Avoiding the Past: A Simple but Effective Strategy for Reactive Navigation

نویسندگان

  • Tucker R. Balch
  • Ronald C. Arkin
چکیده

|An issue central to the navigation problem is memory. Traditional systems build symbolic maps of the world for navigational reference. Reactive methods, in contrast, eliminate or minimize the use of memory. These reac-tive techniques have been remarkably successful at solving a wide range of navigational problems. Some problems, however, still present a challenge to reactive strategies, (box canyons for example). The addition of a local spatial memory allows a robot to avoid areas that have already been visited. \Avoiding the past" ooers a solution to the box canyon and other navigational problems. An avoid-past strategy has been implemented using a spatial memory within a schema-based motor control model. Experiments have produced promising results in simulation and on mobile robots. I. Introduction Reactive robotic control systems have emerged as an answer to many of the problems which arise in navigation across unmapped terrain. Reactive systems are characterized by tight sensor to motor couplings. Basic \reactions" to stimuli are combined to generate a resultant behavior. The processing requirements for these systems are greatly reduced in comparison to traditional symbolic methods. The reduced computational demand allows a reactive system to operate in real-time and in changing environments. Reactive methods diier from more traditional naviga-tional strategies in many respects-memory is certainly one of the most signiicant. Symbolic systems 1, 12] build and maintain internal representations of the world which are referenced for motion planning. In contrast, many reactive systems maintain a state memory at most, and act immediately on external stimuli 6, 9]. Robots utilizing reactive control exhibit local behavior like walking 7] and obstacle avoidance, but their higher-level performance can be limited. Box canyons, for example , are often a challenge for goal-oriented reactive systems. Such systems are adept at traveling into a canyon without collisions, but they cannot easily determine how to get out. This is often referred to as \the y at the

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Avoiding the Past: A Simple but E ective Strategy for Reactive Navigation

|An issue central to the navigation problem is memory. Traditional systems build symbolic maps of the world for navigational reference. Reactive methods, in contrast, eliminate or minimize the use of memory. These reactive techniques have been remarkably successful at solving a wide range of navigational problems. Some problems, however, still present a challenge to reactive strategies, (box ca...

متن کامل

Reactive navigation by fuzzy control

Reactive navigation can improve the performance of robotic systems by solving simple subtasks without requiring the update of internal representations or plans: it involves only the mapping of perceptual situations onto control commands. Fuzzy systems and neural networks are both eecient methods for learning such a mapping from training data, avoiding its annoying and error-prone programming. M...

متن کامل

A New Strategy for Simultaneous Compensation of Instantaneous Reactive Power and Harmonics of Non-Linear Loads (RESEARCH NOTE)

This paper presents a new control method for simultaneous compensation of instantaneous reactive power and current harmonics by parallel active filters (PAFs). Reference compensating currents of PAF are calculated using the subtraction of instantaneous power from its average value. In this way, it is possible omitting high/low pass filter(s) from the control circuit of PAF, which usually result...

متن کامل

Neural sensor-based navigation of wheeled mobile robot in unknown environment

In presented paper a new approach to a collisionfree trajectory generating for a wheeled mobile robot with Adaptive Critic Designs and Fuzzy Logic algorithm, is proposed. The presented discrete hierarchical control system consists of a trajectory generating algorithm based on a reactive navigation of the wheeled mobile robot in an unknown 2D environment with static obstacles, and a tracking con...

متن کامل

Implementing Temporal Radial Basis Function for Reactive Navigation of Mobile Robot

We present in this article, the realisation of reactive navigation module based on neural networks Like Temporal Radial Basis Functions (TRBF), with respect of security constraints and inherent robustness while using an Orthogonal Least Square algorithm (OLS). Applied to a structured type like interior of building, the mobile robot must assure its task of navigation mildly all while avoiding ob...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1993