In this paper we apply incremental evolution for automatic synthesis of neural network controllers for a group of physically connected mobile robots called s-bots. The robots should be able to safely and cooperatively perform phototaxis in an arena containing holes. We experiment with two approaches to incremental evolution, namely behavioral decomposition and environmental complexity increase....

We present an integrated framework that permits implicit task learning and kinesthetic teaching during the execution of robotic tasks in cooperation with humans. The proposed system combines physical human-robot interaction, attentional supervision, multimodal interaction to support robot teaching and incremental task learning. We describe the overall system architecture discussing a task learn...

I. INTRODUCTION " Planning " , or selecting a sequence of actions to achieve a goal, has been a core focus of interest within the field of Artificial Intelligence (AI) since the field was founded in the 1950's. Initially, the focus of attention was on task planning which is concerned with sequencing actions within a symbolic representation of the state space [2]. When action costs are further i...

High Performance Fortran (HPF) has emerged as a standard language for data parallel computing. However, a wide variety of scientiic applications are best programmed by a combination of task and data parallelism. Therefore, a good model of task parallelism is important for continued success of HPF for parallel programming. This paper presents a task parallelism model that is simple, elegant, and...

This paper presents a new approach for mapping and scheduling task graphs for heterogeneous hardware/software computing systems using heuristic search. Task mapping and scheduling are vital in hardware/software codesign and previous approaches that treat them separately lead to suboptimal solutions. In this paper, we propose two techniques to enhance the speedup of mapping/scheduling solutions:...

This work presents a knowledge-based task and motion planning framework based on a version of the FastForward task planner. A reasoning process on symbolic literals in terms of knowledge and geometric information about the workspace, together with the use of a physics-based motion planner, is proposed to evaluate the applicability and feasibility of manipulation actions and to compute the heuri...

In this paper, we present an architecture for high-level aspects of taskoriented dialog that integrates interpretation and generation, as well as domain-level and dialog-level knowledge. We report and analyze two implemented systems based on this architecture, including one for meeting support and another military medic assistance, and we discuss our experiences with the first system. We conclu...

AbstructIntelligent robots interact with the real world by employing their advanced sensory mechanisms to perceive their environment, and using their effectors and tools to change the state of their environment. Some of the important capabilities which endow “intelligence” to those robots include, (1) planning, i.e., given a goal, the ability to generate a set of task plans which will lead to a...

Modern discriminative predictors have been shown to match natural intelligences in specific perceptual tasks in image classification, object and part detection, boundary extraction, etc. However, a major advantage that natural intelligences still have is that they work well for all perceptual problems together, solving them efficiently and coherently in an integrated manner. In order to capture...