Skip to main content

Building Safer Autonomous Agents by Leveraging Risky Driving Behavior Knowledge.

Rana, A. and Malhi, A., 2021. Building Safer Autonomous Agents by Leveraging Risky Driving Behavior Knowledge. In: CCCI 2021: International Conference on Communications, Computing, Cybersecurity, and Informatics, 15-17 October 2021, Beijing, China.

Full text available as:

[img]
Preview
PDF
ccci_2021_final_copy.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial.

3MB

DOI: 10.1109/CCCI52664.2021.9583209

Abstract

The highway-env reinforcement learning tasks provides a good abstract testbed for designing driving agents for specific driving scenarios like lane changing, parking or intersections etc. But, generally these driving simulation environments often restrict themselves to safer and precise trajectories. However, we clearly know that real driving tasks often involve very high risk collision prone unexpected situations. Hence, the autonomous model-free driving agents prepared in these environments are blind to certain low probability traffic collision corner cases. In our study we systematically focus on generating adversarial driving collision prone scenarios with dangerous driving behavior and heavy traffic in order to create robust autonomous agents. In our experimentation we train model free learning agents with additional collision prone scenario simulations and compare their efficacy with regular simulation based agents. Ultimately, we create a causal experimentation setup which successfully accounts for the performance improvements across different driving scenarios by utilizing learning from risky driving situations.

Item Type:Conference or Workshop Item (Paper)
Group:Faculty of Science & Technology
ID Code:36354
Deposited By: Symplectic RT2
Deposited On:13 Dec 2021 11:08
Last Modified:14 Mar 2022 14:31

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -