Type of Submission
Poster
Keywords
Autonomous vehicles, RADAR, GPS, collision avoidance, Waypoint Navigation
Abstract
This presentation describes a subset of the systems devised for this year's autonomous golf cart senior design project. Our goal is to explore the possibilities of low cost autonomy using only radar and GPS for environmental sensing and navigation. Although autonomous and semi-autonomous ground vehicles are a relatively new reality, prototypes have been a subject of engineering research for decades, often utilizing an array of sensors and sensor fusion techniques. State of the art autonomous ground vehicle prototypes typically use a combination of LIDAR and other distance sensors (such as radar or sonar) as well as cameras and GPS, sometimes also including functionality for inter-vehicle connectivity. We believe that a low cost solution can be achieved using only radar and GPS. Such a system requires more creativity and robustness in software design, but would maintain the essential capabilities of self-localization, path navigation, and obstacle avoidance. Compared to the specified alternatives, GPS and radar are substantially cheaper to implement and still retain baseline navigational requirements. Additionally, these sensors do not necessitate specific lighting or visibility conditions to operate effectively, making them viable candidates for a wide variety of environmental situations. Our low cost autonomous ground vehicle project progressed significantly on these objectives during its first year. The team's achievements include a robust data communication system spanning software and hardware needs, integrated peripheral sensors, and a system-wide interface methodology which simplifies the process of adding additional sensors / data acquisition units (such as LIDAR or computer vision).
Campus Venue
Stevens Student Center Lobby
Location
Cedarville, OH
Start Date
4-3-2019 11:00 AM
End Date
4-3-2019 2:00 PM
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Included in
Controls and Control Theory Commons, Navigation, Guidance, Control, and Dynamics Commons, Software Engineering Commons
Low Cost Vehicular Autonomy Using RADAR and GPS
Cedarville, OH
This presentation describes a subset of the systems devised for this year's autonomous golf cart senior design project. Our goal is to explore the possibilities of low cost autonomy using only radar and GPS for environmental sensing and navigation. Although autonomous and semi-autonomous ground vehicles are a relatively new reality, prototypes have been a subject of engineering research for decades, often utilizing an array of sensors and sensor fusion techniques. State of the art autonomous ground vehicle prototypes typically use a combination of LIDAR and other distance sensors (such as radar or sonar) as well as cameras and GPS, sometimes also including functionality for inter-vehicle connectivity. We believe that a low cost solution can be achieved using only radar and GPS. Such a system requires more creativity and robustness in software design, but would maintain the essential capabilities of self-localization, path navigation, and obstacle avoidance. Compared to the specified alternatives, GPS and radar are substantially cheaper to implement and still retain baseline navigational requirements. Additionally, these sensors do not necessitate specific lighting or visibility conditions to operate effectively, making them viable candidates for a wide variety of environmental situations. Our low cost autonomous ground vehicle project progressed significantly on these objectives during its first year. The team's achievements include a robust data communication system spanning software and hardware needs, integrated peripheral sensors, and a system-wide interface methodology which simplifies the process of adding additional sensors / data acquisition units (such as LIDAR or computer vision).
