Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients

09/27/2021
by   Oliver Scheel, et al.
0

In this work we are the first to present an offline policy gradient method for learning imitative policies for complex urban driving from a large corpus of real-world demonstrations. This is achieved by building a differentiable data-driven simulator on top of perception outputs and high-fidelity HD maps of the area. It allows us to synthesize new driving experiences from existing demonstrations using mid-level representations. Using this simulator we then train a policy network in closed-loop employing policy gradients. We train our proposed method on 100 hours of expert demonstrations on urban roads and show that it learns complex driving policies that generalize well and can perform a variety of driving maneuvers. We demonstrate this in simulation as well as deploy our model to self-driving vehicles in the real-world. Our method outperforms previously demonstrated state-of-the-art for urban driving scenarios – all this without the need for complex state perturbations or collecting additional on-policy data during training. We make code and data publicly available.

READ FULL TEXT

page 2

page 3

page 5

page 6

page 7

page 9

page 10

page 14

research
09/28/2021

SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policies

In this paper we present the first safe system for full control of self-...
research
07/10/2018

CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving

Autonomous urban driving navigation with complex multi-agent dynamics is...
research
06/10/2021

Learning by Watching

When in a new situation or geographical location, human drivers have an ...
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
02/04/2023

CLiNet: Joint Detection of Road Network Centerlines in 2D and 3D

This work introduces a new approach for joint detection of centerlines b...
research
03/22/2022

Learning from All Vehicles

In this paper, we present a system to train driving policies from experi...
research
10/04/2022

Learning from Demonstrations of Critical Driving Behaviours Using Driver's Risk Field

In recent years, imitation learning (IL) has been widely used in industr...

Please sign up or login with your details

Forgot password? Click here to reset