cs.RO（2025-09-18）

📊 共 22 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (16 🔗4) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱三：空间感知与语义 (Perception & Semantics) (2)

🔬 支柱一：机器人控制 (Robot Control) (16 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Implicit Kinodynamic Motion Retargeting for Human-to-humanoid Imitation Learning	提出隐式运动动力学重定向(IKMR)，实现高效的人形机器人模仿学习。	humanoid humanoid robot whole-body control
2	RealMirror: A Comprehensive, Open-Source Vision-Language-Action Platform for Embodied AI	RealMirror：为具身AI打造的全面开源视觉-语言-动作平台	humanoid humanoid robot sim2real	✅
3	A Novel Task-Driven Diffusion-Based Policy with Affordance Learning for Generalizable Manipulation of Articulated Objects	提出DART：一种基于可供性学习和扩散策略的通用铰接物体操作方法	manipulation dexterous manipulation reinforcement learning
4	M4Diffuser: Multi-View Diffusion Policy with Manipulability-Aware Control for Robust Mobile Manipulation	M4Diffuser：多视角扩散策略与可操作性感知控制，提升移动操作的鲁棒性	manipulation mobile manipulation diffusion policy
5	The Role of Touch: Towards Optimal Tactile Sensing Distribution in Anthropomorphic Hands for Dexterous In-Hand Manipulation	研究触觉在灵巧手内操作中的作用，优化拟人手部的触觉传感器分布	manipulation in-hand manipulation reinforcement learning
6	Robot Control Stack: A Lean Ecosystem for Robot Learning at Scale	提出Robot Control Stack (RCS)，用于大规模机器人学习的精简生态系统	sim-to-real vision-language-action VLA
7	Toward Embodiment Equivariant Vision-Language-Action Policy	提出具身等变视觉-语言-动作策略，提升机器人泛化能力	manipulation cross-embodiment vision-language-action	✅
8	CAD-Driven Co-Design for Flight-Ready Jet-Powered Humanoids	提出CAD驱动的协同设计框架，优化喷气动力人形机器人的飞行性能	humanoid humanoid robot MPC
9	Dual-Arm Hierarchical Planning for Laboratory Automation: Vibratory Sieve Shaker Operations	提出双臂机器人分层规划框架，实现振动筛分机操作自动化	manipulation bi-manual dual-arm
10	Scalable Multi-Objective Robot Reinforcement Learning through Gradient Conflict Resolution	提出GCR-PPO以解决多目标机器人强化学习中的梯度冲突问题	locomotion manipulation reinforcement learning	✅
11	COMPASS: Confined-space Manipulation Planning with Active Sensing Strategy	提出COMPASS框架，解决受限空间内基于主动感知的操作规划问题	manipulation
12	Learning to Pick: A Visuomotor Policy for Clustered Strawberry Picking	提出基于模仿学习的草莓采摘策略，解决遮挡环境下机器人采摘难题	manipulation dexterous manipulation teleoperation
13	exUMI: Extensible Robot Teaching System with Action-aware Task-agnostic Tactile Representation	exUMI：基于动作感知的触觉表示，可扩展的机器人教学系统	manipulation imitation learning representation learning	✅
14	ExT: Towards Scalable Autonomous Excavation via Large-Scale Multi-Task Pretraining and Fine-Tuning	ExT：基于大规模多任务预训练和微调实现可扩展的自主挖掘	manipulation reinforcement learning
15	Sym2Real: Symbolic Dynamics with Residual Learning for Data-Efficient Adaptive Control	Sym2Real：结合符号回归与残差学习，实现数据高效的自适应控制	sim2real
16	DIPP: Discriminative Impact Point Predictor for Catching Diverse In-Flight Objects	提出DIPP模型，用于四足机器人接取空中飞行物体的落点预测，提升复杂环境下的泛化性。	quadruped

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

#	题目	一句话要点	标签	🔗	⭐
17	CollabVLA: Self-Reflective Vision-Language-Action Model Dreaming Together with Human	CollabVLA：提出自反思的视觉-语言-动作模型，实现人机协同	vision-language-action VLA
18	Embodied Arena: A Comprehensive, Unified, and Evolving Evaluation Platform for Embodied AI	Embodied Arena：构建全面、统一、可演进的具身智能评估平台	embodied AI foundation model
19	Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue	提出Ask-to-Clarify框架，通过多轮对话解决具身智能体指令模糊问题	VLA
20	PA-MPPI: Perception-Aware Model Predictive Path Integral Control for Quadrotor Navigation in Unknown Environments	提出感知驱动的MPPI算法，提升四旋翼无人机在未知环境中的导航能力	foundation model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
21	Affordance-Based Disambiguation of Surgical Instructions for Collaborative Robot-Assisted Surgery	提出基于可供性的手术指令消歧框架，用于协作机器人辅助手术	affordance multimodal
22	BEV-ODOM2: Enhanced BEV-based Monocular Visual Odometry with PV-BEV Fusion and Dense Flow Supervision for Ground Robots	BEV-ODOM2：面向地面机器人的PV-BEV融合与稠密光流监督单目视觉里程计	visual odometry optical flow

⬅️ 返回 cs.RO 首页 · 🏠 返回主页