The paradigm of learning-from-observation (LfO) enables a robot to learn how to perform actions by observing human-demonstrated actions. Previous research in LfO have mainly focused on the industrial domain which only consist of the observable physical constraints between a manipulating tool and the robot's working environment. In order to extend this paradigm to the household domain which consists non-observable constraints derived from a human's common sense; we introduce the idea of semantic constraints. The semantic constraints are represented similar to the physical constraints by defining a contact with an imaginary semantic environment. We thoroughly investigate the necessary and sufficient set of contact state and state transitions to understand the different types of physical and semantic constraints. We then apply our constraint representation to analyze various actions in top hit household YouTube videos and real home cooking recordings. We further categorize the frequently appearing constraint patterns into physical, semantic, and multistage task groups and verify that these groups are not only necessary but a sufficient set for covering standard household actions. Finally, we conduct a preliminary experiment using textual input to explore the possibilities of combining verbal and visual input for recognizing the task groups. Our results provide promising directions for incorporating common sense in the literature of robot teaching.
Otto-von-Guericke University Magdeburg（马格德堡奥托·冯·格里克大学）；Jacobs University（雅各布大学）；Technische Universität Bergakademie Freiberg（弗赖贝格工业大学）；OFFIS Institute for Information Technology（奥弗斯信息技术研究所）
Tool-use applications in robotics require conceptual knowledge about objects for informed decision making and object interactions. State-of-the-art methods employ hand-crafted symbolic knowledge which is defined from a human perspective and grounded into sensory data afterwards. However, due to different sensing and acting capabilities of robots, their conceptual understanding of objects must be generated from a robot's perspective entirely, which asks for robot-centric conceptual knowledge about objects. With this goal in mind, this article motivates that such knowledge should be based on phy…
Robustness Testing of Multi-Modal Models in Varied Home Environments for Assistive Robots
Ludwig Maximilian University of Munich（慕尼黑大学）；Institute for Information and Language Processing（信息与语言处理研究所）；Munich Center of Machine Learning (MCML)（慕尼黑机器学习中心）
Smart Help: Strategic Opponent Modeling for Proactive and Adaptive Robot Assistance in Households
Beijing Institute for General Artificial Intelligence (BIGAI)（北京通用人工智能研究院）；State Key Laboratory of General Artificial Intelligence（通用人工智能国家重点实验室）；Tsinghua University（清华大学）；Peking University（北京大学）；University of California, Los Angeles（加州大学洛杉矶分校）
Semantic 3D scene understanding is a problem of critical importance in robotics. While significant advances have been made in simultaneous localization and mapping algorithms, robots are still far from having the common sense knowledge about household objects and their locations of an average human. We introduce a novel method for leveraging common sense embedded within large language models for labelling rooms given the objects contained within. This algorithm has the added benefits of (i) requiring no task-specific pre-training (operating entirely in the zero-shot regime) and (ii) generalizi…
The sense of touch is fundamental in several manipulation tasks, but rarely used in robot manipulation. In this work we tackle the problem of learning rich touch features from cross-modal self-supervision. We evaluate them identifying objects and their properties in a few-shot classification setting. Two new datasets are introduced using a simulated anthropomorphic robotic hand equipped with tactile sensors on both synthetic and daily life objects. Several self-supervised learning methods are benchmarked on these datasets, by evaluating few-shot classification on unseen objects and poses. Our …
PlanAgent: A Multi-modal Large Language Agent for Closed-loop Vehicle Motion Planning
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Beijing University of Posts and Telecommunications（北京邮电大学）；School of Mechanical Engineering and Automation, Beihang University（北京航空航天大学）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Li Auto（理想汽车）
Wearable electronic equipment is constantly evolving and is increasing the integration of humans with technology. Available in various forms, these flexible and bendable devices sense and can measure the physiological and muscular changes in the human body and may use those signals to machine control. The MYO gesture band, one such device, captures Electromyography data (EMG) using myoelectric signals and translates them to be used as input signals through some predefined gestures. Use of this device in a multi-modal environment will not only increase the possible types of work that can be acc…
Contact-rich manipulation tasks in unstructured environments often require both haptic and visual feedback. It is non-trivial to manually design a robot controller that combines these modalities which have very different characteristics. While deep reinforcement learning has shown success in learning control policies for high-dimensional inputs, these algorithms are generally intractable to deploy on real robots due to sample complexity. In this work, we use self-supervision to learn a compact and multimodal representation of our sensory inputs, which can then be used to improve the sample eff…
Contact-rich manipulation tasks in unstructured environments often require both haptic and visual feedback. However, it is non-trivial to manually design a robot controller that combines modalities with very different characteristics. While deep reinforcement learning has shown success in learning control policies for high-dimensional inputs, these algorithms are generally intractable to deploy on real robots due to sample complexity. We use self-supervision to learn a compact and multimodal representation of our sensory inputs, which can then be used to improve the sample efficiency of our po…
