Sensor-based Robot Navigation Research Articles

Histogram Refined Local Ternary Pattern-based Bilateral LPP for Vision Sensor-based Robot Navigation Guidance under Challenging Environments

The present paper proposes a new variant of bilateral locality preserving projection (BLPP), a nonlinear manifold learning technique, for vision sensor-based robot navigation guidance in challenging environments, suffering from both variations in ambient illumination levels and vision sensor noises and uncertainties in image acquisition. In its basic form, the adjacency graph in BLPP is formulated both in feature subspace and spatial subspace, simultaneously. The present work proposes to compute the feature weights using local ternary pattern (LTP), a lesser noise-sensitive feature descriptor, which is also robust against illumination variations. In addition, histogram refinement has been performed on the feature descriptor to encode the local neighborhood structure of the data, proposing a further augmented version of BLPP named histogram refined local ternary pattern-based BLPP (HRLTP-BLPP). Extensive real-life experiments with challenging photometric conditions and sensor noises have been performed to show the usefulness of HRLTP-BLPP over other competing, state-of-the-art approaches, utilized for robot navigation guidance.

Augmented and Virtual Reality Experiences for Learning Robotics and Training Integrative Thinking Skills

Learning through augmented reality (AR) and virtual reality (VR) experiences has become a valuable approach in modern robotics education. This study evaluated this approach and investigated how 99 first-year industrial engineering students explored robot systems through such online experiences while staying at home. The objective was to examine learning in the AR/VR environment and evaluate its contribution to understanding the robot systems and to fostering integrative thinking. During the AR experiences that we developed using Vuforia Studio, the students learned about TurtleBot2 and RACECAR MN robots while disassembling and modifying their models and by obtaining information about their components. In the VR experience with the RacecarSim simulator, the students explored sensor-based robot navigation. Quizzes were used to assess understanding of robot systems, and a post-workshop questionnaire evaluated the workshop’s contribution to learning about the robots and to training integrative thinking skills. The data indicate that the students gained understanding of the robot systems, appreciated the contribution of the augmented and virtual reality apps, and widely used integrative thinking throughout the practice. Our study shows that AR apps and virtual simulators can be effectively used for experiential learning about robot systems in online courses. However, these experiences cannot replace practice with real robots.

Lessons Learned in Integration for Sensor-Based Robot Navigation Systems

This paper presents our work of integration during the last years within the context of sensor-based robot navigation systems. In our motion system, as in many others, there are functionalities involved such as modeling, planning or motion control, which have to be integrated within an architecture. This paper addresses this problematic. Furthermore, we also discuss the lessons learned while: (i) designing, testing and validating techniques that implement the functionalities of the navigation system, (ii) building the architecture of integration, and (iii) using the system on several robots equipped with different sensors in different laboratories.

Indoor robot navigation using log-polar local maps

In this paper we consider the problem of building a new class of metric maps representing the surroundings of a mobile robot moving in an unstructured indoor environment. Maps are conceived with a metric based on a log-polar space representation: this retina-like representation allows a better definition of objects near the robot, giving less importance to far ones. Information provided at each step by ultrasonic sensors has an uncertainty that is conceptualised as a fuzzy measure and is combined with previous data using Smets transferable believe model. The map building algorithm is integrated in a sensor-based robot navigation system able to recognise some characteristics of the environment. A pattern-matching algorithm, based on Mellin transform, takes advantage on the particular retina-like representation.

Automatic Generation of Fuzzy Rules Using The Fuzzy Behaviorist Approach: The Case of Sensor-Based Robot Navigation

ABSTRACTA system for automatic generation of fuzzy rules is proposed which is based on a new approach, called “Fuzzy Behaviorist,” and on its associated formalism for rule base development in behavior-based robot control systems. The automated generator of fuzzy rules automatically constructs the membership functions of fuzzy rules that implement reasoning schemes that have been expressed in qualitative terms. The system also checks for completeness of the rule base and independence and/or redundancy of the rules to ensure that the requirements of the formalism are satisfied. Examples of the automatic generation of fuzzy rules for cases involving suppression and/or inhibition of fuzzy behaviors are given and discussed. Experimental results obtained with the automated fuzzy rule generator applied to the domain of sensor-based navigation in a priori unknown environments using one of our autonomous test-bed robots and a real car in outdoor environments are then presented and discussed to illustrate the feasi...