ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst

by   Mayank Bansal, et al.

Our goal is to train a policy for autonomous driving via imitation learning that is robust enough to drive a real vehicle. We find that standard behavior cloning is insufficient for handling complex driving scenarios, even when we leverage a perception system for preprocessing the input and a controller for executing the output on the car: 30 million examples are still not enough. We propose exposing the learner to synthesized data in the form of perturbations to the expert's driving, which creates interesting situations such as collisions and/or going off the road. Rather than purely imitating all data, we augment the imitation loss with additional losses that penalize undesirable events and encourage progress -- the perturbations then provide an important signal for these losses and lead to robustness of the learned model. We show that the ChauffeurNet model can handle complex situations in simulation, and present ablation experiments that emphasize the importance of each of our proposed changes and show that the model is responding to the appropriate causal factors. Finally, we demonstrate the model driving a car in the real world.


page 4

page 9

page 11

page 14

page 17

page 18


Exploring Imitation Learning for Autonomous Driving with Feedback Synthesizer and Differentiable Rasterization

We present a learning-based planner that aims to robustly drive a vehicl...

DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving

Today, there are two major paradigms for vision-based autonomous driving...

Enhanced Behavioral Cloning with Environmental Losses for Self-Driving Vehicles

Learned path planners have attracted research interest due to their abil...

Applying adversarial networks to increase the data efficiency and reliability of Self-Driving Cars

Convolutional Neural Networks (CNNs) are vulnerable to misclassifying im...

Experiments in Autonomous Driving Through Imitation Learning

This report demonstrates several methods used to make a self-driving veh...

Vision-based Autonomous Driving for Unstructured Environments Using Imitation Learning

Unstructured environments are difficult for autonomous driving. This is ...

Exploring the Limitations of Behavior Cloning for Autonomous Driving

Driving requires reacting to a wide variety of complex environment condi...

Code Repositories



view repo


Deep Learning-based Autonomous Driving Toolkit

view repo