Fast nonlinear risk assessment for autonomous vehicles using learned conditional probabilistic models of agent futures
Name
10514_2021_10000_ReferencePDF.pdf
Size
1.03 MB
Format
Adobe PDF
Checksum (MD5)
c94d9239343c9f73817891b7e30d1f6e
Author(s)
Jasour, Ashkan
Huang, Xin
Wang, Allen
Williams, Brian C.
Date Issued
November 25, 2021
Publisher
Springer US
Citation
Jasour, Ashkan, Huang, Xin, Wang, Allen and Williams, Brian C. 2021. "Fast nonlinear risk assessment for autonomous vehicles using learned conditional probabilistic models of agent futures."
Version
Author's final manuscript
Abstract
Abstract
This paper presents fast non-sampling based methods to assess the risk for trajectories of autonomous vehicles when probabilistic predictions of other agents’ futures are generated by deep neural networks (DNNs). The presented methods address a wide range of representations for uncertain predictions including both Gaussian and non-Gaussian mixture models to predict both agent positions and control inputs conditioned on the scene contexts. We show that the problem of risk assessment when Gaussian mixture models of agent positions are learned can be solved rapidly to arbitrary levels of accuracy with existing numerical methods. To address the problem of risk assessment for non-Gaussian mixture models of agent position, we propose finding upper bounds on risk using nonlinear Chebyshev’s Inequality and sums-of-squares programming; they are both of interest as the former is much faster while the latter can be arbitrarily tight. These approaches only require higher order statistical moments of agent positions to determine upper bounds on risk. To perform risk assessment when models are learned for agent control inputs as opposed to positions, we propagate the moments of uncertain control inputs through the nonlinear motion dynamics to obtain the exact moments of uncertain position over the planning horizon. To this end, we construct deterministic linear dynamical systems that govern the exact time evolution of the moments of uncertain position in the presence of uncertain control inputs. The presented methods are demonstrated on realistic predictions from DNNs trained on the Argoverse and CARLA datasets and are shown to be effective for rapidly assessing the probability of low probability events.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/s10514-021-10000-1
