Matching Items (250)
Filtering by
- All Subjects: robotics
- All Subjects: artificial intelligence
- Genre: Masters Thesis
- Member of: ASU Electronic Theses and Dissertations
Description
A Graph Neural Network (GNN) is a type of neural network architecture that operates on data consisting of objects and their relationships, which are represented by a graph. Within the graph, nodes represent objects and edges represent associations between those objects. The representation of relationships and correlations between data is unique to graph structures. GNNs exploit this feature of graphs by augmenting both forms of data, individual and relational, and have been designed to allow for communication and sharing of data within each neural network layer. These benefits allow each node to have an enriched perspective, or a better understanding, of its neighbouring nodes and its connections to those nodes. The ability of GNNs to efficiently process high-dimensional node data and multi-faceted relationships among nodes gives them advantages over neural network architectures such as Convolutional Neural Networks (CNNs) that do not implicitly handle relational data. These quintessential characteristics of GNN models make them suitable for solving problems in which the correspondences among input data are needed to produce an accurate and precise representation of these data. GNN frameworks may significantly improve existing communication and control techniques for multi-agent tasks by implicitly representing not only information associated with the individual agents, such as agent position, velocity, and camera data, but also their relationships with one another, such as distances between the agents and their ability to communicate with one another. One such task is a multi-agent navigation problem in which the agents must coordinate with one another in a decentralized manner, using proximity sensors only, to navigate safely to their intended goal positions in the environment without collisions or deadlocks. The contribution of this thesis is the design of an end-to-end decentralized control scheme for multi-agent navigation that utilizes GNNs to prevent inter-agent collisions and deadlocks. The contributions consist of the development, simulation and evaluation of the performance of an advantage actor-critic (A2C) reinforcement learning algorithm that employs actor and critic networks for training that simultaneously approximate the policy function and value function, respectively. These networks are implemented using GNN frameworks for navigation by groups of 3, 5, 10 and 15 agents in simulated two-dimensional environments. It is observed that in $40\%$ to $50\%$ of the simulation trials, between 70$\%$ to 80$\%$ of the agents reach their goal positions without colliding with other agents or becoming trapped in deadlocks. The model is also compared to a random run simulation, where actions are chosen randomly for the agents and observe that the model performs notably well for smaller groups of agents.
ContributorsAyalasomayajula, Manaswini (Author) / Berman, Spring (Thesis advisor) / Mian, Sami (Committee member) / Pavlic, Theodore (Committee member) / Arizona State University (Publisher)
Created2022
Description
Reinforcement Learning(RL) algorithms have made a remarkable contribution in the eld of robotics and training human-like agents. On the other hand, Evolutionary Algorithms(EA) are not well explored and promoted to use in the robotics field. However, they have an excellent potential to perform well. In thesis work, various RL learning algorithms like Q-learning, Deep Deterministic Policy Gradient(DDPG), and Evolutionary Algorithms(EA) like Harmony Search Algorithm(HSA) are tested for a customized Penalty Kick Robot environment. The experiments are done with both discrete and continuous action space for a penalty kick agent. The main goal is to identify which algorithm suites best in which scenario. Furthermore, a goalkeeper agent is also introduced to block the ball from reaching the goal post using the multiagent learning algorithm.
ContributorsTrivedi, Maitry Ronakbhai (Author) / Amor, Heni Ben (Thesis advisor) / Redkar, Sangram (Thesis advisor) / Sugar, Thomas (Committee member) / Arizona State University (Publisher)
Created2021
Description
Traditional Reinforcement Learning (RL) assumes to learn policies with respect to reward available from the environment but sometimes learning in a complex domain requires wisdom which comes from a wide range of experience. In behavior based robotics, it is observed that a complex behavior can be described by a combination of simpler behaviors. It is tempting to apply similar idea such that simpler behaviors can be combined in a meaningful way to tailor the complex combination. Such an approach would enable faster learning and modular design of behaviors. Complex behaviors can be combined with other behaviors to create even more advanced behaviors resulting in a rich set of possibilities. Similar to RL, combined behavior can keep evolving by interacting with the environment. The requirement of this method is to specify a reasonable set of simple behaviors. In this research, I present an algorithm that aims at combining behavior such that the resulting behavior has characteristics of each individual behavior. This approach has been inspired by behavior based robotics, such as the subsumption architecture and motor schema-based design. The combination algorithm outputs n weights to combine behaviors linearly. The weights are state dependent and change dynamically at every step in an episode. This idea is tested on discrete and continuous environments like OpenAI’s “Lunar Lander” and “Biped Walker”. Results are compared with related domains like Multi-objective RL, Hierarchical RL, Transfer learning, and basic RL. It is observed that the combination of behaviors is a novel way of learning which helps the agent achieve required characteristics. A combination is learned for a given state and so the agent is able to learn faster in an efficient manner compared to other similar approaches. Agent beautifully demonstrates characteristics of multiple behaviors which helps the agent to learn and adapt to the environment. Future directions are also suggested as possible extensions to this research.
