cs.RO（2026-09-01）

📊 共 20 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (15 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱一：机器人控制 (Robot Control) (15 篇)

#	题目	一句话要点	标签	🔗	⭐
1	A System for Fast, Resilient, and Adaptable Loco-Manipulation Behaviors on Humanoid Robots	提出一种快速、弹性和适应性强的人形机器人运动操控行为系统	humanoid humanoid robot whole-body control
2	Facet-0: A Robotic Foundation Model for Contact-Rich Precise Manipulation	提出Facet-0以解决机器人精确操作中的接触问题	manipulation reinforcement learning flow matching
3	ADAPT: Agile Diffusion Action Priors for Robust and Steerable Online Text-Driven Humanoid Control	提出ADAPT框架以解决文本驱动的人形机器人控制问题	humanoid humanoid control whole-body control
4	Does Imitation Learning Preserve Temporal Robustness in Dexterous Manipulation? An Expert-Learner Comparison Across Task Execution Speeds	比较模仿学习与专家在灵巧操作中的时间鲁棒性	manipulation dexterous manipulation imitation learning	✅
5	Accelerating Reinforcement Learning via MPC Solver-Gradient Guidance for Weights-varying MPC	提出SG-RL以解决MPC权重在线适应问题	MPC model predictive control reinforcement learning
6	Knowing When to Stop: Adaptive Action Chunking via Internal Cross-Attention Dynamics in VLAs	提出自适应动作分块方法以解决固定执行视角的效率与准确性问题	manipulation vision-language-action VLA
7	SG-AMP: Scene-Graph-Guided Active Perception and Semantics-Aware Motion Planning for Pepper Plants	提出SG-AMP以解决辣椒植物的主动感知与运动规划问题	motion planning AMP
8	AM-Bench: A Modular Simulation Suite and Benchmark for Aerial Manipulation Policy Learning	提出AM-Bench以解决无人机操控学习中的标准化评估问题	manipulation policy learning
9	Importance and methods to control, vary, and characterize mud strength for studying locomotion	提出控制和表征泥浆强度的方法以研究动物和机器人运动	locomotion penetration
10	ProxPI: Proximal Prior Injection for Sampling-Based MPC under Learned-Prior Mismatch	提出ProxPI以解决学习策略与模型预测控制不匹配问题	MPC model predictive control
11	Exploring Nonlinear Body Oscillations for Natural Quadruped Gaits	提出利用非线性体振动实现自然四足步态的框架	quadruped locomotion
12	Non-Prehensile Throwing: A Reinforcement Learning Perspective	提出强化学习方法以解决非抓取投掷问题	sim-to-real reinforcement learning
13	A Wearable Pneumatic Device for Continuous, Closed-Loop, Bidirectional Tactile Interaction	提出可穿戴气动设备以实现双向触觉交互	manipulation teleoperation
14	Peg-in-Bench: A Modular Benchmark for High-Precision Robotic Insertion	提出可重构的基准测试以解决高精度机器人插入问题	manipulation	✅
15	Mudskippers use tail thrusting to help crutching to move on mud of various wetness	研究泥鳅在不同湿度泥土中使用尾部推力辅助移动	locomotion

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

#	题目	一句话要点	标签	🔗	⭐
16	Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching	提出DroneCATS-Agent以解决无人机控制中的多模态决策问题	vision-language-action large language model multimodal
17	EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA Agents	提出EmbodiedSkills框架以解决长时间任务中的VLA代理协调问题	vision-language-action VLA
18	VerNav: Verifier-First Low-Latency Vision-and-Language Navigation	提出VerNav框架以解决低延迟视觉语言导航问题	VLN

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
19	DSG: Dynamic 3D Scene Graph Construction for Embodied Agents in Changing Indoor Environments	提出DSG框架以解决动态室内环境中的场景图构建问题	spatial relationship large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
20	Potential-Guided Particle Steering for Negation-Constrained Dexterous Grasping	提出潜在引导粒子引导以解决否定约束灵巧抓取问题	classifier-free guidance

⬅️ 返回 cs.RO 首页 · 🏠 返回主页