Safety-aware metrics for object detectors in autonomous driving

03/04/2022
by   Andrea Ceccarelli, et al.
0

We argue that object detectors in the safety critical domain should prioritize detection of objects that are most likely to interfere with the actions of the autonomous actor. Especially, this applies to objects that can impact the actor's safety and reliability. In the context of autonomous driving, we propose new object detection metrics that reward the correct identification of objects that are most likely to interact with the subject vehicle (i.e., the actor), and that may affect its driving decision. To achieve this, we build a criticality model to reward the detection of the objects based on proximity, orientation, and relative velocity with respect to the subject vehicle. Then, we apply our model on the recent autonomous driving dataset nuScenes, and we compare eight different object detectors. Results show that, in several settings, object detectors that perform best according to the nuScenes ranking are not the preferable ones when the focus is shifted on safety and reliability.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/21/2022

Safety Metrics and Losses for Object Detection in Autonomous Driving

State-of-the-art object detectors have been shown effective in many appl...
research
12/14/2021

Revisiting 3D Object Detection From an Egocentric Perspective

3D object detection is a key module for safety-critical robotics applica...
research
09/11/2023

SHIFT3D: Synthesizing Hard Inputs For Tricking 3D Detectors

We present SHIFT3D, a differentiable pipeline for generating 3D shapes t...
research
12/22/2021

Exploring Credibility Scoring Metrics of Perception Systems for Autonomous Driving

Autonomous and semi-autonomous vehicles' perception algorithms can encou...
research
10/19/2021

Watch out for the risky actors: Assessing risk in dynamic environments for safe driving

Driving in a dynamic environment that consists of other actors is inhere...
research
06/20/2023

Deep Learning Accelerator in Loop Reliability Evaluation for Autonomous Driving

The reliability of deep learning accelerators (DLAs) used in autonomous ...
research
05/04/2021

Robustness Enhancement of Object Detection in Advanced Driver Assistance Systems (ADAS)

A unified system integrating a compact object detector and a surrounding...

Please sign up or login with your details

Forgot password? Click here to reset