Learning to Simulate Dynamic Environments With GameGAN
© 2020 IEEE. Simulation is a crucial component of any robotic system. In order to simulate correctly, we need to write complex rules of the environment: how dynamic agents behave, and how the actions of each of the agents affect the behavior of others. In this paper, we aim to learn a simulator by s...
Main Authors: | Kim, Seung Wook, Zhou, Yuhao, Philion, Jonah, Torralba, Antonio, Fidler, Sanja |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
Format: | Article |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2021
|
Online Access: | https://hdl.handle.net/1721.1/137598 |
Similar Items
-
DriveGAN: Towards a Controllable High-Quality Neural Simulation
by: Kim, Seung Wook, et al.
Published: (2022) -
VirtualHome: Simulating Household Activities Via Programs
by: Puig, Xavier, et al.
Published: (2020) -
Learning to Act Properly: Predicting and Explaining Affordances from Images
by: Chuang, Ching-Yao, et al.
Published: (2020) -
Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization
by: Li, Daiqing, et al.
Published: (2022) -
GAN based simultaneous localization and mapping framework in dynamic environment
by: Bo Sun, et al.
Published: (2022-11-01)