Real-Time Reactive Control Layer Design for Intelligent Silver-Mate Robot on RTAI

Intelligent robots are capable of handling complex tasks that includes recognition of vocal commands, logical inference, autonomous navigation and manipulation, etc. To accomplish intelligent behaviors, researchers have proposed a number of control software architectures such as tripodal schematic control architecture (TSCA). To achieve real-time performance for robot's navigation, we have implemented software components in the reactive layer of TSCA on RTAI (Real-Time Application Interface) for our intelligent robot. In this project, structures of the reactive layer components is presented and Real-time performance of the designed reactive control layer is demonstrated via experimental results. You can also Subscribe to FINAL YEAR PROJECT'S by Email for more such projects and seminar.

Designed reactive control layer was implemented using RTAI. Version 3.1 of RTAI distribution was used, along with 2.4.27 version of Linux kernel and 0.7.69 Version of COMEDI3 drivers for the DAQ board. Since the Main SBC uses an 8-port serial board, real-time serial driver included in RTAI distribution was modified accordingly. COMEDI driver was also modified to support hardware timer functionality of the DAQ board.

There are two sonar controller boards on the system, one in charge of six sonar sensors around the front half of the robot platform and the other in charge of six sonar sensors around the rear half.

Recommended Project: Microcontroller based Mobile Phone Operated Land Rover

To obtain a sonar data periodically, an RT task is used. At every given time interval, RT task issues are command, waits for some time and issues read data command for each sonar sensor. Reception of serial data is handled using a callback function and an RT task, similar to LRF or IR Resource modules. Extracted sonar data is stored in shared memory.

In this paper, author explained how the real-time reactive control layer structure of modified TSCA architecture for Silver-Mate robot using RTAI is implemented. Experimental results demonstrates that our implementation is able to obtain sensor data periodically in a predictable manner and execute navigation commands in real-time.

As a further work, exhaustive testing will be performed on our implementation. Furthermore, this implementation will be integrated with resulting software components of other researches for final integration and test. This research will focus on use of Controller Area Network (CAN) and Ethernet for distributed computing environment for intelligent mobile robots.


Author:- K.Sai Baba Reddy, C.Bhanu Deepthi, S.Sarath Chandra


Download

Advertisements:-