Date of Award

12-1-2022

Language

English

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

College/School/Department

Department of Computer Science

Content Description

1 online resource (x, 84 pages) : illustrations (some color)

Dissertation/Thesis Chair

Chinwe Ekenna

Committee Members

Paliath Narendran, Ming-Ching Chang, Mukulika Ghosh

Keywords

Motion Planning, Multi-Robot Collaboration, Uncertainty Analysis, Robots, Autonomous robots, Mobile robots

Subject Categories

Artificial Intelligence and Robotics

Abstract

A robot is an agent that can bring some changes to the environment around it. Motion planning is the problem of carrying out specialized tasks by a robot by either moving itself or some other object (usually called \textit{payload}) from one place to another. In a real-world scenario, a robot is faced with constraints such as momentum, friction, sensor inaccuracies, etc., that can affect its decision-making while performing specialized tasks. These constraints are identified as uncertainties, and successful planning involves making provisions for such uncertainties. In this work, we present methods like stochastic processes, sequential inference, and pattern recognition to identify different sources of uncertainties and mitigate them to enable successful planning in the presence of uncertainties in real-world scenarios. Uncertainty analysis is important in robotic applications where tolerance of error is marginal like space missions, military operations, or even urban cities for infrastructure development. Under current technological development, error margins limit the applications of robots in these fields. With the advent of uncertainty analysis in robotics, military applications of robots can be extended to supervision, police surveillance, tactical support in hostile environments, and finally, preparation of invasive autonomous strikes in enemy territories. In space missions, where a minor error can lead to the loss of months of research work, public money, and in extreme cases, human lives, it is important to analyze the risks involved in autonomous planning and provide autonomous resolutions for them online. In urban infrastructure development, where heavy payload is moved at a regular basis, it is difficult to rely on autonomous systems that are unaware of the uncertainties involved in the tasks to be performed and do not respond to errors in the planning process. This study further improves the ease of entry of autonomous robots for infrastructure developers and engineers in different life-saving and innovative areas of research.

Download

Share

COinS