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

12/07/2018
by   Mayank Bansal, et al.
10

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.

READ FULL TEXT

page 4

page 9

page 11

page 14

page 17

page 18

research
10/18/2022

Hierarchical Model-Based Imitation Learning for Planning in Autonomous Driving

We demonstrate the first large-scale application of model-based generati...
research
03/02/2021

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...
research
02/04/2022

Enhanced Behavioral Cloning with Environmental Losses for Self-Driving Vehicles

Learned path planners have attracted research interest due to their abil...
research
02/16/2022

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

Convolutional Neural Networks (CNNs) are vulnerable to misclassifying im...
research
05/01/2015

DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving

Today, there are two major paradigms for vision-based autonomous driving...
research
12/16/2022

Distribution-aware Goal Prediction and Conformant Model-based Planning for Safe Autonomous Driving

The feasibility of collecting a large amount of expert demonstrations ha...
research
02/21/2022

Vision-based Autonomous Driving for Unstructured Environments Using Imitation Learning

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

Please sign up or login with your details

Forgot password? Click here to reset