Q&A with the capstone winners of 2020 Most Innovative Project

3-minute pitch for Autonomous Vehicle Perception With High-Definition Radars

The Fung Institute’s Most Innovative Project Award is awarded to the Capstone team that most effectively demonstrates the relevance of the problem they are trying to solve, the originality of their proposed solution, and the potential of their project’s impact. In this year’s online showcase, two winners were selected by MEng alumni, based on the teams’ video or print project pitch submissions. The recognition for best video pitch goes to the Developing An Affordable Alternative For Autonomous Vehicle Localization Using High-Definition Radar Images capstone team, who collaborated with the company Zendar.

About Zendar

Based in San Francisco, CA, Zendar works on building the highest resolution automotive radar in the world. The product utilizes the resolution of LiDAR along with the benefits of radar, such as long-range and all-weather operation, to make autonomous driving safe and accessible for everyone.

Project Overview

Localization of autonomous vehicles on the road currently relies on LiDAR (laser) and camera sensors which simultaneously map the environment around the car. The team proposed an algorithm to achieve an equivalent performance with a technology that is cheaper, easier to install, and less susceptible to adverse weather conditions such as rain, fog, and snow: high-definition radar images. This solution, based on the hardware and software suite of Zendar, breaks the traditional reliance on costly LiDARs.

We had a chance to speak with the capstone team members Bowen Wang (ME), Pierre-Louis Blossier (ME), Johan Gerfaux (IEOR), and David Scanlan (IEOR), about their experience.

Four business casual dressed young men pose for a group photo in front of a pink wall.
Bowen Wang, Pierre-Louis Blossier, Johan Gerfaux, and David Scanlan

How do you define the scope of the capstone project?

Our industry partner, Zendar, proposed two key goals: mapping the environment around the car and the localization of the car. We wanted to demonstrate how we can leverage raw data, preprocessing, and mapping to prototype a high-precision technology that is more cost-efficient than the currently used LiDAR sensors.

What were some of the most significant technical and teaming challenges in the project and how did you face them?

We came in with different levels and experiences in software, so one big challenge we faced was effectively matching individuals’ skill sets with responsibilities over the many parts of the project. Furthermore, we had some difficulties with understanding the given product, but we were able to develop a relationship with our industry partner to flesh out these difficulties and smoothly transition into completing the tasks at hand, and eventually meeting our goals.

“We came in with different levels and experiences in software, so one big challenge we faced was effectively matching individuals’ skill sets with responsibilities over the many parts of the project.”

How has this capstone project been different than any of the other technical projects you may have done in the past?

This project was definitely more complex than anything we’ve worked on in the past! Working with industry added this professional aspect; presenting deliverables and frequent communication with our advisor made us feel like this project was a true investment. There was a mutual trust between us and Zendar, and our results added value to their company.

If there is one thing we’ll remember from our MEng experience, it is definitely this capstone project!

Edited by Shivani Lamba

Connect with the team: Bowen Wang (ME), Pierre-Louis Blossier (ME), Johan Gerfaux (IEOR), and David Scanlan (IEOR)

--

--

Berkeley Master of Engineering
Berkeley Master of Engineering

Master of Engineering at UC Berkeley with a focus on leadership. Learn more about the program through our publication.