Perception Entropy: A Metric for Multiple Sensors Configuration Evaluation and Design
This addresses the multi-sensor configuration problem for autonomous driving, which is crucial for improving perception system performance, and is a novel contribution as the first method to tackle this specific issue.
The paper tackles the problem of evaluating and designing sensor configurations for autonomous vehicles by proposing a novel method based on conditional entropy, introducing a metric called perception entropy that considers both sensor selections and perception algorithm performance, with simulation results demonstrating superior performance.
Sensor configuration, including the sensor selections and their installation locations, serves a crucial role in autonomous driving. A well-designed sensor configuration significantly improves the performance upper bound of the perception system. However, as leveraging multiple sensors is becoming the mainstream setting, existing methods mainly focusing on single-sensor configuration problems are hardly utilized in practice. To tackle these issues, we propose a novel method based on conditional entropy in Bayesian theory to evaluate the sensor configurations containing both cameras and LiDARs. Correspondingly, an evaluation metric, perception entropy, is introduced to measure the difference between two configurations, which considers both the perception algorithm performance and the selections of the sensors. To the best of our knowledge, this is the first method to tackle the multi-sensor configuration problem for autonomous vehicles. The simulation results, extensive comparisons, and analysis all demonstrate the superior performance of our proposed approach.