Modular Optimization for Robotic Explorers
نویسندگان
چکیده
Robotic explorers perform multiple tasks and have multiple constraints to optimize. Planning the best sequence of tasks requires information about how a given sequence will affect the constraints and goals of the explorer. Modules for all constraints and goals are created, each one of which evaluates a given plan from its point of view. The resulting values of the modules are then combined in a weighted sum, producing a score for each plan. The best plan is then selected.
منابع مشابه
EFFICIENT SIMULATION FOR OPTIMIZATION OF TOPOLOGY, SHAPE AND SIZE OF MODULAR TRUSS STRUCTURES
The prevalent strategy in the topology optimization phase is to select a subset of members existing in an excessively connected truss, called Ground Structure, such that the overall weight or cost is minimized. Although finding a good topology significantly reduces the overall cost, excessive growth of the size of topology space combined with existence of varied types of design variables challe...
متن کاملHolarchical Systems and Emotional Holons: Biologically-Inspired System Designs for Control of Autonomous Aerial Vehicles
The BEES (Bio-inspired Engineering for Exploration Systems) for Mars project at NASA Ames Research Center has the goal of developing bio-inspired flight control strategies to enable aerial explorers for Mars scientific investigations. This paper presents a summary of our ongoing research into biologically inspired system designs for control of unmanned autonomous aerial vehicle communities for ...
متن کاملUsing Modular Pole for Multi-Objective Design Optimization of a Linear Permanent Magnet Synchronous Motor by Particle Swarm Optimization (PSO)
In this paper particle swarm optimization (PSO) is used for a design optimization of a linear permanent magnet synchronous motor (LPMSM) considering ultra low thrust force ripples, low magnet consumption, improved efficiency and thrust. The influence of PM material is discussed, too and the modular poles are proposed to achieve the best characteristic. PM dimensions and material, air gap and mo...
متن کاملA Robotic Mobile Sensor Network for Achieving Scientific Measurements in Challenging Environments
Recently, it has been discovered that the giant ice sheets covering Greenland and Antarctica have been shrinking at an accelerated rate. While it is believed that these regions hold important information related to global climate change, there is still insufficient data to be able to accurately predict the future behavior of those ice sheets. Satellites have been able to map the ice sheet eleva...
متن کاملLearning to Move in Modular Robots using Central Pattern Generators and Online Optimization
This article addresses the problem of how modular robotics systems, i.e. systems composed of multiple modules that can be configured into different robotic structures, can learn to locomote. In particular, we tackle the problems of online learning, that is, learning while moving, and the problem of dealing with unknown arbitrary robotic structures. We propose a framework for learning locomotion...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1999