Online Slip Detection and Friction Coefficient Estimation for Autonomous Racing
arXiv preprint • 2025 • Christopher Oeltjen*, Carson Sobolewski*, Saleh Faghfoorian*, Lorant Domokos,
Giancarlo Vidal, and Ivan Ruchkin
We present a lightweight, real-time method for online slip detection and tire–road friction coefficient
(TRFC) estimation in autonomous racing. The approach relies only on IMU, LiDAR, and control inputs—without
requiring complex tire models or training data—to accurately identify slip events and estimate friction
conditions. Experiments with a 1:10-scale autonomous race car show that the method provides precise and
consistent TRFC estimates across varying surfaces, offering a simple and efficient solution for real-time
slip monitoring in autonomous driving.
Zonal RL-RRT: Integrated RL-RRT path planning with collision probability and zone connectivity
arXiv preprint • 2024 • A.M. Tahmasbi, Saleh Faghfoorian, Saeed Khodaygan, and Aniket Bera
We propose Zonal RL-RRT, a path-planning algorithm that combines kd-tree–based zone partitioning
with reinforcement learning for adaptive high-level decision-making. By segmenting the environment into
connected zones, our method achieves up to 3× faster planning than standard RRT and RRT*, while maintaining
strong success rates across 2D–6D environments. Zonal RL-RRT also outperforms heuristic and learning-based
planners such as BIT*, Informed RRT*, NeuralRRT*, and MPNetSMP, demonstrating its versatility and efficiency
for advanced path planning tasks.
