Much of the world's data is streaming, time-series data, where anomalies give significant information in critical situations; examples abound in domains such as finance, IT, security, medical, and energy. Yet detecting anomalies in streaming data is a difficult task, requiring detectors to process data in real-time, not batches, and learn while simultaneously making predictions. There are no benchmarks to adequately test and score the efficacy of real-time anomaly detectors. Here we propose the Numenta Anomaly Benchmark (NAB), which attempts to provide a controlled and repeatable environment of open-source tools to test and measure anomaly detection algorithms on streaming data. The perfect detector would detect all anomalies as soon as possible, trigger no false alarms, work with real-world time-series data across a variety of domains, and automatically adapt to changing statistics. Rewarding these characteristics is formalized in NAB, using a scoring algorithm designed for streaming data. NAB evaluates detectors on a benchmark dataset with labeled, real-world time-series data. We present these components, and give results and analyses for several open source, commercially-used algorithms. The goal for NAB is to provide a standard, open source framework with which the research community can compare and evaluate different algorithms for detecting anomalies in streaming data.
Path planning is one of the most vital elements of mobile robotics, providing the agent with a collision-free route through the workspace. The global path plan can be calculated with a variety of informed search algorithms, most notably the A* search method, guaranteed to deliver a complete and optimal solution that minimizes the path cost. D* is widely used for its dynamic replanning capabilities. Path planning optimization typically looks to minimize the distance traversed from start to goal, but many mobile robot applications call for additional path planning objectives, presenting a multiobjective optimization (MOO) problem. Common search algorithms, e.g. A* and D*, are not well suited for MOO problems, yielding suboptimal results. The search algorithm presented in this paper is designed for optimal MOO path planning. The algorithm incorporates Pareto optimality into D*, and is thus named D*-PO. Non-dominated solution paths are guaranteed by calculating the Pareto front at each search step. Simulations were run to model a planetary exploration rover in a Mars environment, with five path costs. The results show the new, Pareto optimal D*-PO outperforms the traditional A* and D* algorithms for MOO path planning.
The exploration of planetary surfaces is predominately unmanned, calling for a landing vehicle and an autonomous and/or teleoperated rover. Artificial intelligence and machine learning techniques can be leveraged for better mission planning. This paper describes the coordinated use of both global navigation and metaheuristic optimization algorithms to plan the safe, efficient missions. The aim is to determine the least-cost combination of a safe landing zone (LZ) and global path plan, where avoiding terrain hazards for the lander and rover minimizes cost. Computer vision methods were used to identify surface craters, mounds, and rocks as obstacles. Multiple search methods were investigated for the rover global path plan. Several combinatorial optimization algorithms were implemented to select the shortest distance path as the preferred mission plan. Simulations were run for a sample Google Lunar X Prize mission. The result of this study is an optimization scheme that path plans with the A* search method, and uses simulated annealing to select ideal LZ-path- goal combination for the mission. Simulation results show the methods are effective in minimizing the risk of hazards and increasing efficiency. This paper is specific to a lunar mission, but the resulting architecture may be applied to a large variety of planetary missions and rovers.
Path planning is one of the most vital elements of mobile robotics. With a priori knowledge of the environment, global path planning provides a collision-free route through the workspace. The global path plan can be calculated with a variety of informed search algorithms, most notably the A* search method, guaranteed to deliver a complete and optimal solution that minimizes the path cost. Path planning optimization typically looks to minimize the distance traversed from start to goal, yet many mobile robot applications call for additional path planning objectives, presenting a multiobjective optimization (MOO) problem. Past studies have applied genetic algorithms to MOO path planning problems, but these may have the disadvantages of computational complexity and suboptimal solutions. Alternatively, the algorithm in this paper approaches MOO path planning with the use of Pareto fronts, or finding non-dominated solutions. The algorithm presented incorporates Pareto optimality into every step of A* search, thus it is named A*-PO. Results of simulations show A*-PO outperformed several variations of the standard A* algorithm for MOO path planning. A planetary exploration rover case study was added to demonstrate the viability of A*-PO in a real-world application.