Open Access. Powered by Scholars. Published by Universities.®
- Publication
- Publication Type
Articles 1 - 3 of 3
Full-Text Articles in Engineering
An Approach To Fast Multi-Robot Exploration In Buildings With Inaccessible Spaces, Matt Mcneill, Damian Lyons
An Approach To Fast Multi-Robot Exploration In Buildings With Inaccessible Spaces, Matt Mcneill, Damian Lyons
Faculty Publications
The rapid exploration of unknown environments is a common application of autonomous multi-robot teams. For some types of exploration missions, a mission designer may possess some rudimentary knowledge about the area to be explored. For example, the dimensions of a building may be known, but not its floor layout or the location of furniture and equipment inside. For this type of mission, the Space- Based Potential Field (SBPF) method is an approach to multirobot exploration which leverages a priori knowledge of area bounds to determine robot motion. Explored areas and obstacles exert a repulsive force, and unexplored areas exert an …
Evaluation Of Field Of View Width In Stereo-Vision-Based Visual Homing, Damian Lyons, Benjamin Barriage, Luca Del Signore
Evaluation Of Field Of View Width In Stereo-Vision-Based Visual Homing, Damian Lyons, Benjamin Barriage, Luca Del Signore
Faculty Publications
Visual homing is a local navigation technique used to direct a robot to a previously seen location by comparing the image of the original location with the current visual image. Prior work has shown that exploiting depth cues such as image scale or stereo-depth in homing leads to improved homing performance. While it is not unusual to use a panoramic field of view (FOV) camera in visual homing, it is unusual to have a panoramic FOV stereo-camera. So, while the availability of stereo-depth information may improve performance, the concomitant-restricted FOV may be a detriment to performance, unless specialized stereo hardware …
Robot Navigation In Cluttered Environments With Deep Reinforcement Learning, Ryan Weideman
Robot Navigation In Cluttered Environments With Deep Reinforcement Learning, Ryan Weideman
Master's Theses
The application of robotics in cluttered and dynamic environments provides a wealth of challenges. This thesis proposes a deep reinforcement learning based system that determines collision free navigation robot velocities directly from a sequence of depth images and a desired direction of travel. The system is designed such that a real robot could be placed in an unmapped, cluttered environment and be able to navigate in a desired direction with no prior knowledge. Deep Q-learning, coupled with the innovations of double Q-learning and dueling Q-networks, is applied. Two modifications of this architecture are presented to incorporate direction heading information that …