cs.RO（2026-08-31）

📊 共 19 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (12 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (12 篇)

#题目一句话要点标签🔗⭐
1 Motus2: A Self-Evolving General World Model for Dexterous Manipulation 提出Motus2以解决通用世界模型在灵巧操作中的不足 manipulation dexterous hand dexterous manipulation
2 Temporal Forcing: 4D Representation Alignment for Vision-Language-Action Models 提出Temporal Forcing以解决长时间操作中的观察别名问题 manipulation vision-language-action VLA
3 Behavior-Skill: A Fine-Grained Benchmark for Evaluating Vision-Language-Action Policies in Long-Horizon Tasks 提出Behavior-Skill基准以解决长时间任务评估中的技能分析问题 manipulation mobile manipulation vision-language-action ✅
4 SleepWalking: Privileged Representation Shaping for End-to-End Blind Locomotion in Legged Robots 提出SleepWalking以解决盲目运动中的信息保留问题 legged robot locomotion policy learning
5 DARP: A Calibrated Dual-Arm RGB-D-IR Dataset for Multi-View Robotic Perception 提出DARP数据集以解决多视角机器人感知问题 dual-arm geometric consistency multimodal
6 CometVLA: Co-Training on an Embodied Data Pyramid towards Physical Understanding 提出CometVLA以解决物理常识不足的问题 manipulation teleoperation egocentric
7 Zeva: In-Context Causal Learning for Generalizable Embodied Manipulation 提出Zeva框架以解决机器人自我学习的挑战 manipulation VLA
8 SUN: Persistent Programs For Language-Grounded Control-to-Learning-to-Real Policies 提出SUN程序以解决长时间操作中的控制与学习统一问题 manipulation MPC model predictive control
9 Autonomously Acquiring Robot Manipulation Skills with Language-Driven Quality-Diversity 提出一种基于语言驱动的质量多样性方法以提升机器人自主技能 manipulation reward shaping
10 Provably Safe Decentralized Contingency MPC under State-Only Information and Limited Sensing for Nonlinear Multi-agent Systems 提出去中心化应急MPC以解决多智能体系统的安全控制问题 MPC
11 A Dual-Cam Parallel Elastic Actuator with Shared Gas-Spring Compensation for Humanoid Ankles 提出双凸轮并联弹性驱动器以解决类人脚踝扭矩补偿问题 humanoid
12 Learning to infer and manipulate through distributed whole-arm interaction in a soft robot 提出物理智能框架以解决软机器人交互信息推断问题 manipulation sim-to-real reinforcement learning

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
13 Open-Source Autonomous Driving System Analysis and Multi-Disciplinary Hardware-in-the-Loop Research Paradigm with Reinforcement-Learning Testing and Large Language Models 提出基于强化学习和大语言模型的多学科硬件在环实验框架以解决自动驾驶系统实验记录问题 reinforcement learning large language model
14 LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation 提出LightNav-0以解决通用体态导航中的空间智能问题 reinforcement learning open-vocabulary open vocabulary
15 CIG-RL: Curiosity-Driven Information-Guided Reinforcement Learning for Source Term Estimation in Uncertain Environments 提出好奇驱动的信息引导强化学习以解决源项估计问题 reinforcement learning deep reinforcement learning DRL
16 PAVE: Predictive Alignment and Value-Guided Evolution for World-Action Policies 提出PAVE以解决机器人行动策略中的动态表示与行为重用问题 behavior cloning flow matching JEPA
17 CanonNav: Disentangling Navigation Behavior from Camera Geometry in Cross-Platform Visual Navigation 提出CanonNav以解决跨平台视觉导航中的行为与几何纠缠问题 imitation learning traversability

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
18 Rethinking Language's Role in Efficient VLA for Autonomous Vehicles: Toward Smarter, Trustworthy Driving 提出语言残留分类法以优化自主驾驶中的语言使用 vision-language-action VLA
19 GAFT: Geo-Anchored Fine-Tuning for Hazard Identification from Rare Failures 提出Geo-Anchored Fine-Tuning以解决稀有故障的危险识别问题 foundation model ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页