Related papers: Continual Learning from Synthetic Data for a Human…

Vision-based human-to-robot handover is an important and challenging task in human-robot interaction. Recent work has attempted to train robot policies by interacting with dynamic virtual humans in simulated environments, where the policies…

Real-time human activity recognition plays an essential role in real-world human-centered robotics applications, such as assisted living and human-robot collaboration. Although previous methods based on skeletal data to encode human poses…

Learning articulated object pose is inherently difficult because the pose is high dimensional but has many structural constraints. Most existing work do not model such constraints and does not guarantee the geometric validity of their pose…

Existing Graph Convolutional Networks to achieve human motion prediction largely adopt a one-step scheme, which output the prediction straight from history input, failing to exploit human motion patterns. We observe that human motions have…

Here we present a machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains, involving fluids, rigid solids, and deformable materials interacting with one another. Our…

This paper focuses on the problem of learning 6-DOF grasping with a parallel jaw gripper in simulation. We propose the notion of a geometry-aware representation in grasping based on the assumption that knowledge of 3D geometry is at the…

An important challenge in robotics is understanding the interactions between robots and deformable terrains that consist of granular material. Granular flows and their interactions with rigid bodies still pose several open questions. A…

With the popularization of game and VR/AR devices, there is a growing need for capturing human motion with a sparse set of tracking data. In this paper, we introduce a deep neural-network (DNN) based method for real-time prediction of the…

We present a series of modifications which improve upon Graph WaveNet's previously state-of-the-art performance on the METR-LA traffic prediction task. The goal of this task is to predict the future speed of traffic at each sensor in a…

Skeleton-based human action recognition has recently attracted increasing attention due to the popularity of 3D skeleton data. One main challenge lies in the large view variations in captured human actions. We propose a novel view…

We present a generative model that learns to synthesize human motion from limited training sequences. Our framework provides conditional generation and blending across multiple temporal resolutions. The model adeptly captures human motion…

The widespread success of artificial intelligence in fields like natural language processing and computer vision has not yet fully transferred to robotics, where progress is hindered by the lack of large-scale training data and the…

We propose a new transformer model for the task of unsupervised learning of skeleton motion sequences. The existing transformer model utilized for unsupervised skeleton-based action learning is learned the instantaneous velocity of each…

Generation of realistic high-resolution videos of human subjects is a challenging and important task in computer vision. In this paper, we focus on human motion transfer - generation of a video depicting a particular subject, observed in a…

Current exoskeleton control methods often face challenges in delivering personalized treatment. Standardized walking gaits can lead to patient discomfort or even injury. Therefore, personalized gait is essential for the effectiveness of…

Human motion prediction from motion capture data is a classical problem in the computer vision, and conventional methods take the holistic human body as input. These methods ignore the fact that, in various human activities, different body…

Rapid progress in deep reinforcement learning has made it increasingly feasible to train controllers for high-dimensional humanoid bodies. However, methods that use pure reinforcement learning with simple reward functions tend to produce…

Video-based person re-identification deals with the inherent difficulty of matching unregulated sequences with different length and with incomplete target pose/viewpoint structure. Common approaches operate either by reducing the problem to…

We propose Ground Reaction Inertial Poser (GRIP), a method that reconstructs physically plausible human motion using four wearable devices. Unlike conventional IMU-only approaches, GRIP combines IMU signals with foot pressure data to…

3D skeleton-based action recognition and motion prediction are two essential problems of human activity understanding. In many previous works: 1) they studied two tasks separately, neglecting internal correlations; 2) they did not capture…