Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation

By Fengda Zhu, Linchao Zhu, Yi Yang. 2019

29 citations recorded by the source corpus.

There has been an increasing interest in 3D indoor navigation, where a robot in an environment moves to a target according to an instruction. To deploy a robot for navigation in the physical world, lots of training data is required to learn an effective policy. It is quite labour intensive to obtain sufficient real environment data for training robots while synthetic data is much easier to construct by render-ing. Though it is promising to utilize the synthetic environments to facilitate navigation training in the real world, real environment are heterogeneous from synthetic environment in two aspects. First, the visual representation of the two environments have significant variances. Second, the houseplans of these two environments are quite different. There-fore two types of information,i.e. visual representation and policy behavior, need to be adapted in the reinforce mentmodel. The learning procedure of visual representation and that of policy behavior are presumably reciprocal. We pro-pose to jointly adapt visual representation and policy behavior to leverage the mutual impacts of environment and policy. Specifically, our method employs an adversarial feature adaptation model for visual representation transfer anda policy mimic strategy for policy behavior imitation. Experiment shows that our method outperforms the baseline by 19.47% without any additional human annotations.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yi Yang
2. Mehrtash Harandi
3. Christian Simon
4. Liang Zheng
5. Yang He
6. Ping Liu
7. Tong Zhang
8. Ziwei Wang

In Computer Vision and Pattern Recognition

1. Yi Yang
2. Mehrtash Harandi
3. Luc Van Gool
4. Liang Zheng
5. Dacheng Tao
6. Trevor Darrell
7. Xiaogang Wang
8. Andrea Vedaldi

In Reinforcement Learning

1. Christian Simon
2. Liang Zheng
3. Mehrtash Harandi
4. Yang He
5. Weihao Li
6. Jie Hong
7. Lars Petersson
8. Tong Zhang

Citations in the corpus

• DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis (2019, background): “With the recent successes of Variational Autoencoders (VAEs) [9] and GANs [4], a large number of methods have been proposed to handle generation [14, 17, 28, 1] and domain adaptation task [25, 32].”
• Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration (2018, background): “The deeper and wider architectures of deep CNNs bring about the superior performance of computer vision tasks [6, 26, 45].”
• Taking a Closer Look at Domain Shift: Category-Level Adversaries for Semantics Consistent Domain Adaptation (2018, background): “To address this issue, domain adaptation approaches [35, 41, 14, 46, 17, 16, 13, 48] are proposed to bridge the gap between the source and target domains.”
• Reinforced Attention for Few-Shot Learning and Beyond (2021, methodology): “Reinforcement learning is easily utilized in sequential visual tasks, like tracking [64, 3, 41], action recognition [63, 52, 4], visual navigation [57, 67], video summarization [29] and person re-id [25].”