Estimating the region of attraction (${\tt RoA}$) for a robot controller is essential for safe application and controller composition. Many existing methods require a closed-form expression that limit applicability to data-driven controllers. Methods that operate only over trajectory rollouts tend to be data-hungry. In prior work, we have demonstrated that topological tools based on ${\it Morse Graphs}$ (directed acyclic graphs that combinatorially represent the underlying nonlinear dynamics) offer data-efficient ${\tt RoA}$ estimation without needing an analytical model. They struggle, however, with high-dimensional systems as they operate over a state-space discretization. This paper presents ${\it Mo}$rse Graph-aided discovery of ${\it R}$egions of ${\it A}$ttraction in a learned ${\it L}$atent ${\it S}$pace (${\tt MORALS}$). The approach combines auto-encoding neural networks with Morse Graphs. ${\tt MORALS}$ shows promising predictive capabilities in estimating attractors and their ${\tt RoA}$s for data-driven controllers operating over high-dimensional systems, including a 67-dim humanoid robot and a 96-dim 3-fingered manipulator. It first projects the dynamics of the controlled system into a learned latent space. Then, it constructs a reduced form of Morse Graphs representing the bistability of the underlying dynamics, i.e., detecting when the controller results in a desired versus an undesired behavior. The evaluation on high-dimensional robotic datasets indicates data efficiency in ${\tt RoA}$ estimation.
M3imic: Learning a Versatile Whole-Body Controller for Multimodal Motion Mimicking
School of Automation, Southeast University(东南大学自动化学院);School of Vehicle and Mobility, Tsinghua University(清华大学车辆与移动性学院);Department of Robotics, Mohamed Bin Zayed University of Artificial Intelligence(马尔代夫比兹亚德大学人工智能学院机器人系)
我们介绍了智能潜在动作(LILA),一个框架,用于学习自然语言接口的背景下,人机协作。LILA属于共享自治范例:除了提供离散的语言输入之外,人类还被给予低维控制器$-$,例如,2自由度(DoF)操纵杆,其可以向左/右和上/下移动$-$以操作机器人。LILA学习使用语言来调节这个控制器,为用户提供一个语言通知的控制空间:给定一个指令,如“将谷物碗放在托盘上”,LILA可以学习一个2-DoF空间,其中一个维度控制机器人的末端执行器到碗的距离,另一个维度控制机器人的末端执行器相对于碗上的抓取点的姿势。我们通过真实世界的用户研究来评估LILA,用户可以在操作7自由度Franka Panda Arm的同时提供语言指令,以完成一系列复杂的操作任务。我们发现LILA模型不仅比模仿学习和末端效应器控制基线更有效,而且它们在质量上也是用户首选的。
From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance
University of Sydney(悉尼大学);BAAI(北京人工智能研究院);Harbin Institute of Technology(哈尔滨工业大学);Hong Kong University of Science and Technology(香港科学与技术大学);Shanghai Jiao Tong University(上海交通大学);Peking University(北京大学)
Sparse Representation Learning with Modified q-VAE towards Minimal Realization of World Model
National Institute of Informatics(信息学研究所);The Graduate University for Advanced Studies (SOKENDAI)(高级研究大学院大学(SOKENDAI));Nara Institute of Science and Technology(奈良科学技术研究所)
Prescribed Performance Control of Deformable Object Manipulation in Spatial Latent Space
Department of Mechanical Engineering, The Hong Kong Polytechnic University(机械工程系,香港理工大学);T Stone Robotics Institute, Department of Mechanical and Automation Eng., The Chinese University of Hong Kong(T Stone机器人研究所,机械与自动化工程系,香港中文大学)