Computational Adaptive Autonomy:
نویسندگان
چکیده
We describe a generalization of Copycat, an important computational architecture for high-level perception. We show how this generalization simplifies the application of computational perception to problems previously beyond the reach of the fluid analogy-making principles underlying Copycat. We also discuss the ways in which this generalization addresses the fundamental problem of brittleness, and embraces a new standard for autonomy and adaptation in artificial systems.
منابع مشابه
Image Restoration with Two-Dimensional Adaptive Filter Algorithms
Two-dimensional (TD) adaptive filtering is a technique that can be applied to many image, and signal processing applications. This paper extends the one-dimensional adaptive filter algorithms to TD structures and the novel TD adaptive filters are established. Based on this extension, the TD variable step-size normalized least mean squares (TD-VSS-NLMS), the TD-VSS affine projection algorithms (...
متن کاملMaritime situational awareness using adaptive multi-sensor management under hazy conditions
This paper presents a multi-sensor architecture with an adaptive multi-sensor management system suitable for control and navigation of autonomous maritime vessels in hazy and poorvisibility conditions. This architecture resides in the autonomous maritime vessels. It augments the data from on-board imaging sensors and weather sensors with the AIS data and weather data from sensors on other vesse...
متن کاملAutonomous navigation using an adaptive hierarchy of multiple fuzzy-behaviors
Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the IEEE. Abstract Adaptive behavioral capabilities are necessary for robust mobil...
متن کاملScience of Autonomy: Time-Optimal Path Planning and Adaptive Sampling for Swarms of Ocean Vehicles
Ocean observing is the process of collecting ocean measurements to provide most useful information about the ocean systems and dynamics of interest. Such marine sensing is expensive and challenging. In the ocean, not everything can be measured on a sustained basis. Ocean modeling is the process of developing and utilizing theoretical and computational models for the understanding and prediction...
متن کاملLearning to Navigate by Growing Deep Networks
Adaptability is central to autonomy. Intuitively, for high-dimensional learning problems such as navigating based on vision, internal models with higher complexity allow to accurately encode the information available. However, most learning methods rely on models with a fixed structure and complexity. In this paper, we present a self-supervised framework for robots to learn to navigate, without...
متن کامل