ContributorsVora, Kevin Jatin (Author) / Zhang, Yu (Thesis advisor) / Yang, Yezhou (Committee member) / Praharaj, Sarbeswar (Committee member) / Arizona State University (Publisher)
Created2021
Description
Machine learning models can pick up biases and spurious correlations from training data and projects and amplify these biases during inference, thus posing significant challenges in real-world settings. One approach to mitigating this is a class of methods that can identify filter out bias-inducing samples from the training datasets to force models to avoid being exposed to biases. However, the filtering leads to a considerable wastage of resources as most of the dataset created is discarded as biased. This work deals with avoiding the wastage of resources by identifying and quantifying the biases. I further elaborate on the implications of dataset filtering on robustness (to adversarial attacks) and generalization (to out-of-distribution samples). The findings suggest that while dataset filtering does help to improve OOD(Out-Of-Distribution) generalization, it has a significant negative impact on robustness to adversarial attacks. It also shows that transforming bias-inducing samples into adversarial samples (instead of eliminating them from the dataset) can significantly boost robustness without sacrificing generalization.
ContributorsSachdeva, Bhavdeep Singh (Author) / Baral, Chitta (Thesis advisor) / Liu, Huan (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2021
Description
Instructional prompts are a novel technique that can significantly improve the performance of natural language processing tasks by specifying the task instruction to the language model. This is the first paper that uses instructional prompts to improve performance of the question answering task in biomedical domain. This work makes two significant contributions. Firstly, a question answer dataset of 600K question answer pairs has been developed by using the medical textbook ‘Differential Diagnosis Primary Care’, which contains information on how to diagnose a patient by observing their disease symptoms. Secondly, a question answering language model augmented with instructional prompts has been developed by training on the medical information extracted from the book ‘Differential Diagnosis Primary Care’. Experiments have been conducted to demonstrate that it performs better than a normal question answering model that does not use instructional prompts. Instructional prompts are based on prompt tuning and prefix tuning, which are novel techniques which can help train language model to do specific downstream tasks by keeping majority of model parameters frozen, and only optimizing a small number of continuous task-specific vectors (called the prefixes).
ContributorsSaxena, Sharad (Author) / Baral, Chitta (Thesis advisor) / Blanco, Eduardo (Committee member) / Anwar, Saadat (Committee member) / Arizona State University (Publisher)
Created2021
Description
Recently, Generative Adversarial Networks (GANs) have been applied to the problem of Cold-Start Recommendation, but the training performance of these models is hampered by the extreme sparsity in warm user purchase behavior. This thesis introduces a novel representation for user-vectors by combining user demographics and user preferences, making the model a hybrid system which uses Collaborative Filtering and Content Based Recommendation. This system models user purchase behavior using weighted user-product preferences (explicit feedback) rather than binary user-product interactions (implicit feedback). Using this a novel sparse adversarial model, Sparse ReguLarized Generative Adversarial Network (SRLGAN), is developed for Cold-Start Recommendation. SRLGAN leverages the sparse user-purchase behavior which ensures training stability and avoids over-fitting on warm users. The performance of SRLGAN is evaluated on two popular datasets and demonstrate state-of-the-art results.
