cs.RO（2025-03-11）

📊 共 41 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (30 🔗3) 支柱三：空间感知与语义 (Perception & Semantics) (4 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (30 篇)

#题目一句话要点标签🔗⭐
1 Distillation-PPO: A Novel Two-Stage Reinforcement Learning Framework for Humanoid Robot Perceptive Locomotion 提出Distillation-PPO，用于提升人型机器人感知运动的强化学习框架 humanoid humanoid robot locomotion
2 MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models MoRE：四足机器人视觉-语言-动作模型强化学习扩展性方案 quadruped reinforcement learning vision-language-action
3 Instruction-Augmented Long-Horizon Planning: Embedding Grounding Mechanisms in Embodied Mobile Manipulation 提出指令增强的长程规划系统，解决具身移动操作中LLM规划器的环境理解不足问题 humanoid humanoid robot manipulation
4 LiPS: Large-Scale Humanoid Robot Reinforcement Learning with Parallel-Series Structures LiPS：基于并联-串联结构的大规模人形机器人强化学习方法 humanoid humanoid robot sim2real
5 EMMOE: A Comprehensive Benchmark for Embodied Mobile Manipulation in Open Environments EMMOE：开放环境中具身移动操作的综合基准测试 manipulation mobile manipulation DPO
6 Trajectory Optimization for In-Hand Manipulation with Tactile Force Control 提出基于触觉力控制的灵巧手内操作轨迹优化框架，提升操作精度和鲁棒性 manipulation in-hand manipulation trajectory optimization
7 Cross-Embodiment Robotic Manipulation Synthesis via Guided Demonstrations through CycleVAE and Human Behavior Transformer 提出基于CycleVAE和人类行为Transformer的跨具身机器人操作合成方法 manipulation motion planning cross-embodiment
8 Trinity: A Modular Humanoid Robot AI System Trinity：融合强化学习、大语言模型和视觉语言模型的人形机器人AI系统 humanoid humanoid robot reinforcement learning
9 Proc4Gem: Foundation models for physical agency through procedural generation Proc4Gem：通过程序化生成赋能物理智能的基础模型 quadruped whole-body control foundation model
10 MoE-Loco: Mixture of Experts for Multitask Locomotion MoE-Loco：面向多任务运动的混合专家模型，提升腿式机器人泛化性 quadruped legged robot bipedal
11 Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion 提出CrossQ算法，实现四足机器人8分钟内高效学习全向运动 quadruped legged robot locomotion
12 FAM-HRI: Foundation-Model Assisted Multi-Modal Human-Robot Interaction Combining Gaze and Speech FAM-HRI：基于Foundation Model融合注视与语音的多模态人机交互 manipulation large language model foundation model
13 Hierarchical Contact-Rich Trajectory Optimization for Multi-Modal Manipulation using Tight Convex Relaxations 提出一种分层轨迹优化框架，利用紧凸松弛解决多接触操作中的轨迹规划问题 manipulation bi-manual trajectory optimization
14 General-Purpose Aerial Intelligent Agents Empowered by Large Language Models 提出基于大语言模型的通用无人机智能体，实现开放环境任务执行 motion planning scene understanding large language model
15 TLA: Tactile-Language-Action Model for Contact-Rich Manipulation 提出TLA模型，利用触觉-语言-动作融合提升接触式操作的机器人灵活性 manipulation imitation learning diffusion policy
16 MetaFold: Language-Guided Multi-Category Garment Folding Framework via Trajectory Generation and Foundation Model MetaFold：基于轨迹生成和基础模型的语言引导多类别服装折叠框架 manipulation foundation model ✅
17 ForceGrip: Reference-Free Curriculum Learning for Realistic Grip Force Control in VR Hand Manipulation ForceGrip：一种虚拟现实手部操作中逼真握力控制的无参考课程学习方法 manipulation curriculum learning ✅
18 Cooperative Bearing-Only Target Pursuit via Multiagent Reinforcement Learning: Design and Experiment 提出基于多智能体强化学习的协同方位角目标追踪方法，解决异构环境下的未知目标追踪问题。 sim-to-real reinforcement learning zero-shot transfer
19 FP3: A 3D Foundation Policy for Robotic Manipulation 提出FP3：用于机器人操作的3D基础策略模型，提升泛化能力。 manipulation foundation model
20 Geometric Data-Driven Multi-Jet Locomotion Inspired by Salps 受樽海鞘启发，提出几何数据驱动的多喷射运动控制框架，应用于陆地机器人LandSalp。 locomotion motion planning
21 DG16M: A Large-Scale Dataset for Dual-Arm Grasping with Force-Optimized Grasps 提出DG16M大规模双臂抓取数据集，优化力闭合约束并提升抓取性能。 manipulation dual-arm
22 Elastic Motion Policy: An Adaptive Dynamical System for Robust and Efficient One-Shot Imitation Learning 提出弹性运动策略以解决模仿学习中的泛化问题 motion planning imitation learning behavior cloning ✅
23 Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies FAIL-Detect：一种基于不确定性的模仿学习策略运行时故障检测方法，无需故障数据。 manipulation imitation learning
24 Adaptive Anomaly Recovery for Telemanipulation: A Diffusion Model Approach to Vision-Based Tracking 提出DET框架，利用扩散模型进行遥操作中的视觉异常恢复，提升系统鲁棒性。 manipulation
25 Bio-Skin: A Cost-Effective Thermostatic Tactile Sensor with Multi-Modal Force and Temperature Detection Bio-Skin：一种低成本、多模态力温触觉传感器，用于类人机器人交互 humanoid humanoid robot
26 Soft Actor-Critic-based Control Barrier Adaptation for Robust Autonomous Navigation in Unknown Environments 提出基于SAC的CBF参数自适应方法，提升未知环境自主导航的鲁棒性 motion planning SAC
27 SICNav-Diffusion: Safe and Interactive Crowd Navigation with Diffusion Trajectory Predictions 提出SICNav-Diffusion，通过扩散模型预测轨迹，实现安全交互式人群导航 MPC
28 Deformable Linear Object Surface Placement Using Elastica Planning and Local Shape Control 提出基于弹性规划的变形线性物体表面放置方法以解决机器人操作难题 manipulation
29 Efficient Trajectory Generation Based on Traversable Planes in 3D Complex Architectural Spaces 提出基于可通行平面的高效轨迹生成方法，用于复杂建筑空间中的地面机器人导航。 trajectory optimization
30 HEATS: A Hierarchical Framework for Efficient Autonomous Target Search with Mobile Manipulators HEATS：一种用于移动机械臂高效自主目标搜索的分层框架 motion planning

