The problem Project Athena solves

The multiple problems which this project solves are:

• REDUCED ACCIDENTS
  According to the USDOT website: "With 94 percent of fatal vehicle crashes attributable to human error, the potential of autonomous vehicle technologies to reduce deaths and injuries on our roads urges us to action."
  Self-driving cars are projected to reduce traffic deaths by 90 percent, saving 30,000 lives a year

• REDUCED CO2 EMISSIONS
  The reduction in congestion will most likely result in a reduction of CO2 emissions as well.
  Since the software will drive the car, the modern vehicle can now be programmed to reduce emissions to the maximum extent possible. The transition to new-age cars is expected to contribute to a 60% fall in emissions.

• REDUCED TRAFFIC CONGESTION
  Americans currently spend more than 6.9 billion hours a year sitting in traffic, according to the American Society of Civil Engineers. Even decreasing the number of accidents could reduce congestion, because up to 25% of congestion is caused by traffic incidents,
  Under normal circumstances, human drivers naturally create stop-and-go traffic, even in the absence of bottlenecks, lane changes, merges, or other disruptions. This phenomenon is called the "phantom traffic jam." U of Illinois researchers found that by controlling the pace of the autonomous car in the study, they were able to smooth out the traffic flow for all the cars.

• INCREASED LANE CAPACITY
  Research from the State Smart Transportation Initiative (SSTI) shows potential for autonomous vehicles could increase highway capacity by 100 percent and increase expressway travel speeds by more than 20 percent.

• LOWER FUEL CONSUMPTION
  AV technology can improve fuel economy, improving it by 4–10 percent by accelerating and decelerating more smoothly than a human driver. Further improvements could be had by reducing the distance between vehicles and increasing roadway capacity.

Challenges we ran into

The project went pretty smoothly except for a few minor challenges.

1. generating urdf: URDF or Unified Robot Description Format describes how the robot will look like. It consists of links and joints. Having not much prior experience in generating urdfs, it was pretty much trial-and-error based which took up a lot of time.

2. Topic connections: There were a lot of topics that needed to be connected and so the visualization of the connection of topics was tough. This was solved by mapping the topics on a paper. True, in the start we had to continuously look up on the paper but slowly we got a grasp on the topics.