cs.RO（2026-07-05）

📊 共 51 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (34) 支柱二：RL算法与架构 (RL & Architecture) (10) 支柱三：空间感知与语义 (Perception & Semantics) (3) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱一：机器人控制 (Robot Control) (34 篇)

#题目一句话要点标签🔗⭐
1 Multi-Rate Nonlinear Model Predictive Control for Wall-Supported Bipedal Locomotion of Quadrupedal Robots 提出多速率非线性模型预测控制以解决四足机器人壁支撑的双足行走问题 quadruped bipedal biped
2 LIME: Learning Intent-aware Camera Motion from Egocentric Video 提出LIME以解决语言条件下相机运动生成问题 manipulation flow matching motion generation
3 Actuator Reality Shaping for Zero-Shot Sim-to-Real Robot Learning 提出执行器现实塑造以解决零-shot仿真到现实机器人学习问题 legged robot humanoid humanoid robot
4 HEFT: Heavy-Payload Full-size Humanoid Teleoperation with Privileged Motion Guidance and Windowed Payload Curriculum 提出HEFT框架以解决全尺寸人形机器人重载遥操作问题 humanoid motion tracking locomotion
5 Sim2Real-AD: A Modular Sim-to-Real Framework for Deploying VLM-Guided Reinforcement Learning in Real-World Autonomous Driving 提出Sim2Real-AD框架以解决仿真到现实的自动驾驶部署问题 sim-to-real sim2real reinforcement learning
6 The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection 提出混合动态数据收集以增强VLA空间泛化能力 manipulation dual-arm spatial relationship
7 Neuro-Symbolic Safety Guidance for Vision-Language-Action Models via Constrained Flow Matching 提出神经符号安全指导机制以解决视觉-语言-动作模型的碰撞预防问题 manipulation flow matching vision-language-action
8 Guided Action Flow: Q-Guided Inference for Flow-Matching Vision-Language-Action Policies 提出引导动作流以解决流匹配视觉-语言-动作策略的推理问题 manipulation flow matching vision-language-action
9 CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation 提出CaP-X框架以提升机器人操作中的编码代理性能 manipulation sim2real reinforcement learning
10 PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation 提出PhysMani以解决动态物体操控中的物理建模问题 manipulation world model world models
11 VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon 提出VLA-Corrector以解决VLA策略的闭环反应不足问题 manipulation vision-language-action VLA
12 VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer 提出VLSA架构以解决机器人操作中的安全性问题 manipulation vision-language-action VLA
13 Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration 提出无训练注意力重校准方法以解决VLA模型的语言盲目问题 manipulation vision-language-action VLA
14 ManipArena: Comprehensive Real-world Evaluation of Reasoning-Oriented Generalist Robot Manipulation 提出ManipArena框架以解决机器人操作评估的现实差距问题 manipulation mobile manipulation world action model
15 VT-WAM: Visual-Tactile World Action Model for Contact-Rich Manipulation 提出VT-WAM以解决接触丰富操作中的动态建模问题 manipulation flow matching world action model
16 DVG-WM: Disentangled Video Generation Enables Efficient Embodied World Model for Robotic Manipulation 提出DVG-WM以解决机器人操作中的视频生成与动态建模问题 manipulation flow matching world model
17 WorldSample: Closed-loop Real-robot RL with World Modelling 提出WorldSample以解决真实机器人强化学习中的高交互成本问题 manipulation reinforcement learning imitation learning
18 BIFROST: Bridging Invariant Feature Representation for Observation-space Sim2Real Transfer 提出BIFROST以解决机器人政策学习中的Sim2Real转移问题 manipulation sim2real policy learning
19 ACID: Action Consistency via Inverse Dynamics for Planning with World Models 提出ACID框架以解决决策时间规划中的动作一致性问题 manipulation world model world models
20 BIEVR-LIO: Robust LiDAR-Inertial Odometry through Bump-Image-Enhanced Voxel Maps 提出BIEVR-LIO以解决LiDAR惯性里程计在复杂环境中的鲁棒性问题 locomotion LIO elevation map
21 One Demonstration Is Enough for Real-World Robotic Reinforcement Learning 提出AutoSERL框架以解决机器人强化学习中的数据收集难题 manipulation reinforcement learning imitation learning
22 CoRe: Combined Rewards with Vision-Language Model Feedback for Preference-Aligned Reinforcement Learning 提出CoRe框架以解决强化学习中的奖励设计问题 manipulation reinforcement learning policy learning
23 Learning Locomotion on Discrete Terrain via Minimal Proximity Sensing 通过最小接近传感器提升四足机器人在离散地形上的行走能力 quadruped locomotion reinforcement learning
24 Imagining the Sense of Touch: Touch-Informed Manipulation via Imagined Tactile Representations 提出TacImag框架以解决无触觉传感器的机器人操控问题 manipulation contact-aware
25 Bridge-WA: Predicting Where and How the World Changes for Robotic Action 提出Bridge-WA以解决机器人行动中的场景变化预测问题 manipulation world model world models
26 NeHMO: Neural Hamilton-Jacobi Reachability Learning for Decentralized Safe Multi-Arm Motion Planning 提出NeHMO以解决安全多臂运动规划问题 trajectory optimization motion planning
27 Distilling Collaborative Dynamics into Latent Space for Implicit Coordination in Decentralized Multi-Agent Manipulation 提出CLS-DP以解决多臂操控中的隐式协调问题 manipulation spatiotemporal
28 Learning Semantic Atomic Skills for Multi-Task Robotic Manipulation 提出AtomSkill框架以解决多任务机器人操作中的技能学习问题 manipulation imitation learning
29 Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution 提出潜在策略障碍以解决视觉运动策略的鲁棒性问题 manipulation policy learning behavior cloning
30 SPOT: Spatio-Temporal Obstacle-free Trajectory Planning for UAVs in Unknown Dynamic Environments 提出SPOT以解决无人机在未知动态环境中的轨迹规划问题 trajectory optimization motion planning reactive motion
31 VLM-AR3L: Vision-Language Models for Absolute and Relative Rewards in Reinforcement Learning 提出VLM-AR3L以解决强化学习中的奖励函数设计问题 manipulation reinforcement learning
32 Choreographing the Way of Water: A Computational Framework for Aquatic Robotic Art 提出水上机器人编排框架以应对流体动力学挑战 model predictive control
33 Human Supervisor Workload Prediction: Lag Horizon Selection 提出生理传感器驱动的人类工作负载预测方法以解决反应性问题 teleoperation
34 Regression Test Selection for Updated Capability Modules in Compositional ML Systems via Atomic-Quality Probes 提出回归测试选择方法以解决组合机器学习系统中的模块更新问题 manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (10 篇)

