A Novel Neural Multi-Store Memory Network for Autonomous Visual Navigation in Unknown Environment
- 6 January 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 2039-2046
Abstract
Learning to achieve a user-specified objective from a random position in unseen environments is challenging for image-guided navigation agents. The abilities of long-horizon reasoning and semantic understanding are still lacking. Inspired by the human memory mechanism, we introduce a neural multi-store memory network to the reinforcement learning framework for target-driven visual navigation. The proposed memory network utilizes three temporal stages of memory to build time dependency for better scene understanding. Sensory memory encodes observations and embeds transient information into working memory, which is short-term and realized by a gated recurrent neural network (RNN). Then, the long-term memory stores the latent state from each step of the RNN into a single slot. Finally, a self-attention reading mechanism is designed to retrieve goal-related information from long-term memory. In addition, to improve the scene generalization capability of the agent, we facilitate training of the visual representation with a self-supervised auxiliary task and image augmentation. This method can navigate agents in unknown visual-realistic environments using only egocentric observations, without the need for any position sensors or pretrained models. The evaluation results on the Matterport3D dataset through the Habitat simulator demonstrate that our method outperforms the state-of-the-art approaches.Keywords
Funding Information
- National Key Research and Development Program of China (2020AAA0108905)
- National Natural Science Foundation of China (61825303, 51975415, 62088101)
- Science and Technology Commission of Shanghai Municipality (2021SHZDZX0100, 19511132101, 20511105402)
- Fundamental Research Funds for the Central Universities (22120210547)
- Beijing Advanced Innovation Center for Intelligent Robots and Systems, Beijing Institute of Technology (2019IRS04)
This publication has 27 references indexed in Scilit:
- Virtual-to-real deep reinforcement learning: Continuous control of mobile robots for mapless navigation2017
- Cognitive Mapping and Planning for Visual Navigation2017
- Target-driven visual navigation in indoor scenes using deep reinforcement learning2017
- Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception AgeIEEE Transactions on Robotics, 2016
- Hybrid computing using a neural network with dynamic external memoryNature, 2016
- Deep Residual Learning for Image Recognition2016
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
- A frontier-based approach for autonomous exploration2002
- Long Short-Term MemoryNeural Computation, 1997
- Human Memory: A Proposed System and its Control Processes1968