Fast connectionist learning for trailer backing using a real robot
نویسندگان
چکیده
This paper presents the application of a connection-ist control-learning system to an autonomous mini-robot. The system's design is severely constrained by the computing power and memory available on board the mini-robot and the on-board training time is greatly limited by the short life of the battery. The system is capable of rapid unsupervised learning of output responses in temporal domains through the use of eligibility traces and data sharing within topologically de-ned neighborhoods.
منابع مشابه
Rapid unsupervised connectionist learning for backing a robot with two trailers
This paper presents an application of a connec-tionist control-learning system designed for use on an autonomous mini-robot. This system was formerly shown to form useful two-dimensional mappings rapidly when applied to backing a car with a single trailer. In the current paper the learning system is extended to three dimensions and applied to a similar but signiicantly more diicult problem. The...
متن کاملTrajectory Tracking Weeled Mobile Robot Using Backstepping Method with Connection off Axle Trailer
The connection of the tractor to the inactive trailer or motor vehicle causes a motion control problem when turning in the screw, forward or backward movements and high speeds. This is due to the inactive trailer being controlled by the tracking using a physical link that is not affected by the movement. Trailers usually take tracks under these conditions. This phenomenon is called Jack Knife. ...
متن کاملBackward and forward path following control of a wheeled robot
A wheeled mobile robot is one of the most important types of mobile robots. A subcategory of these robots is wheeled robots towing trailer(s). Motion control problem, especially in backward motion is one of the challenging research topics in this field. In this article, a control algorithm for path-following problem of a tractor-trailer system is provided, which at the same time provides the ab...
متن کاملDynamic Obstacle Avoidance by Distributed Algorithm based on Reinforcement Learning (RESEARCH NOTE)
In this paper we focus on the application of reinforcement learning to obstacle avoidance in dynamic Environments in wireless sensor networks. A distributed algorithm based on reinforcement learning is developed for sensor networks to guide mobile robot through the dynamic obstacles. The sensor network models the danger of the area under coverage as obstacles, and has the property of adoption o...
متن کاملTrajectory Generation for the N - trailer problem using Goursat Normal Form *
In this paper, we show how ihe machinery of ederior differential sysiemr can k wed i o help soltie nonholonomic motion planning problems. Since the Gorrsat normal form for ezterior differential systems is dual i o chained form for vectorfields, we solve the problem of steering a mobile robot with n trailers by convcriing ihe system int.0 chained form, doing ihe paih-planning in the chained form...
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 1996