HoME: a Household Multimodal Environment
نویسندگان
چکیده
We introduce HoME: a Household Multimodal Environment for artificial agents to learn from vision, audio, semantics, physics, and interaction with objects and other agents, all within a realistic context. HoME integrates over 45,000 diverse 3D house layouts based on the SUNCG dataset, a scale which may facilitate learning, generalization, and transfer. HoME is an open-source, OpenAI Gym-compatible platform extensible to tasks in reinforcement learning, language grounding, soundbased navigation, robotics, multi-agent learning, and more. We hope HoME better enables artificial agents to learn as humans do: in an interactive, multimodal, and richly contextualized setting.
منابع مشابه
Multimodal platform for continuous monitoring of elderly and disabled at home
Health monitoring at home could be an important element of care and support environment for older people. Diversity of diseases and different needs of users require universal design of a home platform. We present our work on a sensor-based multimodal platform that is trained to recognize the activities elderly person on their home. Two specific problems were investigated: configuration and func...
متن کاملBITT: A Corpus for Topic Tracking Evaluation on Multimodal Human-Robot-Interaction
Our research is concerned with the development of robotic systems which can support people in household environments, such as taking care of elderly people. A central goal of our research consists in creating robot systems which are able to learn and communicate about a given environment without the need of a specially trained user. For the communication with such users it is necessary that the...
متن کاملKnowledge, attitudes and practices on household food waste: Bases for formulation of a recycling system
This study assessed the knowledge, attitudes and practices on food waste of selected households in the northern province of the Philippines. The results of the assessment were used as bases for formulation of a recycling system. A total of one hundred rural households were selected using stratified equal allocation sampling technique. Data were collected through the use of researcher-made quest...
متن کاملRecognizing household activities from human motion data using active learning and feature selection
The ability to accurately recognize human household activities is an important stepping stone toward creating home living assistance systems in the future. Classifying these activities can be difficult due to noisy sensor data, lack of labeled training samples for rare actions and large individual differences in activity execution. In this article, we present two techniques for improving the su...
متن کاملMultimodal Smart Home User Interfaces
Interacting with smart devices and smart homes becomes increasingly complex but also more and more important. Computing systems can help the aging society to live autonomously in their own home. However, interacting with such systems is a challenge not only for older people. Multimodal user interfaces and new interaction paradigms can help addressing these problems, but are not yet mature enoug...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1711.11017 شماره
صفحات -
تاریخ انتشار 2017