cs.RO（2025-03-03）

📊 共 39 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (25 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (7) 支柱三：空间感知与语义 (Perception & Semantics) (4 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (25 篇)

#题目一句话要点标签🔗⭐
1 Code-as-Symbolic-Planner: Foundation Model-Based Robot Planning via Symbolic Code Generation 提出Code-as-Symbolic-Planner，利用代码生成提升LLM在机器人任务规划中的能力。 motion planning large language model foundation model ✅
2 Discrete-Time Hybrid Automata Learning: Legged Locomotion Meets Skateboarding 提出DHAL框架，解决无轨迹分割的离散时间混合自动机学习问题，应用于四足机器人滑板任务。 quadruped legged robot legged locomotion
3 Few-shot Sim2Real Based on High Fidelity Rendering with Force Feedback Teleoperation 提出基于高保真渲染与力反馈遥操作的少样本Sim2Real方法 manipulation sim-to-real sim2real
4 Impact of Static Friction on Sim2Real in Robotic Reinforcement Learning 提出静摩擦感知域随机化方法，提升机器人强化学习Sim2Real在复杂地形的适应性 locomotion sim2real domain randomization
5 RoboDexVLM: Visual Language Model-Enabled Task Planning and Motion Control for Dexterous Robot Manipulation RoboDexVLM：基于视觉语言模型实现灵巧机器人操作的任务规划与运动控制 manipulation dexterous hand dexterous manipulation ✅
6 A Taxonomy for Evaluating Generalist Robot Manipulation Policies 提出STAR-Gen：通用机器人操作策略评估分类法，并提供可复现的基准测试指南 manipulation bi-manual vision-language-action
7 FRMD: Fast Robot Motion Diffusion with Consistency-Distilled Movement Primitives for Smooth Action Generation 提出FRMD：结合运动基元与一致性蒸馏的快速机器人运动扩散模型，实现平滑动作生成。 manipulation distillation motion diffusion
8 CorrA: Leveraging Large Language Models for Dynamic Obstacle Avoidance of Autonomous Vehicles CorrA：利用大语言模型实现自动驾驶车辆的动态避障 MPC model predictive control large language model
9 TacCap: A Wearable FBG-Based Tactile Sensor for Seamless Human-to-Robot Skill Transfer TacCap：一种用于无缝人-机器人技能迁移的可穿戴FBG触觉传感器 manipulation dexterous manipulation human-to-robot
10 AVR: Active Vision-Driven Precise Robot Manipulation with Viewpoint and Focal Length Optimization AVR：主动视觉驱动的精确机器人操作，优化视角和焦距 manipulation bi-manual teleoperation
11 SIMS: Surgeon-Intention-driven Motion Scaling for Efficient and Precise Teleoperation 提出基于外科医生意图的运动缩放系统SIMS，提升遥操作手术的效率和精度。 manipulation dual-arm teleoperation
12 KineSoft: Learning Proprioceptive Manipulation Policies with Soft Robot Hands KineSoft：利用软体机器人手的本体感受学习操作策略 manipulation dexterous manipulation imitation learning
13 FABG : End-to-end Imitation Learning for Embodied Affective Human-Robot Interaction 提出FABG，通过端到端模仿学习实现具身情感人机交互中自然流畅的面部情感行为生成。 humanoid humanoid robot imitation learning
14 FLAME: A Federated Learning Benchmark for Robotic Manipulation 提出FLAME：一个用于机器人操作的联邦学习基准测试平台 manipulation policy learning
15 Exo-ViHa: A Cross-Platform Exoskeleton System with Visual and Haptic Feedback for Efficient Dexterous Skill Learning Exo-ViHa：用于灵巧技能学习的跨平台视觉触觉反馈外骨骼系统 manipulation dexterous hand dexterous manipulation
16 Diffusion Stabilizer Policy for Automated Surgical Robot Manipulations 提出基于扩散稳定器策略（DSP）的自动手术机器人操作方法，提升轨迹扰动下的鲁棒性。 manipulation policy learning
17 Ground contact and reaction force sensing for linear policy control of quadruped robot 通过增强观测空间，提升四足机器人线性策略控制在复杂地形的适应性和稳定性 quadruped reinforcement learning
18 NavG: Risk-Aware Navigation in Crowded Environments Based on Reinforcement Learning with Guidance Points NavG：基于强化学习与引导点的拥挤环境风险感知导航 motion planning reinforcement learning
19 Catching Spinning Table Tennis Balls in Simulation with End-to-End Curriculum Reinforcement Learning 提出基于课程强化学习的乒乓球机器人控制方法，解决高速旋转球的接球问题 real2sim reinforcement learning
20 TACO: General Acrobatic Flight Control via Target-and-Command-Oriented Reinforcement Learning 提出TACO框架，通过目标与指令导向强化学习实现通用无人机特技飞行控制 sim-to-real reinforcement learning
21 Design and Development of a Locomotion Interface for Virtual Reality Lower-Body Haptic Interaction 设计ForceBot下肢触觉交互 locomotion 接口，实现VR中行走和地形交互 locomotion
22 Optimal Trajectory Planning for Cooperative Manipulation with Multiple Quadrotors Using Control Barrier Functions 提出基于控制屏障函数的多无人机协同操作轨迹优化算法，解决复杂环境下的安全操作问题。 manipulation
23 Interactive Navigation for Legged Manipulators with Learned Arm-Pushing Controller 针对腿式机械臂，提出基于强化学习的交互式导航方法，解决狭窄空间操作难题。 manipulation reinforcement learning ✅
24 Aerial Gym Simulator: A Framework for Highly Parallelized Simulation of Aerial Robots 提出Aerial Gym：一个用于无人机高并行仿真与渲染的框架 sim2real reinforcement learning ✅
25 No Plan but Everything Under Control: Robustly Solving Sequential Tasks with Dynamically Composed Gradient Descent 提出动态梯度下降方法，无需规划即可稳健解决序列任务 manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
26 Stone Soup Multi-Target Tracking Feature Extraction For Autonomous Search And Track In Deep Reinforcement Learning Environment 利用Stone Soup特征提取，提出深度强化学习自主搜索跟踪方法 reinforcement learning deep reinforcement learning DRL
27 Enhancing Deep Reinforcement Learning-based Robot Navigation Generalization through Scenario Augmentation 提出场景增强方法，提升深度强化学习机器人导航在未知环境的泛化性 reinforcement learning deep reinforcement learning
28 Beyond Visibility Limits: A DRL-Based Navigation Strategy for Unexpected Obstacles 提出基于DRL-NSUO的导航策略，解决动态环境中受限视野下意外障碍物的避障问题 reinforcement learning deep reinforcement learning DRL
29 Action Tokenizer Matters in In-Context Imitation Learning 提出LipVQ-VAE，解决ICIL中动作Tokenizer忽略时序平滑性的问题 imitation learning VQ-VAE
30 Active Alignments of Lens Systems with Reinforcement Learning 提出基于强化学习的光学镜头主动对准方法，提升相机制造效率。 reinforcement learning
31 MapExRL: Human-Inspired Indoor Exploration with Predicted Environment Context and Reinforcement Learning MapExRL：结合环境上下文预测与强化学习的室内机器人探索 reinforcement learning
32 An energy-efficient learning solution for the Agile Earth Observation Satellite Scheduling Problem 提出一种节能的深度强化学习方法，解决敏捷地球观测卫星调度问题 reinforcement learning deep reinforcement learning DRL

