N. Nirmal Singh

Vision Based Autonomous Robot Navigation

This monograph is devoted to the theory and development of autonomous navigation of mobile robots using computer vision based sensing mechanism. The conventional robot navigation systems, utilizing traditional sensors like ultrasonic, IR, GPS, laser sensors etc., suffer several drawbacks related to either the physical limitations of the sensor or incur high cost. Vision sensing has emerged as a popular alternative where cameras can be used to reduce the overall cost, maintaining high degree of intelligence, flexibility and robustness.This book includes a detailed description of several new approaches for real life vision based autonomous navigation algorithms and SLAM. It presents the concept of how subgoal based goal-driven navigation can be carried out using vision sensing. The development concept of vision based robots for path/line tracking using fuzzy logic is presented, as well as how a low-cost robot can be indigenously developed in the laboratory with microcontroller based sensor systems. The book describes successful implementation of integration of low-cost, external peripherals, with off-the-shelf procured robots. An important highlight of the book is that it presents a detailed, step-by-step sample demonstration of how vision-based navigation modules can be actually implemented in real life, under 32-bit Windows environment. The book also discusses the concept of implementing vision based SLAM employing a two camera based system.

A PIC microcontroller-based system for real-life interfacing of external peripherals with a mobile robot

The present article describes the development of a peripheral interface controller (PIC) microcontroller-based system for interfacing external add-on peripherals with a real mobile robot, for real life applications. This system serves as an important building block of a complete integrated vision-based mobile robot system, integrated indigenously in our laboratory. The system is composed of the KOALA mobile robot in conjunction with a personal computer (PC) and a two-camera-based vision system where the PIC microcontroller is used to drive servo motors, in interrupt-driven mode, to control additional degrees of freedom of the vision system. The performance of the developed system is tested by checking it under the control of several user-specified commands, issued from the PC end.

Simultaneous Localization and Mapping (SLAM) in Mobile Robots

This chapter first introduces the concept of SLAM for navigation of mobile robots and then describes the extended Kalman filter (EKF) based SLAM algorithms in detail. Next we consider a more complex scenario where this EKF based SLAM algorithm is implemented in presence of incorrect knowledge of sensor statistics and discuss how fuzzy or neuro-fuzzy supervision can help in improving the estimation performance in such situations. In this context, we also discuss how evolutionary optimization strategies can be employed to automatically learn the free parameters of such neuro-fuzzy supervisors.

Vision-Based Mobile Robot Navigation Using Subgoals

This chapter discusses how a vision based robot navigation scheme can be developed, in a two-layered architecture, in collaboration with IR sensors. The algorithm employs a subgoal based scheme where the attempt is made to follow the shortest path to reach the final goal and also simultaneously achieve the desired obstacle avoidance. The algorithm operates in an iterative fashion with the objective of creating the next subgoal and navigating upto this point in a single iteration such that the final goal is reached in minimum number of iterations, as far as practicable.

A two-camera-based vision system for image feature identification, feature tracking and distance measurement by a mobile robot

This paper presents a two-camera-based vision system for image feature selection, tracking of the selected features and the calculation of 3D distance of the selected features. The feature tracking approach is based on minimisation of the sum of squared intensity differences between the past and the current window, which determines whether a current window is a warped version of the past window. The 3D positions of these features can be calculated on the basis of the known image coordinates of the same point/window in the left and right camera images. The distance calculation is carried out by employing ‘midpoint of closest approach’. The vision system with the controlling architecture is implemented with the KOALA mobile robot. The system has been tested for real life environment in our laboratory and the experiments showed that the system can reliably detect features and track in subsequent frames and the 3D distances calculated for tracked features showed satisfactory accuracy.

Vision Based SLAM in Mobile Robots

This chapter is an extension of the previous chapter and it discusses how the previously discussed concept of SLAM for mobile robots can be actually implemented in real-life in an indoor environment. The system developed employs a two camera based vision system which successfully performs image feature identification and tracking.

Mobile Robot Navigation

This chapter introduces the basic concepts of autonomous navigation of mobile robots and the utility of using vision as the sensing mechanism in achieving the desired objectives. The chapter discusses the broad categories of vision-based navigation in indoor and outdoor environments. Different prominent directions of research in this context are introduced and also different broad modalities of obstacle detection and avoidance are presented.

Vision Based Mobile Robot Path/Line Tracking

In this chapter we discuss how a vision based navigation scheme can be developed for indoor path/line tracking, so that the robot is equipped to follow a narrow line or to travel along a wide path. The scheme utilizes fuzzy logic to achieve the desired objective. The scheme is so developed that, in case of absence of obstacles in front, it will guide the robot to navigate using fuzzy vision-based navigation. The scheme also employs a fuzzy IR-based obstacle avoidance strategy which becomes active on detection of any obstacle.

Sample Implementations of Vision-Based Mobile Robot Algorithms

This chapter presents a detailed, step-by-step demonstration of how vision-based navigation modules can be actually implemented in real life, under 32-bit Windows environment. These lessons start with a simple development of capturing image frames from a running video and then gradually proceeds to more complex tasks of incorporating image processing capabilities e.g. filtering techniques, contrast enhancement, adaptive thresholding etc. Then the lessons demonstrate how to extract path for the robot from such images and how a rulebased approach can be utilized to determine left and right wheel speed settings of a differential drive system.

Interfacing External Peripherals with a Mobile Robot

This chapter discusses how real-life interfacing of external peripherals with a ready-made mobile robot can be successfully achieved. Such a system is hoped to be useful for those research scenarios where, many-a-time, because of the fund constraints, a complete robot system cannot be procured with all its accessories and sensor systems. This chapter discusses how such interfacing can be achieved for the KOALA robot using serial communication in interrupt driven mode.