In distributed mobile robot systems, autonomous robots accomplish complicated tasks through intelligent cooperation with each other. This paper presents behavior learning and online distributed evolution for cooperative behavior of a group of autonomous robots. Learning and evolution capabilities are essential for a group of autonomous robots to adapt to unstructured environments. Behavior lear...

The Community of Practice GRAPAU, related to the RIMA project (http://www.upc.edu/rima), has been focusing their work on collecting activities and experiences related to Autonomous Learning and developing a decalogue of good teaching practices to improve the quality of Autonomous Learning in UPC-BARCELONATECH) degrees. This work is based on GRAPAU items that were developed in order to improve A...

Helicopters have highly stochastic, nonlinear, dynamics, and autonomous helicopter flight is widely regarded to be a challenging control problem. As helicopters are highly unstable at low speeds, it is particularly difficult to design controllers for low speed aerobatic maneuvers. In this paper, we describe a successful application of reinforcement learning to designing a controller for sustain...

PAGODA (Probabilistic Autonomous GOalDirected Agent) is an autonomous intelligent agent that explores a novel environment, building a model of the world and using the model to plan its actions [desJardins, 1992b]. PAGODA incorporates solutions to the problems of selecting learning tasks, choosing a learning bias, classifying observations, and performing induetire learning of world models under ...

A novel integrative learning architecture, RLSM with a STDP network is described. This architecture models symbol emergence in an autonomous agent engaged in reinforcement learning tasks. The architecture consists of two constitutional learning architectures: a reinforcement learning schema model (RLSM) and a spike timing-dependent plasticity (STDP) network. RLSM is an incremental modular reinf...

Autonomous learning plays an important role in raising students’ learning effect and innovation ability in university education. An effective e-learning environment is indispensable in autonomous learning. This paper studies a web based e-learning system and examines students’ autonomous learning ability and perceptions of e-learning taking students at University of Jinan in China as an example...

the salient, and often ignored, role that out-of-class learning plays in second/foreign language (l2) learners’ development is overshadowed by classroom research. the main aim of this study is to problematize the role of out-of-class learning in the specific english-as-foreign-language (efl) context of iran by examination of the ways in which four learners attempted to revamp their english lang...

The swift development of multimedia technology is further promoting the College English Teaching reform. College English autonomous learning model, based on a combination of student-centered teaching concept with multimedia technology, is one of the most important developing trends in the process of the reform. This paper discusses the difference of student’s autonomous learning ability between...

In the thesis we propose, we focus on equipping existing Reinforcement Learning algorithms with different kinds of safety constraints imposed on the exploration scheme. Common Reinforcement Learning algorithms are (sometimes implicitly) assumed to work in an ergodic1, or even “restartable” environment. However, these conditions are not achievable in field robotics, where the expensive robots ca...

Autonomous off-road navigation of robotic ground vehicles has important applications on Earth and in space exploration. Progress in this domain has been retarded by the limited lookahead range of 3-D sensors and by the difficulty of preprogramming systems to understand the traversability of the wide variety of terrain they can encounter. Enabling robots to learn from experience may alleviate bo...