Quanser is excited to be in American Control Conference again, this year in San Diego. As part of the partnership, we will not only showcase the Quanser solution at the exhibition, but also take our partnership with academia to the new heights by hosting the first-ever Self-Driving Car Student Competition during the conference. Additionally, we are delighted to join forces with MathWorks for a joint special session. If you plan to attend the conference, we invite you to join us for these exciting events.

Meet us at the booth

At ACC 2023, we will showcase three pillars of the Quanser ecosystem in the exhibit area. To highlight our control systems education solutions,we will show examples of our Qube-Servo 3 platform collaborating in an IoT scenario with a digital twin. We will also present an application of our most versatile control systems teaching platform, the Aero 2, and its high-fidelity digital twin. The second demonstration will showcase our robotics solutions featuring a demonstration of a vision application using a physical QArm in coordination with a virtual environment. We will also share a sneak peek of our exciting new mobile robotics platform that will be available later this year. Finally, our autonomous vehicle corner will offer a hands-on experience with our self-driving car and autonomous drone, demonstrating our ground-breaking virtual environment for self-driving car teaching and research. In addition to the many aspects of Autonomy that can be researched, our QCar and QDrone are phenomenal platforms to explore Applied AI and Machine Learning. Built on the latest NVidia embedded systems, there is no better platform to bring AI to life than with Quanser drones and cars.

Be sure to also visit our self-driving car competition to witness the platform in action as students compete to overcome the many challenges of modern autonomous vehicle localization and navigation.


Self-Driving Car Competition

Time: 16:30-18:00 pm, Thursday, June 1st

Location: Sapphire 410 A-B

The first-ever self-driving car student competition at ACC is focused on various aspects of autonomous driving vehicles. Participation in this competition puts students in the seat of a self-driving engineer applying skills related to image processing, machine learning, state estimation, vehicle speed and steering control and behaviour planning.

Students teams are tasked to design a map of the world which outlines features required for self-driving. These include key landmarks such as road signs, traffic lights, construction cones etc. Phase 1 is done leading up to ACC where code has been tested with the virtual environment. In phase 2 student teams will focus on code transfer from a virtual to physical environment and the challenge with this exchange. Post the code transfer student teams will present the designed algorithms to the panel of judges. Teams successful at running their algorithms in the physical QCar will advance to the finals where they will test the adaptability of their code to meet new challenges which emulate the environmental changes in the real world.

All delegates are welcome to stop by the competition on Wednesday and Thursday, and also join us to watch the finals and awards presentation which will take place Thursday afternoon.

Special Session: AI Made Easy using Quanser Hardware and MathWorks Tools

Presenters:      John Pineros (Quanser) and Craig Buhr (Mathworks)

Time:               12:30 – 13:30 Wednesday, May 31, 2023

Location:         Sapphire 411B

Artificial Intelligence is a tool with the potential to tackle complex decision-making problems using the human brain as inspiration. Reinforcement Learning uses a trial-and-error learning approach which enables the computer to make a series of decisions without human intervention and without being explicitly programmed to perform the task. Reinforcement Learning has been applied in many applications, such as industrial automation, aerospace, autonomous driving, and robotics. In this session, Reinforcement Learning will be presented as a practical approach applied to Quanser Qube Servo 2 using the toolsets available from MathWorks. An extension to Deep Reinforcement Learning will be given to demonstrate the wide range of applications where Machine Learning can help accelerate different areas of research.