Navigation is a fundamental problem of mobile robots, for which Deep Reinforcement Learning (DRL) has received significant attention because of its strong representation and experience learning abilities. There is a growing trend of applying DRL to mobile robot navigation. In this paper, we review DRL methods and DRL-based navigation frameworks. Then we systematically compare and analyze the relationship and differences between four typical application scenarios: local obstacle avoidance, indoor navigation, multi-robot navigation, and social navigation. Next, we describe the development of DRL-based navigation. Last, we discuss the challenges and some possible solutions regarding DRL-based navigation.
With the increasing demands of electric vehicles, many DC electrical energy meters for vehicle battery charger appear. In this paper, a verification device of DC electrical energy meter is developed that base on real-time pulse period compare method, which used PCI-6281 for data acquisition, used LabVIEW for data processing and human-computer interface. This article describes the working principle of the verification device and core technology. The practical application verify the device can use for calibration of DC electrical energy meter efficiently.
Collaborative coverage for target search using a group of unmanned aerial vehicles (UAVs) has received increasing attention in recent years. However, the design of distributed control strategy and coordination mechanisms remains a challenge. This paper presents a distributed and online heuristic strategy to solve the problem of multi-UAV collaborative coverage. As a basis, each UAV maintains a probability grid map in the form of a locally stored matrix, without shared memory. Then we design two evaluation functions and related technical strategies to enable UAVs to make state transfer or area transfer decisions in an online self-organizing way. The simulation results show that the algorithm integrates geometric features such as parallel search and internal spiral search, and is not interfered by factors such as sudden failure of UAVs, changes in detection range, and target movement. Compared with other commonly used methods for target search, our strategy has high search efficiency, good robustness, and fault tolerance.
The article studies on the application of the shuffled frog leaping algorithm (SFLA) in power distribution network reconfiguration, taking the minimum loss and voltage quality of distribution network as a multi-objective function. The article improves the initial solution generation strategy of traditional genetic algorithm, which ensures the initial solution is feasible solution. Shuffled frog leaping algorithm and genetic algorithms are combined and proposed as shuffled frog leaping genetic algorithm (SFLGA). The algorithm uses the efficient coding strategy based on the basic loop and initial solution generation strategy, improves the calculation efficiency. The algorithm is verified by simulation results from test case on IEEE 33-bus system with distributed generations.
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.