The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Reinforcement learning (RL) has distinguished itself as a prominent learning method to augment the efficacy of autonomous systems. Recent advances in deep learning studies have complemented existing RL methods and led to a crucial breakthrough in the effort of applying RL to automation and robotics. Artificial agents based on deep RL can take selective and intelligent actions comparable with those...
The following topics are dealt with: machine learning; swarm intelligence; constraint programming; evolutionary algorithms; data mining; uncertainty handling; natural language processing; image processing; robotics; and multiagent systems.
Autonomous navigation by a mobile robot through L natural, unstructured terrain is one of the premier k challenges in field robotics. Tremendous advances V in autonomous navigation have been made recently in field robotics. Machine learning has played an increasingly important role in these advances. The Defense Advanced Research Projects Agency (DARPA) UGCV-Perceptor Integration (UPI) program was...
The following topics are dealt with: pattern recognition; computer vision; image processing; video motion analysis; face recognition; biometrics recognition; medical image information; biological information; language speech; multimedia; robotics; machine learning; document analysis; character recognition; and speech processing.
The paper presents the second phase of a curriculum project that builds on existing successful work. Our work involves the development, implementation, and testing of an adaptable framework for the presentation of core AI topics that emphasizes the relationship between AI and computer science. Under phase 1, we developed and pilot-tested our proof-of-concept. The second phase involves further development...
A new framework for sustainable spaces is proposed. Proposed framework consists of a group of conceptual hardware and software design. Purpose of the work is to solve the sustainability problem for terrestrial and extraterrestrial applications, using key concepts of the computer science, robotics, thermodynamics and architecture. Related to the proposed work, a machine learning method is applied for...
In 2005, inspired by Von Neumannpsilas self-reproducing automata, the author had introduced self-reproducing machine learning (SRML). In this article the author is trying to explore the nature of self-reproducing machine learning, SRML architectures, formal structures, mathematical structures and its integrated systems software engineering principles. The author will demonstrate SRML technology to...
RoboCup Soccer is a rich domain for the study of multiagent learning issues. Not only must the players learn low-level skills, but they must also learn to work together and to adapt to the behaviors of different opponents. Dynamic behaviour learning in the face of adversarial opponents involves a) learning a basic set of strategies, and b) tuning these strategies for the specific opponents involved...
Recent advancements of technologies, including computation, robotics, machine learning, communication, and miniaturization technologies, bring us closer to futuristic visions of compassionate intelligent devices. The missing element is a basic understanding of how to relate human functions (physiological, physical, and cognitive) to the design of intelligent devices and systems that aid and interact...
It is hard to define a state space or the proper reward function in reinforcement learning to make the robot act as expected. In this paper, we demonstrate the expected behavior for a robot Then a RL-based decision tree approach which decides to split according to long-term evaluations, instead of a top-down greedy strategy which finds out the relationship between the input and output from the demonstration...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.