H/t: IEEE Spectrum
Autonomous drifting in a Toyota Supra looks like fun, and this video made by researchers Franck Djeumou, Jonathan Y.M. Goh, Ufuk Topcu, and Avinash Balachandran from University of Texas, proves it. This feat was made possible using just 3 minutes of data learned through tire models since near the limits of adhesion, the forces they generate are nonlinear and intricately coupled.
The researchers discovered that the novel family of tire force models based on neural ordinary differential equations and a neural-ExpTanh parameterization they proposed was sufficient to achieve high-performance autonomous drifting on various trajectories including a figure 8 at speeds of up to 45 mph.
- Authentically detailed LEGO replica of the legendary Toyota GR Supra, plus racing driver minifigure
- With its wider 8-stud chassis, the collectible model car toy has room for 2 minifigures and lots of authentic detailing
- Driver minifigure has a Toyota racing suit, safety helmet and wrench, providing plenty of inspiration for imaginative, high-speed play
Comparisons with the benchmark model show a 4x improvement in tracking performance, smoother control inputs, and faster and more consistent computation time,” said the researchers.