#题目一句话要点标签🔗⭐
35 From World Models to World Action Models: A Concise Tutorial for Robotics 提出世界动作模型以增强机器人控制能力 policy learning world model world models
36 Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs 提出任务无关的预训练方法以解决VLA模型的专家演示稀缺问题 behavior cloning embodied AI vision-language-action
37 Transport Discrepancy as a Reliability Signal for Vision-Language-Action Models 提出DiG模块以解决VLA模型的可靠性评估问题 flow matching vision-language-action VLA
38 SPLC: Social Preference Learning for Crowd Robot Navigation 提出SPLC算法以解决人群机器人导航中的奖励设计问题 reinforcement learning offline RL offline reinforcement learning
39 WaveLander: A Generalizable Hierarchical Control Framework for UAV Landing on Wave-Disturbed Platforms via Reinforcement Learning 提出WaveLander以解决无人机在波动平台上着陆问题 reinforcement learning motion prediction
40 Lightweight Safe Reinforcement Learning for End-to-End UAV Navigation 提出安全约束感知控制框架以解决无人机导航问题 reinforcement learning PPO curriculum learning
41 DynFly: Dynamic-Aware Continuous Trajectory Generation for UAV Vision-Language Navigation in Urban Environments 提出DynFly以解决UAV视觉语言导航中的轨迹生成问题 flow matching VLN multimodal
42 Cross-Platform Control for Autonomous Surface Vehicles via Adaptive Reinforcement Learning 提出自适应强化学习方法以实现自主水面车辆的跨平台控制 reinforcement learning teacher-student
43 Simulation Based Reward Function Validation for Multi-Agent On Orbit Inspection 提出基于仿真的奖励函数验证方法以优化多智能体轨道检查 reinforcement learning 3D reconstruction
44 Learning Agile Intruder Interception using Differentiable Quadrotor Dynamics 提出基于可微四旋翼动力学的拦截控制策略以解决入侵者拦截问题 reinforcement learning deep reinforcement learning

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
45 A Stereo Visual SLAM System Using Object-Level Motion Estimation and Geometric Filtering Based on Cross Disparity 提出OCD SLAM以解决动态环境下SLAM精度问题 visual SLAM motion estimation
46 DL-SLAM: Enabling High-Fidelity Gaussian Splatting SLAM in Dynamic Environments based on Dual-Level Probability 提出DL-SLAM以解决动态环境下SLAM中的伪影问题 3D gaussian splatting 3DGS gaussian splatting
47 SE(2) Navigation Mesh 提出SE(2)导航网格以解决复杂环境中的路径规划问题 traversability

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
48 VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models 提出VLA-Arena以解决视觉-语言-动作模型的评估问题 vision-language-action VLA
49 CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation 提出CoFL-S以解决低级动作表示不足的问题 vision-language-action VLN language conditioned
50 Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots 提出Embodied.cpp以解决异构机器人上嵌入式AI模型部署问题 embodied AI vision-language-action VLA

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
51 Controllable Sim Agents with Behavior Latents 提出可控神经变分代理以解决交通模拟中的行为可控性问题 classifier-free guidance

⬅️ 返回 cs.RO 首页 · 🏠 返回主页