Physical AI Detects EV Loss-Of-Control in Real-Time
Researchers led by Professor Kanghyun Nam at DGIST, with Shanghai Jiao Tong University and the University of Tokyo, publish a physical AI system that enables electric vehicles to detect loss of control in real time by combining tire-force physics models with AI regression. Tests report stable accuracy across varying road surfaces, speeds, and aggressive cornering, and the team says the approach could augment ADAS and autonomous driving stacks.
Key Points
- 1Combine physical tire-force models with AI regression to estimate unmeasured motion states like sideslip angle.
- 2Improve robustness where conventional estimators fail under nonlinear tire behavior, varying surfaces, and aggressive maneuvers.
- 3Enable real-time loss-of-control detection for EVs, augmenting ADAS/autonomy and enhancing safety in edge cases.
Scoring Rationale
Solid university-backed research with practical testing, but it remains incremental method development focused on automotive segment rather than broad paradigm shift.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
