State-of-the-art algorithms for visual place recognition, and related visual navigation systems, can be broadly split into two categories: computer-science-oriented models including deep learning or image retrieval based techniques with minimal biological plausibility, and neuroscience-oriented dynamical networks that model temporal properties found in neural cells underlying spatial navigation in the brain. In this paper, we propose a new compact and high-performing place recognition hybrid model that bridges this divide for the first time. Our approach comprises two key components that incorporate neural models of these two categories: (1) FlyNet, a compact, sparse twolayer neural network inspired by brain architectures of fruit flies, Drosophila melanogaster, and (2) a one-dimensional continuous attractor neural network (CANN). The resulting FlyNet+CANN network combines the compact pattern recognition capabilities of our FlyNet model with the powerful temporal filtering capabilities of an equally compact CANN, replicating entirely in a hybrid neural implementation the functionality that yields high performance in algorithmic localization approaches like SeqSLAM. We evaluate our approach, and compare it to three state-of-the-art place recognition methods, on two benchmark real-world datasets with small viewpoint variations and extreme environmental changes; including day/night cycles where it achieves an AUC performance of 87% compared to 60% for Multi-Process Fusion, 46% for LoST-X and 1% for SeqSLAM, while being 6.5, 310, and 1.5 times faster respectively.
<div>Visual navigation tasks in real-world environments often require both self-motion and place recognition feedback. While deep reinforcement learning has shown success in solving these perception and decision-making problems in an end-to-end manner, these algorithms require large amounts of experience to learn navigation policies from high-dimensional data, which is generally impractical for real robots due to sample complexity. In this paper, we address these problems with two main contributions. We first leverage place recognition and deep learning techniques combined with goal destination feedback to generate compact, bimodal image representations that can then be used to effectively learn control policies from a small amount of experience. Second, we present an interactive framework, CityLearn, that enables for the first time training and deployment of navigation algorithms across city-sized, realistic environments with extreme visual appearance changes. CityLearn features more than 10 benchmark datasets, often used in visual place recognition and autonomous driving research, including over 100 recorded traversals across 60 cities around the world. We evaluate our approach on two CityLearn environments, training our navigation policy on a single traversal. Results show our method can be over 2 orders of magnitude faster than when using raw images, and can also generalize across extreme visual changes including day to night and summer to winter transitions.</div>
The temperature and humidity control of an intake air conditioning (IAC) system for internal combustion engine testing is considered. A decentralized control structure with four PID controllers is proposed, where the PID parameters are chosen using either the Ziegler-Nichols method or a fuzzy gain scheduling. Experimental tests were conducted on a diesel engine test bench to obtain air conditions data to simulate a closed-loop system. A simulation model of the IAC system is used to evaluate the two PID parameter approaches, and the results show that a fuzzy gain scheduling approach achieves small improvements in terms of settling time and steady-state error.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.