Litcius/Paper detail

Learn to Predict How Humans Manipulate Large-Sized Objects From Interactive Motions

Weilin Wan, Lei Yang, Lingjie Liu, Zhuoying Zhang, Ruixing Jia, Yi‐King Choi, Jia Pan, Christian Theobalt, Taku Komura, Wenping Wang

2022IEEE Robotics and Automation Letters21 citationsDOIOpen Access PDF

Abstract

Understanding human intentions during interactions has been a long-lasting theme, that has applications in human-robot interaction, virtual reality and surveillance. In this study, we focus on full-body human interactions with large-sized daily objects and aim to predict the future states of objects and humans given a sequential observation of human-object interaction. As there is no such dataset dedicated to full-body human interactions with large-sized daily objects, we collected a large-scale dataset containing thousands of interactions for training and evaluation purposes. We also observe that an object’s intrinsic physical properties are useful for the object motion prediction, and thus design a set of object dynamic descriptors to encode such intrinsic properties. We treat the object dynamic descriptors as a new modality and propose a graph neural network, HO-GCN, to fuse motion data and dynamic descriptors for the prediction task. We show the proposed network that consumes dynamic descriptors can achieve state-of-the-art prediction results and help the network better generalize to unseen objects. We also demonstrate the predicted results are useful for human-robot collaborations.

Topics & Concepts

Computer scienceENCODEArtificial intelligenceObject (grammar)Motion (physics)Human–computer interactionRobotSet (abstract data type)GraphModality (human–computer interaction)Task (project management)Machine learningComputer visionTheoretical computer scienceEngineeringSystems engineeringChemistryBiochemistryGeneProgramming languageHuman Pose and Action RecognitionMultimodal Machine Learning ApplicationsAnomaly Detection Techniques and Applications