ContributorsShah, Aksheshkumar Ajaykumar (Author) / Venkateswara, Hemanth (Thesis advisor) / Berman, Spring (Thesis advisor) / Ladani, Leila J (Committee member) / Arizona State University (Publisher)
Created2022
Description
The ability for aerial manipulators to stay aloft while interacting with dynamic environments is critical for successfully in situ data acquisition methods in arboreal environments. One widely used platform utilizes a six degree of freedom manipulator attached to quadcoper or octocopter, to sample a tree leaf by maintaining the system in a hover while the arm pulls the leaf for a sample. Other system are comprised of simpler quadcopter with a fixed mechanical device to physically cut the leaf while the system is manually piloted. Neither of these common methods account or compensate for the variation of inherent dynamics occurring in the arboreal-aerial manipulator interaction effects. This research proposes force and velocity feedback methods to control an aerial manipulation platform while allowing waypoint navigation within the work space to take place. Using these methods requires minimal knowledge of the system and the dynamic parameters. This thesis outlines the Robot Operating System (ROS) based Open Autonomous Air Vehicle (OpenUAV) simulations performed on the purposed three degree of freedom redundant aerial manipulation platform.
ContributorsCohen, Daniel (Author) / Das, Jnaneshwar (Thesis advisor) / Marvi, Hamidreza (Committee member) / Saldaña, David (Committee member) / Arizona State University (Publisher)
Created2022
Description
The drone industry is worth nearly 50 billion dollars in the public sector, and drone flight anomalies can cost up to 12 million dollars per drone. The project's objective is to explore various machine-learning techniques to identify anomalies in drone flight and express these anomalies effectively by creating relevant visualizations. The research goal is to solve the problem of finding anomalies inside drones to determine severity levels. The solution was visualization and statistical models, and the contribution was visualizations, patterns, models, and the interface.
ContributorsElenes Cazares, Jose R (Author) / Bryan, Chris (Thesis advisor) / Banerjee, Ayan (Committee member) / Gonzalez Sanchez, Javier (Committee member) / Arizona State University (Publisher)
Created2022
Description
In recent years, the development of Control Barrier Functions (CBF) has allowed safety guarantees to be placed on nonlinear control affine systems. While powerful as a mathematical tool, CBF implementations on systems with high relative degree constraints can become too computationally intensive for real-time control. Such deployments typically rely on the analysis of a system's symbolic equations of motion, leading to large, platform-specific control programs that do not generalize well. To address this, a more generalized framework is needed. This thesis provides a formulation for second-order CBFs for rigid open kinematic chains. An algorithm for numerically computing the safe control input of a CBF is then introduced based on this formulation. It is shown that this algorithm can be used on a broad category of systems, with specific examples shown for convoy platooning, drone obstacle avoidance, and robotic arms with large degrees of freedom. These examples show up to three-times performance improvements in computation time as well as 2-3 orders of magnitude in the reduction in program size.
ContributorsPietz, Daniel Johannes (Author) / Fainekos, Georgios (Thesis advisor) / Vrudhula, Sarma (Thesis advisor) / Pedrielli, Giulia (Committee member) / Pavlic, Theodore (Committee member) / Arizona State University (Publisher)
Created2022
Description
Event detection refers to the task of identifying event occurrences in a given natural language text. Event detection comprises two subtasks; recognizing event mention (event identification) and the type of event (event classification). Breaking from the sequence labeling and word classification approaches, this work models event detection, and its constituent subtasks of trigger identification and trigger classification, as independent sequence generation tasks. This work proposes a prompted multi-task generative model trained on event identification, classification, and combined event detection. The model is evaluated on on general-domain and biomedical-domain event detection datasets, achieving state-of-the-art results on the general-domain Roles Across Multiple Sentences (RAMS) dataset, establishing event detection benchmark performance on WikiEvents, and achieving competitive performance on the general-domain Massive Event Detection (MAVEN) dataset and the biomedical-domain Multi-Level Event Extraction (MLEE) dataset.
ContributorsAnantheswaran, Ujjwala (Author) / Baral, Chitta (Thesis advisor) / Kerner, Hannah (Committee member) / Gopalan, Nakul (Committee member) / Arizona State University (Publisher)
Created2022