Since acquiring our object recognition sensors we’ve been working to calibrate them and start setting them up with ROS, the software framework we’ll be using to link the sensor outputs with our sensor fusion, object detection filtering, SLAM, path planning, and path following algorithms. We’re in the process of testing our PID control with an RC car while building our computational nodes for an EKF and SLAM.
Test output from one of our LiDAR units. We’re currently working on converting the raw hex data from the unit to distance/angle coordinate pairs.
Experimenting with our stereo camera. We’re currently calibrating our device for different lighting conditions and developing our object recognition pipeline to extract distance data more efficiently.
Optimization our path planning algorithms. Upper image is top down view showing a fastest time/distance path through a sample course. Lower image shows the velocity profiles along the path per rough vehicle dynamic calculations. Working to increase algorithm speed and characterize speed profiles more accurately.
Our current top level block diagram plan for the autonomous data pipeline. Sensors will pick up cone and car locations before feeding them into the NVIDIA. Output is desired steering, velocity and acceleration which the ECU will convert to actuation via PID control.
Our stereo camera feeding IMU directional data to a ROS topic. Visualized using rviz within ROS.
At our new member orientation meeting this past Sunday we welcomed several new students to each of our sub teams. Especially as a first year team with lots of work ahead of us, it’s great to have that influx of help!
The team is fully student run with our Faculty Advisor Glenn Bower overseeing our work. Our team generally breaks down into leaders of different subteams that work with a group of students to make each subsystem of the car come together. Team members collaborate with each other, university professors, and industry contacts to develop their design projects. These projects vary between subteams but include powertrain CAD, actuation design (steering, braking, emergency stop system), chassis kinematics and loading, sensor calibration, object recognition, path planning, algorithm optimization, image processing, battery sizing, electrical schematic design, and more.
The team brings together students from different (primarily engineering and business) majors. For example, mechanical engineers are exposed to electrical design, electrical engineers see FEA first hand, business majors learn the engineering design process, and computer science students see how budgets and sponsor outreach are coordinated. This collaborative approach is only successful with all team members learning critical, out-of-the-classroom skills such as teamwork, communication, problem solving, resilience, and how to apply their coursework to real world challenges.
We are excited to have a new wave of motivated students join our team and are looking forward to the work we will accomplish together!
We have been making great progress on the chassis systems for the car. Got all the tires mounted onto the wheels and assembled brake lines and calipers. We also started putting together the master cylinders and bias bar assembly. We are hoping to wrap up the major chassis system within the next week!
The team has been working hard on getting the engine running just perfect. It started out a bit rough in the beginning, but after working through many issues and late nights it is making great power. We are now working on improving the engines emissions, fuel economy, and flex fuel capabilities. This engine will be able to propel the vehicle down the highway for great extended range! With a massive 16 gallon fuel tank, this is a going to a great addition to the car. We are currently working on the vehicles rear subframe and soon will be taking the engine off the dyno and integrating it into the vehicle. From there we can do some some real world engine tuning and perfect the vehicle.
Again, we would like to thank all our sponsors, without you this wouldn’t be possible.