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

#题目一句话要点标签🔗⭐
31 Collaborative Dynamic 3D Scene Graphs for Open-Vocabulary Urban Scene Understanding 提出CURB-OSG，用于开放词汇城市场景理解的协同动态3D场景图构建。 scene understanding open-vocabulary open vocabulary
32 GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splats GigaSLAM：首个基于分层高斯溅射的大规模单目SLAM系统，适用于室外环境。 metric depth 3D gaussian splatting 3DGS ✅
33 Uni-Gaussians: Unifying Camera and Lidar Simulation with Gaussians for Dynamic Driving Scenarios 提出统一高斯方法以解决动态驾驶场景中的传感器模拟问题 gaussian splatting splatting NeRF
34 QLIO: Quantized LiDAR-Inertial Odometry QLIO：一种用于资源受限平台的高效量化激光雷达惯性里程计 LIO

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
35 Investigating the Effectiveness of a Socratic Chain-of-Thoughts Reasoning Method for Task Planning in Robotics, A Case Study 探索性研究：基于苏格拉底式思维链的LLM在机器人任务规划中的有效性 embodied AI large language model chain-of-thought
36 LightPlanner: Unleashing the Reasoning Capabilities of Lightweight Large Language Models in Task Planning LightPlanner通过参数化函数调用和分层推理，提升轻量级LLM在复杂任务规划中的性能。 large language model
37 Reasoning in visual navigation of end-to-end trained agents: a dynamical systems approach 基于动态系统方法，研究端到端训练智能体在视觉导航中的推理能力 embodied AI language conditioned
38 LLM-Pack: Intuitive Grocery Handling for Logistics Applications LLM-Pack：利用LLM解决物流场景下直观的杂货装箱问题 foundation model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
39 Hybrid Deep Reinforcement Learning for Radio Tracer Localisation in Robotic-assisted Radioguided Surgery 提出混合深度强化学习方法，用于机器人辅助放射性示踪剂定位 reinforcement learning deep reinforcement learning DRL
40 Multitask Reinforcement Learning for Quadcopter Attitude Stabilization and Tracking using Graph Policy 提出基于图策略的多任务强化学习方法，用于四旋翼飞行器姿态稳定与跟踪。 reinforcement learning deep reinforcement learning SAC ✅
41 The Impact of VR and 2D Interfaces on Human Feedback in Preference-Based Robot Learning 研究VR与2D界面对基于人类反馈机器人学习中偏好收集的影响 reinforcement learning RLHF

⬅️ 返回 cs.RO 首页 · 🏠 返回主页