2024/10/11 by Parashar, Anjali, Kunal Garg, Garg, Kunal +4
Computer Science · #FOS: Computer and information sciences #Robotics (cs.RO) #Software Reliability and Analysis Research #Software Testing and Debugging Techniques #VLSI and Analog Circuit Testing
paper · pdf · doi:10.48550/arxiv.2410.09249
openalex publication_date 2024/10/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Prediction of failures in real-world robotic systems either requires accurate model information or extensive testing. Partial knowledge of the system model makes simulation-based failure prediction unreliable. Moreover, obtaining such demonstrations is expensive, and could potentially be risky for the robotic system to repeatedly fail during data collection. This work presents a novel three-step methodology for discovering failures that occur in the true system by using a combination of a limited number of demonstrations from the true system and the failure information processed through sampling-based testing of a model dynamical system. Given a limited budget N of demonstrations from true system and a model dynamics (with potentially large modeling errors), the proposed methodology comprises of a) exhaustive simulations for discovering algorithmic failures using the model dynamics; b) design of initial N1 demonstrations of the true system using Bayesian inference to learn a Gaussian process regression (GPR)-based failure predictor; and c) iterative N - N1 demonstrations of the true system for updating the failure predictor. To illustrate the efficacy of the proposed methodology, we consider: a) the failure discovery for the task of pushing a T block to a fixed target region with UR3E collaborative robot arm using a diffusion policy; and b) the failure discovery for an F1-Tenth racing car tracking a given raceline under an LQR control policy.