Deep reinforcement learning has produced many success stories in recent years. Some example fields in which these successes have taken place include mathematics, games, health care, and robotics. In this paper, we are especially interested in multi-agent deep reinforcement learning, where multiple agents present in the environment not only learn from their own experiences but also from each other and its applications in multi-robot systems. In many real-world scenarios, one robot might not be enough to complete the given task on its own, and, therefore, we might need to deploy multiple robots who work together towards a common global objective of finishing the task. Although multi-agent deep reinforcement learning and its applications in multi-robot systems are of tremendous significance from theoretical and applied standpoints, the latest survey in this domain dates to 2004 albeit for traditional learning applications as deep reinforcement learning was not invented. We classify the reviewed papers in our survey primarily based on their multi-robot applications. Our survey also discusses a few challenges that the current research in this domain faces and provides a potential list of future applications involving multi-robot systems that can benefit from advances in multi-agent deep reinforcement learning.

Precision agriculture is the collection of hardware and software technologies that allow a farmer to make informed, differentiated decisions regarding agricultural operations such as planting, fertilizing, pest control, and harvesting. In recent years, advances in agricultural machinery and the emergence of agricultural robots continuously increased the resolution at which differentiated treatment is possible. This creates a corresponding need for information at a fine spatial and temporal resolution. Autonomous multi-robot systems (e.g., unmanned ground and aerial vehicles) are some of the most promising approaches for such information collection in open-air farms. In this paper, we survey the current state and challenges of multi-robot information gathering for precision agriculture, with a special focus on maximizing information and ensuring the security of the collected data while simultaneously keeping energy consumption in check.

We consider the NP-hard problem of multirobot informative path planning in the presence of communication constraints, where the objective is to collect higher amounts of information of an ambient phenomenon. We propose a novel approach that uses continuous region partitioning into Voronoi components to efficiently divide an initially unknown environment among the robots based on newly discovered obstacles enabling improved load balancing between robots. Simulation results show that our proposed approach is successful in reducing the initial imbalance of the robots’ allocated free regions while ensuring close-to-reality spatial modeling within a reasonable amount of time.

We propose a lightweight and fast learning algorithm for classifying the features of an unknown terrain that a robot is navigating in. Most of the existing research on unknown terrain classification by mobile robots relies on a single powerful classifier to correctly identify the terrain using sensor data from a single sensor like laser or camera. In contrast, our proposed approach uses multiple modalities of sensed data and multiple, weak but less-complex classifiers for classifying the terrain types. The classifiers are combined using an ensemble learning algorithm to improve the algorithm’s training rate as compared to an individual classifier. Our algorithm was tested with data collected by navigating a four-wheeled, autonomous robot, called Explorer, over different terrains including brick, grass, rock, sand, and concrete. Our results show that our proposed approach performs better with up to 63% better prediction accuracy for some terrains as compared to a support vector machine (SVM)-based learning technique that uses sensor data from a single sensor. Despite using multiple classifiers, our algorithm takes only a fraction (1/65) of the time on average, as compared to the SVM technique.

Blockchain-powered smart systems deployed in different industrial applications promise operational efficiencies and improved yields, while significantly mitigating cybersecurity risks. Tradeoffs between availability and security arise at implementation, however, triggered by the additional resources (e.g., memory and computation) required by blockchain-enabled hosts. This paper applies an energy-reducing algorithmic engineering technique for Merkle Tree (MT) root calculations and the Proof of Work (PoW) algorithm, two principal elements of blockchain computations, as a means to preserve the promised security benefits but with less compromise to system availability. Using pyRAPL, a python library to measure the energy consumption of a computation, we experiment with both the standard and energy-reduced implementations of both algorithms for different input sizes. Our results show that up to 98% reduction in energy consumption is possible within the blockchain’s MT construction module, with the benefits typically increasing with larger input sizes. For the PoW algorithm, our results show up to 20% reduction in energy consumption, with the benefits being lower for higher difficulty levels. The proposed energy-reducing technique is also applicable to other key elements of blockchain computations, potentially affording even “greener” blockchain-powered systems than implied by only the results obtained thus far on the MT and PoW algorithms.