Towards Safer Self-Driving Through Great PAIN (Physically Adversarial Intelligent Networks)

03/24/2020
by   Piyush Gupta, et al.
3

Automated vehicles' neural networks suffer from overfit, poor generalizability, and untrained edge cases due to limited data availability. Researchers synthesize randomized edge-case scenarios to assist in the training process, though simulation introduces potential for overfit to latent rules and features. Automating worst-case scenario generation could yield informative data for improving self driving. To this end, we introduce a "Physically Adversarial Intelligent Network" (PAIN), wherein self-driving vehicles interact aggressively in the CARLA simulation environment. We train two agents, a protagonist and an adversary, using dueling double deep Q networks (DDDQNs) with prioritized experience replay. The coupled networks alternately seek-to-collide and to avoid collisions such that the "defensive" avoidance algorithm increases the mean-time-to-failure and distance traveled under non-hostile operating conditions. The trained protagonist becomes more resilient to environmental uncertainty and less prone to corner case failures resulting in collisions than the agent trained without an adversary.

READ FULL TEXT

page 4

page 5

research
07/22/2020

Validation Frameworks for Self-Driving Vehicles: A Survey

As a part of the digital transformation, we interact with more and more ...
research
06/29/2018

Ignition: An End-to-End Supervised Model for Training Simulated Self-Driving Vehicles

We introduce Ignition: an end-to-end neural network architecture for tra...
research
03/31/2019

Risk Averse Robust Adversarial Reinforcement Learning

Deep reinforcement learning has recently made significant progress in so...
research
03/16/2021

Building Safer Autonomous Agents by Leveraging Risky Driving Behavior Knowledge

Simulation environments are good for learning different driving tasks li...
research
05/26/2021

SimNet: Learning Reactive Self-driving Simulations from Real-world Observations

In this work, we present a simple end-to-end trainable machine learning ...
research
04/15/2019

Are Self-Driving Cars Secure? Evasion Attacks against Deep Neural Networks for Steering Angle Prediction

Deep Neural Networks (DNNs) have tremendous potential in advancing the v...
research
05/29/2022

Evaluating Automated Driving Planner Robustness against Adversarial Influence

Evaluating the robustness of automated driving planners is a critical an...

Please sign up or login with your details

Forgot password? Click here to reset