A model to predict steering torque fully end-to-end

Overview

torque_model

The torque model is a spiritual successor to op-smart-torque, which was a project to train a neural network to control a car's steering fully end to end.

The input is the current wheel angle and future wheel angle (among other things), and the net's output is what torque the human was applying at the time to reach that future state smoothly and confidently. This bypasses the need to manually tune a PID, LQR, or INDI controller, while gaining human-like control over the steering wheel.

Needs to be cloned into an openpilot repo to take advantage of its tools.

The problem

As talked about in great detail and with a simple thought experiment in comma.ai's blog post here about end to end lateral planning, the same concept of behavioral cloning not being able to recover from disturbances applies here.

Behavior cloning and lack of perturbations

The way we generate automatically-labeled training data for a model that predicts how to control a steering wheel is rather simple; any time a human is driving we just take the current (t0s) and future (t0.3s) steering wheel angles and then just have the model predict whatever torque the human was applying at t0s to get us there.

This seems to work great, and the validation loss also seems to be really low! However, when you actually try to drive on this model or put it in a simulator, you can quickly see that any small disturbances (like wind, road camber, etc) quickly lead to a feedback loop or just plain inability to correct back to our desired steering angle.

This is due to the automatically-generated training and validation data containing only samples where the current and future (desired during runtime) steering wheel angles are very close together (just a couple degrees), as a symptom of only using data where the future angle is just fractions of a second away.

To fully realize the problem, think about what would happen if you wanted this model to predict what a human would actuate if the steering wheel is centered, but our desired angle is something like 90 degrees. As the model has never seen a difference of angles higher than just a couple of degrees, it either outputs a very small torque value, or just nonsense, as this input is vastly outside of its training distribution.

The solution

The solution talked about in the blog post above is to use a very simple simulator to warp the input video to be offset left or right, and then tell the model what path the human actually drove. A similar approach can also be taken here, where we generate random samples with an arbitrary steering wheel angle error, and then use a simple model of steering wheel torque, like a PF (proportional-feedforward) controller as the output to predict.

For the example above where we start at 0 degrees and want to reach 90 degrees, we can inject samples into the training data where we have that exact situation and then have the output be what a simple PF controller would output. Then during runtime in the car, when the model corrects for this arbitrary high angle error situation, the current and desired steering wheel angles become much closer together, and the model can then use its knowledge of how humans control under these circumstances.

The future

The current model described and implememted here is non-temporal, meaning the model has no knowledge of the past, where the steering wheel was, and inferring where it's heading. While the input data includes the steering angle rate, there's a lot of information missing it could use to improve its predictions, as well as a model bug where including the angle rate during runtime causes very smoothed and laggy predictions (probably due to the generated synthetic samples not taking any angle rate into account).

Ideally the model has some knowledge of the past, however this means we need an accurate simulator to train the model with perturbations added, so it can correct for disturbances in the real world.

Owner
Shane Smiskol
I mess around with self driving cars, neural networks, and real world data!
Shane Smiskol
A toolkit for making real world machine learning and data analysis applications in C++

dlib C++ library Dlib is a modern C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real worl

Davis E. King 11.6k Jan 02, 2023
Coursera Machine Learning - Python code

Coursera Machine Learning This repository contains python implementations of certain exercises from the course by Andrew Ng. For a number of assignmen

Jordi Warmenhoven 859 Dec 10, 2022
Toolss - Automatic installer of hacking tools (ONLY FOR TERMUKS!)

Tools Автоматический установщик хакерских утилит (ТОЛЬКО ДЛЯ ТЕРМУКС!) Оригиналь

14 Jan 05, 2023
Exemplary lightweight and ready-to-deploy machine learning project

Exemplary lightweight and ready-to-deploy machine learning project

snapADDY GmbH 6 Dec 20, 2022
Real-time domain adaptation for semantic segmentation

Advanced-Machine-Learning This repository contains the code for the project Real

Andrea Cavallo 1 Jan 30, 2022
Mesh TensorFlow: Model Parallelism Made Easier

Mesh TensorFlow - Model Parallelism Made Easier Introduction Mesh TensorFlow (mtf) is a language for distributed deep learning, capable of specifying

1.3k Dec 26, 2022
An AutoML survey focusing on practical systems.

