Computer Engineering Commons^™

Autonomous Rock Segmentation From Lidar Point Clouds Using Machine Learning Approaches, Lauren E. Flanagan

Electronic Thesis and Dissertation Repository

Rover navigation on planetary surfaces currently uses a method called blind drive which requires a navigation goal as input from operators on Earth and uses camera images to autonomously detect obstacles. Images can be affected by lighting conditions, are not highly accurate from far distances, and will not work in the dark; these factors negatively impact the autonomous capabilities of rovers. By improving a rover's ability to autonomously detect obstacles, the capabilities of rovers in future missions would improve; for example, enabling exploration of permanently shadowed regions, and allowing faster driving speeds and farther travel distances. This thesis demonstrates how …

Utilizing Trajectory Optimization In The Training Of Neural Network Controllers, Nicholas Kimball

Master's Theses

Applying reinforcement learning to control systems enables the use of machine learning to develop elegant and efficient control laws. Coupled with the representational power of neural networks, reinforcement learning algorithms can learn complex policies that can be difficult to emulate using traditional control system design approaches. In this thesis, three different model-free reinforcement learning algorithms, including Monte Carlo Control, REINFORCE with baseline, and Guided Policy Search are compared in simulated, continuous action-space environments. The results show that the Guided Policy Search algorithm is able to learn a desired control policy much faster than the other algorithms. In the inverted pendulum …

Labeling Paths With Convolutional Neural Networks, Sean Wallace, Kyle Wuerch

Computer Engineering

With the increasing development of autonomous vehicles, being able to detect driveable paths in arbitrary environments has become a prevalent problem in multiple industries. This project explores a technique which utilizes a discretized output map that is used to color an image based on the confidence that each block is a driveable path. This was done using a generalized convolutional neural network that was trained on a set of 3000 images taken from the perspective of a robot along with matching masks marking which portion of the image was a driveable path. The techniques used allowed for a labeling accuracy …

“My Logic Is Undeniable”: Replicating The Brain For Ideal Artificial Intelligence, Samuel C. Adams

Senior Honors Theses

Alan Turing asked if machines can think, but intelligence is more than logic and reason. I ask if a machine can feel pain or joy, have visions and dreams, or paint a masterpiece. The human brain sets the bar high, and despite our progress, artificial intelligence has a long way to go. Studying neurology from a software engineer’s perspective reveals numerous uncanny similarities between the functionality of the brain and that of a computer. If the brain is a biological computer, then it is the embodiment of artificial intelligence beyond anything we have yet achieved, and its architecture is advanced …

The Role Of Uncertainty In Categorical Perception Utilizing Statistical Learning In Robots, Nathaniel V. Powell

Graduate College Dissertations and Theses

At the heart of statistical learning lies the concept of uncertainty.

Similarly, embodied agents such as robots

and animals must likewise address uncertainty, as sensation

is always only a partial reflection of reality. This

thesis addresses the role that uncertainty can play in

a central building block of intelligence: categorization.

Cognitive agents are able to perform tasks like categorical perception

through physical interaction (active categorical perception; ACP),

or passively at a distance (distal categorical perception; DCP).

It is possible that the former scaffolds the learning of

the latter. However, it is unclear whether DCP indeed scaffolds

ACP in humans and …

Neuron Clustering For Mitigating Catastrophic Forgetting In Supervised And Reinforcement Learning, Benjamin Frederick Goodrich

Doctoral Dissertations

Neural networks have had many great successes in recent years, particularly with the advent of deep learning and many novel training techniques. One issue that has affected neural networks and prevented them from performing well in more realistic online environments is that of catastrophic forgetting. Catastrophic forgetting affects supervised learning systems when input samples are temporally correlated or are non-stationary. However, most real-world problems are non-stationary in nature, resulting in prolonged periods of time separating inputs drawn from different regions of the input space.

Reinforcement learning represents a worst-case scenario when it comes to precipitating catastrophic forgetting in neural networks. …