🔬 支柱三：空间感知与语义 (Perception & Semantics) (4 篇)

#题目一句话要点标签🔗⭐
33 OVAMOS: A Framework for Open-Vocabulary Multi-Object Search in Unknown Environments 提出OVAMOS框架，解决未知环境中开放词汇多目标搜索问题 open-vocabulary open vocabulary foundation model
34 vS-Graphs: Tightly Coupling Visual SLAM and 3D Scene Graphs Exploiting Hierarchical Scene Understanding 提出vS-Graphs以解决VSLAM语义丰富性不足问题 visual SLAM scene understanding ✅
35 MLINE-VINS: Robust Monocular Visual-Inertial SLAM With Flow Manhattan and Line Features MLINE-VINS：结合光流曼哈顿和线特征的鲁棒单目视觉惯性SLAM VIO optical flow ✅
36 DnD Filter: Differentiable State Estimation for Dynamic Systems using Diffusion Models DnD Filter：利用扩散模型实现动态系统可微状态估计 visual odometry

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

#题目一句话要点标签🔗⭐
37 CognitiveDrone: A VLA Model and Evaluation Benchmark for Real-Time Cognitive Task Solving and Reasoning in UAVs 提出CognitiveDrone，用于无人机实时认知任务求解与推理的VLA模型与评估基准。 vision-language-action VLA
38 LLM-Advisor: An LLM Benchmark for Cost-efficient Path Planning across Multiple Terrains LLM-Advisor：用于多地形成本高效路径规划的LLM基准测试 large language model
39 Language-Guided Object Search in Agricultural Environments 提出基于LLM的农业环境目标物搜索方法，提升机器人自主定位效率 large language model ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页