If you are looking for an answer to the question What is Artificial Intelligence? and you only have a minute, then here's the definition the Association for the Advancement of Artificial Intelligence offers on its home page: "the scientific understanding of the mechanisms underlying thought and intelligent behavior and their embodiment in machines."
However, if you are fortunate enough to have more than a minute, then please get ready to embark upon an exciting journey exploring AI (but beware, it could last a lifetime) …
Electricity disaggregation identifies individual appliances from one or more aggregate data streams and has immense potential to reduce residential and commercial electrical waste. Since supervised learning methods rely on meticulously labeled training samples that are expensive to obtain, unsupervised methods show the most promise for wide-spread application. However, unsupervised learning methods previously applied to electricity disaggregation suffer from critical limitations. This paper introduces the concept of iterative appliance discovery, a novel unsupervised disaggregation method that progressively identifies the "easiest to find" or "most likely" appliances first. Once these simpler appliances have been identified, the computational complexity of the search space can be significantly reduced, enabling iterative discovery to identify more complex appliances. We test iterative appliance discovery against an existing competitive unsupervised method using two publicly available datasets. Results using different sampling rates show iterative discovery has faster runtimes and produces better accuracy. Furthermore, iterative discovery does not require prior knowledge of appliance characteristics and demonstrates unprecedented scalability to identify long, overlapped sequences that other unsupervised learning algorithms cannot.
Anderson, Monica (University of Alabama) | Barták, Roman (Charles University) | Brownstein, John S. (Boston Children's Hospital, Harvard University) | Buckeridge, David L. (McGill University) | Eldardiry, Hoda (Palo Alto Research Center) | Geib, Christopher (Drexel University) | Gini, Maria (University of Minnesota) | Isaksen, Aaron (New York University) | Keren, Sarah (Technion University) | Laddaga, Robert (Vanderbilt University) | Lisy, Viliam (Czech Technical University) | Martin, Rodney (NASA Ames Research Center) | Martinez, David R. (MIT Lincoln Laboratory) | Michalowski, Martin (University of Ottawa) | Michael, Loizos (Open University of Cyprus) | Mirsky, Reuth (Ben-Gurion University) | Nguyen, Thanh (University of Michigan) | Paul, Michael J. (University of Colorado Boulder) | Pontelli, Enrico (New Mexico State University) | Sanner, Scott (University of Toronto) | Shaban-Nejad, Arash (University of Tennessee) | Sinha, Arunesh (University of Michigan) | Sohrabi, Shirin (IBM T. J. Watson Research Center) | Sricharan, Kumar (Palo Alto Research Center) | Srivastava, Biplav (IBM T. J. Watson Research Center) | Stefik, Mark (Palo Alto Research Center) | Streilein, William W. (MIT Lincoln Laboratory) | Sturtevant, Nathan (University of Denver) | Talamadupula, Kartik (IBM T. J. Watson Research Center) | Thielscher, Michael (University of New South Wales) | Togelius, Julian (New York University) | Tran, So Cao (New Mexico State University) | Tran-Thanh, Long (University of Southampton) | Wagner, Neal (MIT Lincoln Laboratory) | Wallace, Byron C. (Northeastern University) | Wilk, Szymon (Poznan University of Technology) | Zhu, Jichen (Drexel University)
Gini, Maria (University of Minnesota)
Task allocation is ubiquitous in computer science and robotics, yet some problems have received limited attention in the computer science and AI community. Specifically, we will focus on multi-robot task allocation problems when tasks have time windows or ordering constraints. We will outline the main lines ofresearch and open problems.
In crowded multi-agent navigation environments, the motion of the agents is significantly constrained by the motion of the nearby agents. This makes planning paths very difficult and leads to inefficient global motion. To address this problem, we propose a new distributed approach to coordinate the motions of agents in crowded environments. With our approach, agents take into account the velocities and goals of their neighbors and optimize their motion accordingly and in real-time. We experimentally validate our coordination approach in a variety of scenarios and show that its performance scales to scenarios with hundreds of agents.
Multi-robot teams are useful in a variety of task allocation domains such as warehouse automation and surveillance. Robots in such domains perform tasks at given locations and specific times, and are allocated tasks to optimize given team objectives. We propose an efficient, satisficing and centralized Monte Carlo TreeSearch based algorithm exploiting branch and bound paradigm to solve the multi-robot task allocation problem with spatial, temporal and other side constraints. Unlike previous heuristics proposed for this problem, our approach offers theoretical guarantees and finds optimal solutions for some non-trivial data sets.
Electricity disaggregation focuses on classification ofindividual appliances by monitoring aggregate electricalsignals. In this paper we present a novel algorithmto automatically correct labels, discard contaminatedtraining samples, and boost signal to noise ratio throughhigh frequency noise reduction. We also propose amethod for prioritized classification which classifies applianceswith the most intense signals first. When testedon four houses in Kaggles Belkin dataset, these methodsautomatically relabel over 77% of all training samplesand decrease error rate by an average of 45% in bothreal power and high frequency noise classification.
We propose an auction algorithm to allocate tasks that have temporal constraints to cooperative robots. Temporal constraints are expressed as time windows, within which a task must be executed. There are no restrictions on the time windows, which are allowed to overlap. Robots model their temporal constraints using a simple temporal network, enabling them to maintain consistent schedules. When bidding on a task, a robot takes into account its own current commitments and an optimization objective, which is to minimize the time of completion of the last task alone or in combination with minimizing the distance traveled. The algorithm works both when all the tasks are known upfront and when tasks arrive dynamically. We show the performance of the algorithm in simulation with different numbers of tasks and robots, and compare it with a baseline greedy algorithm and a state-of-the-art auction algorithm. Our algorithm is computationally frugal and consistently allocates more tasks than the competing algorithms.
In the event of an earthquake or fire, search and rescue efforts may be delayed until it is safe for the human rescue team to enter the area. A team of robots could enter in advance to provide maps, images and locations of interest to the human team, allowing them to prepare their approach when they can enter. In a disaster area, communication may be limited, either due to infrastructure being down, or because of environmental interference. We propose an algorithm that makes use of a small number of robots, which spread as far as their communication allows, but which otherwise stay together while they explore the unknown environment. We show that the algorithm will allow the team of robots to fully explore the environment and maintain communication in order to return the information to the waiting search and rescue team. We also show that this can be achieved with multiple methods of communication.
Airline ticket purchase timing is a strategic problem that requires both historical data and domain knowledge to solve consistently. Even with some historical information (often a feature of modern travel reservation web sites), it is difficult for consumers to make true cost-minimizing decisions. To address this problem, we introduce an automated agent which is able to optimize purchase timing on behalf of customers and provide performance estimates of its computed action policy based on past performance. We apply machine learning to recent ticket price quotes from many competing airlines for the target flight route. Our novelty lies in extending this using a systematic feature extraction technique incorporating elementary user-provided domain knowledge that greatly enhances the performance of machine learning algorithms. Using this technique, our agent achieves much closer to the optimal purchase policy than other proposed decision theoretic approaches for this domain.
Dispersing a team of robots into an unknown and dangerous environment, such as a collapsed building, can provide information about structural damage and locations of survivors and help rescuers plan their actions. We propose a rolling dispersion algorithm, which makes use of a small number of robots and achieves full exploration. The robots disperse as much as possible while maintaining communication, and then advance as a group, leaving behind beacons to mark explored areas and provide a path back to the entrance. The novelty of this algorithm comes from the manner in which the robots continue their exploration as a group after reaching the maximum dispersion possible while staying in contact with each other. We use simulation to show that the algorithm works in multiple environments and for varying numbers of robots.