2026-05-25T00:45:16Zhttps://keep.lib.asu.edu/oai/request

oai:keep.lib.asu.edu:node-1332112024-12-18T20:58:30Zoai_pmh:alloai_pmh:repo_items

133211 https://hdl.handle.net/2286/R.I.50206 http://rightsstatements.org/vocab/InC/1.0/ 2018-05 2021-05-29T22:37:55 25 pages eng Martin, Sarah Ben Amor, Hani Fainekos, Georgios Barrett, The Honors College Text This thesis aims to improve neural control policies for self-driving cars. State-of-the-art navigation software for self-driving cars is based on deep neural networks, where the network is trained on a dataset of past driving experience in various situations. With previous methods, the car can only make decisions based on short-term memory. To address this problem, we proposed that using a Neural Turing Machine (NTM) framework adds long-term memory to the system. We evaluated this approach by using it to master a palindrome task. The network was able to infer how to create a palindrome with 100% accuracy. Since the NTM structure proves useful, we aim to use it in the given scenarios to improve the navigation safety and accuracy of a simulated autonomous car. Artificial Intelligence Autonomous Driving Deep learning Beyond Deep Learning: Synthesizing Navigation Programs using Neural Turing Machines