Loading...
Please wait, while we are loading the content...
Similar Documents
Deep Learning Localization for Self-driving Cars
| Content Provider | Semantic Scholar |
|---|---|
| Author | Bag, Suvam |
| Copyright Year | 2017 |
| Abstract | Smart cars have been present in our lives for a long time but only in the form of science fiction. A number of movies and authors have visualized smart cars capable of traveling to different locations and performing different activities. However this has remained a fairly impossible task, almost a myth until Stanford and then Google actually were able to create the worlds first autonomous cars. The Defense Advanced Research Projects Agency (DARPA) Grand Challenges brought this difficult problem to the forefront and initiated much of the baseline technology that has made today’s limited autonomous driving cars possible. These cars will make our roadways safer, our environment cleaner, our roads less congested, and our lifestyles more efficient. Despite the numerous challenges that remain, scientists generally agree that it is no longer impossible. Besides several other challenges associated with building a smart car, one of the core problems is localization. This project introduces a novel approach for advanced localization performance by applying deep learning in the field of visual odometry. The proposed method will have the ability to assist or replace a purely Global Positioning System based localization approach with a vision based approach. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://scholarworks.rit.edu/cgi/viewcontent.cgi?article=10543&context=theses |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
