Life-long Learning and Testing for Automated Vehicles via Adaptive Scenario Sampling as A Continuous Optimization Process

TL;DR

This paper introduces a continuous optimization framework with a bi-level loop for adaptive scenario sampling to efficiently identify critical testing scenarios and evaluate Automated Vehicles' intelligence.

Contribution

It proposes a novel bi-level optimization approach combining learning and sampling to improve coverage and efficiency in AV testing scenarios.

Findings

Faster identification of critical scenarios improves AV evaluation accuracy.

The bi-level loop enhances coverage of the testing space.

Simulation results demonstrate improved efficiency in AV testing.

Abstract

Sampling critical testing scenarios is an essential step in intelligence testing for Automated Vehicles (AVs). However, due to the lack of prior knowledge on the distribution of critical scenarios in sampling space, we can hardly efficiently find the critical scenarios or accurately evaluate the intelligence of AVs. To solve this problem, we formulate the testing as a continuous optimization process which iteratively generates potential critical scenarios and meanwhile evaluates these scenarios. A bi-level loop is proposed for such life-long learning and testing. In the outer loop, we iteratively learn space knowledge by evaluating AV in the already sampled scenarios and then sample new scenarios based on the retained knowledge. Outer loop stops when all generated samples cover the whole space. While to maximize the coverage of the space in each outer loop, we set an inner loop which receives newly generated samples in outer loop and outputs the updated positions of these samples. We assume that points in a small sphere-like subspace can be covered (or represented) by the point in the center of this sphere. Therefore, we can apply a multi-rounds heuristic strategy to move and pack these spheres in space to find the best covering solution. The simulation results show that faster and more accurate evaluation of AVs can be achieved with more critical scenarios.