DeepAI AI Chat
Log In Sign Up

DR2L: Surfacing Corner Cases to Robustify Autonomous Driving via Domain Randomization Reinforcement Learning

by   Haoyi Niu, et al.

How to explore corner cases as efficiently and thoroughly as possible has long been one of the top concerns in the context of deep reinforcement learning (DeepRL) autonomous driving. Training with simulated data is less costly and dangerous than utilizing real-world data, but the inconsistency of parameter distribution and the incorrect system modeling in simulators always lead to an inevitable Sim2real gap, which probably accounts for the underperformance in novel, anomalous and risky cases that simulators can hardly generate. Domain Randomization(DR) is a methodology that can bridge this gap with little or no real-world data. Consequently, in this research, an adversarial model is put forward to robustify DeepRL-based autonomous vehicles trained in simulation to gradually surfacing harder events, so that the models could readily transfer to the real world.


page 4

page 7


From Simulation to Real World Maneuver Execution using Deep Reinforcement Learning

Deep Reinforcement Learning has proved to be able to solve many control ...

Enhanced Transfer Learning for Autonomous Driving with Systematic Accident Simulation

Simulation data can be utilized to extend real-world driving data in ord...

Cycle-Consistent World Models for Domain Independent Latent Imagination

End-to-end autonomous driving seeks to solve the perception, decision, a...

Sim-To-Real Transfer for Miniature Autonomous Car Racing

Sim-to-real, a term that describes where a model is trained in a simulat...

Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks

Real world data, especially in the domain of robotics, is notoriously co...

Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey

Deep reinforcement learning has recently seen huge success across multip...