Abstract The existing methods for addressing visual navigation employ deep reinforcement learning as the standard tool for the task. However, they tend to be vulnerable to statistical shifts between the training and test data, resulting in poor generalization over novel environments that are out-of-distribution from the training data. In this study, we attempt to improve the generalization ability by utilizing the inductive biases available for the task. Employing the active neural SLAM that learns policies with the advantage actor-critic method as the base framework, we first point out that the mappings represented by the actor and the critic should satisfy specific symmetries. We then propose a network design for the actor and the critic to inherently attain these symmetries. Specifically, we use G-convolution instead of the standard convolution and insert the semi-global polar pooling layer, which we newly design in this study, in the last section of the critic network. Our method can be integrated into existing methods that utilize intermediate goals and 2D occupancy maps. Experimental results show that our method improves generalization ability by a good margin over visual exploration and object goal navigation, which are two main embodied visual navigation tasks.

Visual exploration is a task that seeks to visit all the navigable areas of an environment as quickly as possible. The existing methods employ deep reinforcement learning (RL) as the standard tool for the task. However, they tend to be vulnerable to statistical shifts between the training and test data, resulting in poor generalization over novel environments that are out-of-distribution (OOD) from the training data. In this paper, we attempt to improve the generalization ability by utilizing the inductive biases available for the task. Employing the active neural SLAM (ANS) that learns exploration policies with the advantage actor-critic (A2C) method as the base framework, we first point out that the mappings represented by the actor and the critic should satisfy specific symmetries. We then propose a network design for the actor and the critic to inherently attain these symmetries. Specifically, we use G-convolution instead of the standard convolution and insert the semi-global polar pooling (SGPP) layer, which we newly design in this study, in the last section of the critic network. Experimental results show that our method increases area coverage by 8.1m2when trained on the Gibson dataset and tested on the Matterport3D dataset, establishing the new state-of-the-art.

Underwater active landmarks (UALs) are widely used for short-range underwater navigation in underwater robotics tasks. Detection of UALs is challenging due to large variance of underwater illumination, water quality and change of camera viewpoint. Moreover, improvement of detection accuracy relies upon statistical diversity of images used to train detection models. We propose a generative adversarial network, called Tank-to-field GAN (T2FGAN), to learn generative models of underwater images, and use the learned models for data augmentation to improve detection accuracy. To this end, first a T2FGAN is trained using images of UALs captured in a tank. Then, the learned model of the T2FGAN is used to generate images of UALs according to different water quality, illumination, pose and landmark configurations (WIPCs). In experimental analyses, we first explore statistical properties of images of UALs generated by T2FGAN under various WIPCs for active landmark detection. Then, we use the generated images for training detection algorithms. Experimental results show that training detection algorithms using the generated images can improve detection accuracy. In field experiments, underwater docking tasks are successfully performed in a lake by employing detection models trained on datasets generated by T2FGAN.

The entorhino-hippocampal neural circuits of the mammalian brains are able to internally generate efficient spatial representations of large-scale environments. Hippocampal principal cells in mammalian brains form sparse codes of the positions in large environments. The underlying computational mechanisms of the formation of spatial memory in large-scale environments are still not well understood. We present a competitive learning network that integrates both spatial inputs from grid cells as well as contextual inputs from non-spatial cells. Through self-organisation, place units in the network form place fields at “randomly” interleaved locations, in the sense that both the recruitment process and the inter-field interval are memoryless, a property superior for spatial memory formation in large environments.