Open Access. Powered by Scholars. Published by Universities.®
- Discipline
- Institution
Articles 1 - 2 of 2
Full-Text Articles in Engineering
Synthesis Of Technical Requirements And Considerations For Automated Snowplow Route Optimization: Final Report, Jonathan Dowds, James Sullivan
Synthesis Of Technical Requirements And Considerations For Automated Snowplow Route Optimization: Final Report, Jonathan Dowds, James Sullivan
University of Vermont Transportation Research Center
DOTs and other transportation agencies are increasingly using automated methods for snowplow route optimization, which have been demonstrated to produce significant savings when they result in the implementation of new routes. However, many route optimization projects have fallen short of implementation due to technical/operational issues with the routes produced or institutional barriers to change. These shortcomings can be substantially mitigated with improvements to the process of soliciting, selecting, and managing the route optimization software or service provider. This project’s objective was to provide DOTs with the tools needed to make these improvements. The key lessons from this project are provided …
On The Impact Of Gravity Compensation On Reinforcement Learning In Goal-Reaching Tasks For Robotic Manipulators, Jonathan Fugal, Hasan A. Poonawala, Jihye Bae
On The Impact Of Gravity Compensation On Reinforcement Learning In Goal-Reaching Tasks For Robotic Manipulators, Jonathan Fugal, Hasan A. Poonawala, Jihye Bae
Electrical and Computer Engineering Faculty Publications
Advances in machine learning technologies in recent years have facilitated developments in autonomous robotic systems. Designing these autonomous systems typically requires manually specified models of the robotic system and world when using classical control-based strategies, or time consuming and computationally expensive data-driven training when using learning-based strategies. Combination of classical control and learning-based strategies may mitigate both requirements. However, the performance of the combined control system is not obvious given that there are two separate controllers. This paper focuses on one such combination, which uses gravity-compensation together with reinforcement learning (RL). We present a study of the effects of gravity …