Opportunities and Challenges with Autonomous Racing

In motorsport racing, there is a saying that “If everything seems under control, then you are not going fast enough”. Expert racing drivers have split second reaction times and routinely drive at the limits of control, traction, and agility of the racecar - under high-speed and close proximity situations. Autonomous racing presents unique opportunities and challenges in designing algorithms and hardware that can operate firmly on the limits of perception, planning, and control. Racing has a long and illustrative history of serving as a proving grounds for automotive technology. Similarly, autonomous racing has the potential to serve as the litmus test - but this time - for self-driving software. While a large portion of autonomous vehicle research and development is focused on handling routine driving situations, achieving the safety benefits of autonomous vehicles also requires a focus on driving at the limits of the control of the vehicle.

The main objective of this workshop is to attract the interest of the robotics community on research challenges specific to high-speed autonomous racing. We aim at bringing together experts and researchers from various robotic fields explore the challenges associated with modeling vehicle dynamics at high-speeds, head-to-head multi-agent racing, AI-enabled racing solutions, sensor fusion, overtaking, state-estimation of opponents, racing simulation at scale, perception, localization, and planning. Autonomous racing competitions such as F1/10 Autonomous Racing, Roborace, and Indy Autonomous Challenge are encouraging researchers to think about these problems. We expect that this workshop will become the focal point for bringing together researchers from the growing autonomous racing and robotics communities to foster collaborative and creative solutions.

Demonstrating high-speed autonomous racing can be considered as a grand challenge for self-driving cars, and making progress here has the potential to enable breakthroughs in agile and safe autonomy. To succeed at racing, an autonomous vehicle is required to perform both precise steering and throttle maneuvers in a physically-complex, uncertain environment, and by executing a series of high-frequency decisions. This makes racing an interesting opportunity to explore the physical and algorithmic limits of autonomous driving. Autonomous racing competitions, such as Autonomous Formula SAE, F1/10 autonomous racing, Roborace, and Indy Autonomous Challenge are, both figuratively and literally, getting a lot of traction and becoming proving grounds for testing perception, planning, and control algorithms at high speeds.

We are proposing this workshop to raise awareness of the overall autonomous racing area to the IEEE Robotics and Automation Society community that can take inspiration from the problem space in their own research. This is a good time for such a workshop around this unique and important application space, that will require innovations across core topics in robotics and we believe it will gather a lot of interest.

Topics of Interest

• Modeling vehicle dynamics at high-speeds
• Head-to-head multi-agent racing
• AI-enabled racing solutions
• Overtaking strategies
• State-estimation of opponents
• Racing simulation at scale
• Limits of perception, localization, and planning at high-speeds.
• Adversarial vs Cooperative
• Balancing safe vs aggressive driving policies
• Hardware-software co-design for autonomous racing
• Hardware AI accelerators for perception
• Software stack and architectures for racing

We invite short papers (4-6 pages, including references) for submission to the workshop related to the topics above and the theme of autonomous racing. Position papers, work in progress and novel but not necessarily thoroughly worked out ideas are encouraged. The submissions will be reviewed by the workshop’s program committee and we will accept papers for oral (live) presentations, or a video highlight. A best paper award will be presented in both categories. We are currently exploring the possibility of a journal special issue for the best contributions at the workshop. Each paper will undergo a thorough review process and receive two high quality reviews. Accepted paper will be made available on the website.

The paper should be in PDF format and use the standard IEEE ICRA template.

Please use the following EasyChair link for paper submissions: Submission Link

• Welcome remarks

• Theme 1: Learning based approaches for autonomous racing

• Invited Talk 1
• Invited Talk 2
• Invited Talk 3
• Q/A + Discussion of challenges and gaps
• Contributed Talks [1-4]
• Break

• Theme 2: Exploring the physical limits for autonomous racing

• Invited Talk 4
• Invited Talk 5
• Invited Talk 6
• Q/A + Discussion of challenges and gaps
• Contributed Talks [5-8]
• Break
• Panel discussion
• Demo/Video session