Search results
(1 - 2 of 2)
- Title
- Data-Driven Methods for Soft Robot Control and Turbulent Flow Models
- Creator
- Lopez, Esteban Fernando
- Date
- 2022
- Description
-
The world today has seen an exponential increase in its usage of computers for communication and measurement. Thanks to recent technologies,...
Show moreThe world today has seen an exponential increase in its usage of computers for communication and measurement. Thanks to recent technologies, we are now able to collect more data than ever before. This has dawned a new age of data-driven methods which can describe systems and behaviors with increasing accuracy. Whereas before we relied on the expertise of a few professionals with domain-specific knowledge developed over years of rigorous study, we are now able to rely on collected data to reveal patterns, develop novel ideas, and offer solutions to the world’s engineering problems. No domain is safe. Within the engineering realm, data-driven methods have seen vast usage in the areas of control and system identification. In this thesis we explore two areas of data-driven methods, namely reinforcement learning and data-driven causality. Reinforcement learning is a method by which an agent learns to increase its selection of ideal actions and behaviors which result in an increasing reward. This method was applied to a soft-robotic concept called the JAMoEBA to solve various tasks of interest in the robotics community, specifically tunnel navigation, obstacle field navigation, and object manipulation. A validation study was conducted to show the complications that arise when applying reinforcement learning to such a complex system. Nevertheless, it was shown that reinforcement learning is capable of solving three key tasks (static tunnel navigation, obstacle field navigation, and object manipulation) using specific simulation and learning hyperparameters. Data-driven causality encompasses a range of metrics and methods which attempt to uncover causal relationships between variables in a system. Several information theoretic causal metrics were developed and applied to nine mode turbulent flow data set which represents the Moehlis model. It was shown that careful consideration into the method used was required to identify significant causal relationships. Causal relationships were shown to converge over several hundred realizations of the turbulent model. Furthermore, these results match the expected causal relationships given known information of self-sustaining processes in turbulence, validating the method’s ability to identify causal relationships in turbulence.
Show less
- Title
- Development of Granular Jamming Soft Robots from Boundary Constrained to Interconnected Systems
- Creator
- Tanaka, Koki
- Date
- 2023
- Description
-
This dissertation provides a detailed study on the conceptualization, creation, and optimization of a unique, interconnected soft robot system...
Show moreThis dissertation provides a detailed study on the conceptualization, creation, and optimization of a unique, interconnected soft robot system. It introduces a flexible assembly of locomotive robotic modules interconnected by an envelope, capable of granular jamming. In doing so, it highlights the practical capabilities of these interconnected modules to adapt and function cohesively as a single robot system.As a precursor to the primary investigation, the study initially presents the development and experimental validation of a boundary constrained mobile soft robot. This design leverages granular jamming for locomotion and object grasping, thereby laying a robust foundation for the subsequent exploration of complex soft robotic systems.The cornerstone of this study is the development of an interconnected soft robot system, where locomotive robotic modules, primarily composed of an elastic material, are bound together by a flexible envelope designed for granular jamming. The robotic modules, fundamentally constructed from an elastic material, incorporate origami-inspired artificial muscle actuators. These actuators, with their semi-soft characteristics, complement the inherent flexibility of the modules and play a significant role in facilitating module propulsion. Although the design incorporates a traditional rigid power source, as opposed to a fully soft robot system, the integration of a pneumatic power method into the system successfully reduces the mechanical intricacy and unwieldiness typically associated with rigid mechanisms.This research further probes into the diverse applications of this interconnected soft robot system. Its ability to shape-shift and maintain these forms during locomotion exemplifies a robust control strategy for the system that may undergo substantial deformation, proving instrumental in dynamic environments. The study demonstrates a methodology for object manipulation and obstacle avoidance that does not rely heavily on precise control and sensing. Instead, it utilizes the inherent compliance of the soft robot system. In a notable departure from previous studies, the system also exhibits a unique capability for ascending and traversing inclined surfaces.Additionally, the study dives into the optimization of the interconnected robot system via a physics-based simulation and genetic algorithm. This approach results in an assortment of optimized configurations that excel in object grasping tasks of various shapes, thereby laying a robust groundwork for the progression of soft robotics in the future.In conclusion, this investigation reveals groundbreaking insights into the field of soft robotics through the successful design and optimization of an interconnected soft robot system. Its standout performances in deformation, manipulation, and navigation tasks set it apart. This work serves to significantly enhance the adaptability and functionality of future robotic systems, pushing the edge of what is possible across a diverse range of sectors. By portraying a significant step towards a future where robots can dynamically adapt to their environments and efficiently accomplish complex tasks, this dissertation exemplifies a transformative stride in the field.
Show less