cs.RONov 5, 2026

Training-Independent Validation of a Learning-Based Controller for Stunt Maneuvers

Authors: Kiruthiga Chandra Shekar, Aliasghar Arab, Jingang Yi

Organizations: General Autonomy, USA · City College of New York, New York University, and General Autonomy, USA · Department of Mechanical and Aerospace Engineering, Rutgers University, Piscataway, NJ, USA

Abstract

Learned controllers for vehicle maneuvers are usually validated under the conditions and objective used to train them, where they appear highly reliable, yet the parameters that change on real roads are often not those the model was trained on. We argue that validation must be independent of training: it should vary physical parameters that training kept fixed and use acceptance criteria absent from the training objective. A learning-based control policy, G-Maneuver, with 90.11% success is tested for stunt-level maneuvers. A looser terminal-heading score ranked the worst setting as the best. Because real stunt tests are safety-critical, a simulation-to-reality-to-simulation (Sim2Real2Sim) loop uses the simulation to select safe zones for real-vehicle trials with 16.9% acceptance. Automotive safety analysis frameworks are used to identify parameters for validation using coverage tests. We demonstrated that the kinematic stunt-driving indicators, namely heading change, sideslip, and speed-normalized yaw rate, match between simulation and the real world, while force and roll indicators do not, which identifies the indicators that can support safe deployment. A video of the experiments is available at https://youtu.be/dN1Oes8pNIo.

Figures & tables

Explore similar work

CardsList
  1. Predictive safety filter enhanced curriculum learning control for efficient vehicle dynamics controller

    Aug 10, 2026Baocong Zhang, Siliang Lu, Chenyang LiSafety-Critical ControlVehicle Dynamics

  2. LyEvO: Lyapunov-Guided Evolutionary Optimization for Safe and Robust Sim-to-Real Policy Learning

    Aug 6, 2026Riccardo Curcio, Hongpeng Cao, Marco CaccamoRobot Policy LearningEvolutionary Optimization

  3. Comfort by Construction: Adaptive, Comfort-Bounded Action Spaces for Learned Driving Policies

    Sep 11, 2026Anna Rothenhäusler, Daniel Jost, Raghu Rajan +4Constrained RLVehicle Dynamics