cs.RO（2026-02-06）

📊 共 23 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (16 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (16 篇)

#题目一句话要点标签🔗⭐
1 Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations HuMI：一种基于无机器人演示的人形机器人全身操作框架 humanoid manipulation whole-body manipulation
2 Now You See That: Learning End-to-End Humanoid Locomotion from Raw Pixels 提出端到端框架，从原始像素学习稳健的人形机器人运动控制 humanoid humanoid locomotion locomotion
3 HiWET: Hierarchical World-Frame End-Effector Tracking for Long-Horizon Humanoid Loco-Manipulation HiWET：用于长时程人形机器人操作的层级世界坐标末端执行器跟踪 legged locomotion humanoid locomotion
4 ECO: Energy-Constrained Optimization with Reinforcement Learning for Humanoid Walking 提出ECO框架，通过强化学习中的约束优化，提升人形机器人步行的能量效率。 humanoid humanoid robot humanoid locomotion
5 DynaRetarget: Dynamically-Feasible Retargeting using Sampling-Based Trajectory Optimization DynaRetarget：基于采样的轨迹优化实现动态可行的人形运动重定向 humanoid humanoid control manipulation
6 Think Proprioceptively: Embodied Visual Reasoning for VLA Manipulation ThinkProprio：通过具身视觉推理提升VLA模型操作性能 manipulation vision-language-action VLA
7 The Law of Task-Achieving Body Motion: Axiomatizing Success of Robot Manipulation Actions 提出任务实现型身体运动定律，用于验证机器人操作动作的正确性 manipulation mobile manipulation motion synthesis
8 Beyond the Majority: Long-tail Imitation Learning for Robotic Manipulation 提出Approaching-Phase Augmentation解决机器人操作模仿学习中的长尾问题 manipulation policy learning imitation learning ✅
9 DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos DreamDojo：基于大规模人类视频的通用机器人世界模型 teleoperation world model distillation
10 Strategizing at Speed: A Learned Model Predictive Game for Multi-Agent Drone Racing 提出学习型模型预测博弈以解决多智能体无人机竞速中的决策延迟问题 MPC model predictive control motion planning
11 SURE: Safe Uncertainty-Aware Robot-Environment Interaction using Trajectory Optimization SURE：基于轨迹优化的安全、不确定性感知机器人-环境交互 trajectory optimization
12 A compliant ankle-actuated compass walker with triggering timing control 提出触发定时控制的顺应性踝关节驱动指南针式步行者模型，提升步态效率。 biped locomotion
13 SuReNav: Superpixel Graph-based Constraint Relaxation for Navigation in Over-constrained Environments 提出SuReNav，通过超像素图约束松弛实现在过度约束环境中的导航 quadruped semantic map
14 Consensus-based optimization (CBO): Towards Global Optimality in Robotics 提出基于共识的优化算法(CBO)，用于解决机器人全局轨迹优化问题。 trajectory optimization
15 RAPID: Reconfigurable, Adaptive Platform for Iterative Design RAPID：用于迭代设计的可重构自适应机器人平台 manipulation
16 MultiGraspNet: A Multitask 3D Vision Model for Multi-gripper Robotic Grasping MultiGraspNet：用于多夹爪机器人抓取的3D视觉多任务模型 dual-arm

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
17 World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy 提出World-VLA-Loop，用于视频世界模型和VLA策略的闭环学习，提升机器人操作性能。 reinforcement learning policy learning world model ✅
18 Force Generative Imitation Learning: Bridging Position Trajectory and Force Commands through Control Technique 提出基于反馈控制的力生成模仿学习，解决接触任务中力指令生成难题 imitation learning vision-language-action VLA
19 Crowd-FM: Learned Optimal Selection of Conditional Flow Matching-generated Trajectories for Crowd Navigation Crowd-FM：基于条件流匹配的轨迹选择方法，用于人群导航 flow matching
20 Nipping the Drift in the Bud: Retrospective Rectification for Robust Vision-Language Navigation BudVLN：通过回溯修正解决视觉-语言导航中的漂移问题 imitation learning VLN

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

#题目一句话要点标签🔗⭐
21 Realistic Synthetic Household Data Generation at Scale 提出一种可扩展的逼真家庭环境合成数据生成框架，用于具身智能研究。 embodied AI foundation model
22 Action Hallucination in Generative Visual-Language-Action Models 分析生成式视觉-语言-动作模型中的动作幻觉问题，揭示其与模型结构不匹配的关联 vision-language-action foundation model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
23 A novel Integrated Motion Tracking Device (IMTD) for Objective Laparoscopic Training Assessment: Development and Validation 提出一种用于腹腔镜训练评估的新型集成运动跟踪设备(IMTD)。 motion tracking

⬅️ 返回 cs.RO 首页 · 🏠 返回主页