paper ↗

    [AR Forcing] AR Forcing: Towards Long-Horizon Robot Navigation World Model

    AR Forcing：迈向长视野机器人导航世界模型

    #World Model#Navigation

具身导航

共 3 篇 · 最新 2026-05-29

  1. Paper ↗

    [TARIC] TARIC: Memory-Augmented Traversability-Aware Outdoor VLN under Interrupted Semantic Cues

    TARIC：中断语义线索下记忆增强的可穿越性感知户外视觉语言导航

    #Navigation#3D Perception
  2. Paper ↗

    [LiftNav] LiftNav: Path Planning via Semantic Lifting in TSDF-Guided Gaussian Splatting

    LiftNav：基于TSDF引导高斯泼溅语义提升的路径规划

    #Navigation#3D Perception#Motion Planning
  3. Paper ↗

    The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation Planning

    剑、盾与阿喀琉斯之踵：刻画大语言模型在导航规划中空间推理的语言归纳偏置

    #LLM#Navigation#Spatial Reasoning

数据集评测

共 6 篇 · 最新 2026-05-29

  1. Paper ↗

    [en] nuReasoning: A Reasoning-Centric Dataset and Benchmark for Long-Tail Autonomous Driving

    nuReasoning：面向长尾自动驾驶的以推理为中心的数据集与基准

    #Embodied Reasoning#Benchmark#Foundation Model
  2. Paper ↗

    [SOCO] SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models

    SOCO：视觉基础模型中的语义对象对应基准测试

    #3D Perception#Benchmark
  3. Paper ↗

    [FAM-Bench] FAM-Bench: A Multimodal Benchmark for Condition-Aware Food-as-Medicine Reasoning

    FAM-Bench：面向条件感知食疗推理的多模态基准

    #VLM#Benchmark
  4. Paper ↗

    [FBHM] FBHM: Functional Benchmarking and Steering of VLMs for Hateful Meme Detection

    FBHM：面向仇恨模因检测的VLM功能基准测试与引导

    #VLM#Benchmark#Safety
  5. Paper ↗

    Scaling Conversational Hungarian ASR: The BEA-Dialogue+ Corpus

    扩展对话式匈牙利语ASR：BEA-Dialogue+语料库

    #Dataset
  6. Paper ↗

    [Chem-PerturBridge] Chem-PerturBridge: a harmonized compendium of small molecule perturbation transcriptomic effects

    Chem-PerturBridge：小分子扰动转录组效应的协调概要

    #Dataset

群体智能

共 1 篇 · 最新 2026-05-29

  1. Paper ↗

    [Dreaming Of Others] Dreaming Of Others: Latent Teammate Modeling In World Models For Multi-Agent Reinforcement Learning

    梦见他人：多智能体强化学习中基于世界模型的潜在队友建模

    #World Model#Reinforcement Learning#Multi-Agent
0%
Preparing WebPet