This project is a community effort in constructing and maintaining an up-to-date beginner-friendly introduction to AutoML, focusing on practical systems. AutoML is a big field, and continues to grow

AutoGOAL 16 Aug 14, 2022
MLFlow in a Dockercontainer based on Azurite and Postgres

mlflow-azurite-postgres docker This is a MLFLow image which works with a postgres DB and a local Azure Blob Storage Instance (Azurite). This image is

2 May 29, 2022
Python library which makes it possible to dynamically mask/anonymize data using JSON string or python dict rules in a PySpark environment.

pyspark-anonymizer Python library which makes it possible to dynamically mask/anonymize data using JSON string or python dict rules in a PySpark envir

6 Jun 30, 2022
PyCaret is an open-source, low-code machine learning library in Python that automates machine learning workflows.

An open-source, low-code machine learning library in Python 🚀 Version 2.3.5 out now! Check out the release notes here. Official • Docs • Install • Tu

PyCaret 6.7k Jan 08, 2023
Decision tree is the most powerful and popular tool for classification and prediction

Diabetes Prediction Using Decision Tree Introduction Decision tree is the most powerful and popular tool for classification and prediction. A Decision

Arjun U 1 Jan 23, 2022
Implementation of linesearch Optimization Algorithms in Python

Nonlinear Optimization Algorithms During my time as Scientific Assistant at the Karlsruhe Institute of Technology (Germany) I implemented various Opti

Paul 3 Dec 06, 2022
Massively parallel self-organizing maps: accelerate training on multicore CPUs, GPUs, and clusters

Somoclu Somoclu is a massively parallel implementation of self-organizing maps. It exploits multicore CPUs, it is able to rely on MPI for distributing

Peter Wittek 239 Nov 10, 2022
AutoX是一个高效的自动化机器学习工具,它主要针对于表格类型的数据挖掘竞赛。 它的特点包括: 效果出色、简单易用、通用、自动化、灵活。

English | 简体中文 AutoX是什么? AutoX一个高效的自动化机器学习工具,它主要针对于表格类型的数据挖掘竞赛。 它的特点包括: 效果出色: AutoX在多个kaggle数据集上,效果显著优于其他解决方案(见效果对比)。 简单易用: AutoX的接口和sklearn类似,方便上手使用。

4Paradigm 431 Dec 28, 2022
A simple example of ML classification, cross validation, and visualization of feature importances

Simple-Classifier This is a basic example of how to use several different libraries for classification and ensembling, mostly with sklearn. Example as

Rob 2 Aug 25, 2022
Tribuo - A Java machine learning library

Tribuo - A Java prediction library (v4.1) Tribuo is a machine learning library in Java that provides multi-class classification, regression, clusterin

Oracle 1.1k Dec 28, 2022
Formulae is a Python library that implements Wilkinson's formulas for mixed-effects models.

formulae formulae is a Python library that implements Wilkinson's formulas for mixed-effects models. The main difference with other implementations li

34 Dec 21, 2022
Apache (Py)Spark type annotations (stub files).

PySpark Stubs A collection of the Apache Spark stub files. These files were generated by stubgen and manually edited to include accurate type hints. T

Maciej 114 Nov 22, 2022
pandas, scikit-learn, xgboost and seaborn integration

pandas, scikit-learn and xgboost integration.

299 Dec 30, 2022
Automated Time Series Forecasting

AutoTS AutoTS is a time series package for Python designed for rapidly deploying high-accuracy forecasts at scale. There are dozens of forecasting mod

Colin Catlin 652 Jan 03, 2023