A Comprehensive Safety Metric to Evaluate Perception in Autonomous Systems
This work addresses safety evaluation for autonomous systems, but it is incremental as it builds on existing metrics by adding more parameters.
The paper tackles the problem of evaluating object perception in autonomous vehicles by proposing a new safety metric that incorporates parameters like velocity, orientation, distance, size, and potential collision damage to provide a single interpretable score, and it is evaluated on real-world and virtual datasets compared to state-of-the-art metrics.
Complete perception of the environment and its correct interpretation is crucial for autonomous vehicles. Object perception is the main component of automotive surround sensing. Various metrics already exist for the evaluation of object perception. However, objects can be of different importance depending on their velocity, orientation, distance, size, or the potential damage that could be caused by a collision due to a missed detection. Thus, these additional parameters have to be considered for safety evaluation. We propose a new safety metric that incorporates all these parameters and returns a single easily interpretable safety assessment score for object perception. This new metric is evaluated with both real world and virtual data sets and compared to state of the art metrics.