Vehicle Velocity Prediction Using Artificial Neural Networks and - - PowerPoint PPT Presentation

▶
vehicle velocity prediction using artificial neural
SMART_READER_LITE
LIVE PREVIEW

Vehicle Velocity Prediction Using Artificial Neural Networks and - - PowerPoint PPT Presentation

Jul 29, 2023 905 likes •1.19k views

21-23 20 Vehicle Velocity Prediction Using Artificial Neural Networks and Effect of Real-World Signals on Prediction Window Tushar D. Gaikwad , Zachary D. Asher, Aaron Rabinowitz, Farhang Motallebiaraghi, Thomas Bradley, Alvis Fong, Rick Meyer

slide-1
SLIDE 1

21-23 20

Vehicle Velocity Prediction Using Artificial Neural Networks and Effect of Real-World Signals on Prediction Window

Tushar D. Gaikwad , Zachary D. Asher, Aaron Rabinowitz, Farhang Motallebiaraghi, Thomas Bradley, Alvis Fong, Rick Meyer Western Michigan University, Colorado State University

slide-2
SLIDE 2

2020-01-0729 2

Special Thanks

  • Dr. Thomas H. Bradley
slide-3
SLIDE 3

2020-01-0729 3

Special Thanks

This material is based upon work supported by the U.S. Department of Energy’s Office of Energy Efficiency and Renewable Energy (EERE). The specific organization overseeing this report is the Vehicle Technologies Office under award number DE-EE0008468.

slide-4
SLIDE 4

Conclusions Results Methods Introduction

Agenda:

฀ Introduction/Background ฀ Drive Cycle Development ฀ LSTM ฀ Assessment methods ฀ Effect of different signals ฀ Summary ฀ Results ฀ Future Goal

2020-01-0729 4

slide-5
SLIDE 5

Conclusions Results Methods Introduction Intelligent Transportation Systems(ITS)

  • The shift that we are witnessing toward

Intelligent Transportation Systems(ITS), will be the most disruptive since the Initial days

  • f automobiles.
  • It has potential to completely transform the

movement of people and goods, enabling safer and smarter transportation.

  • ITS consists of several technologies such as

Advanced Driver Assistance System(ADAS), Automated Driving Functions(ADF), Vehicle to Vehicle(V2V) and Vehicle to Infrastructure(V2I) communication.

2020-01-0729 5

slide-6
SLIDE 6

Conclusions Results Methods Introduction

Use of Autonomous Vehicles

  • Autonomous vehicle technology is the key

to improve driver and passenger safety.

  • Control strategies and AI software that

powers it are some of the most critical components.

  • Increase

in computational capabilities, enable to train complex and deep neural networks

2020-01-0729 6

slide-7
SLIDE 7

Conclusions Results Methods Introduction

Motivation for velocity prediction

Fuel economy strategy:

Optimal Energy Management Systems Ego Vehicle velocity Predictions determines the constraints of the energy optimization problem to increase fuel economy

[Gaikwad, Tushar D., Zachary D. Asher, Kuan Liu, Mike Huang, and Ilya

  • Kolmanovsky. Vehicle Velocity Prediction and Energy Management

Strategy Part 2: Integration of Machine Learning Vehicle Velocity Prediction with Optimal Energy Management to Improve Fuel Economy.

  • No. 2019-01-1212. SAE Technical Paper, 2019.]

Safety improvement strategy:

Collision Risk Estimator Ego Vehicle velocity Predictions can be integrated into collision risk estimators thereby helping drivers avoid accidents.

[Phillips, Derek J., Real-time Prediction of Automotive Collision Risk from Monocular Video (2019)]

2020-01-0729 7

slide-8
SLIDE 8

Conclusions Results Methods Introduction

2020-01-0729 8

Novel Contribution

  • Use of different real-world signals in groups to estimate effect on prediction.
  • Understanding effects of different inputs in LSTM for varied prediction window.
  • Use of two assessment methods to understand results.
slide-9
SLIDE 9

Conclusions Results Methods Introduction

2020-01-0729 9

Vehicle Velocity Prediction Strategy

  • Drive Input
  • Deep Learning and Machine Learning Models
  • Prediction Window
  • Assessment

LSTM

Model

slide-10
SLIDE 10

Conclusions Results Methods Introduction

2020-01-0729 10

Drive Cycle Development and Signal Recording

  • Collected in August 2019 at Fort Collins, Colorado.
  • Dataset from repeated drives collected along a fixed route by the same driver.
  • Route Details

1. Parking Lot 2. West on Mulberry until Shields 3. South on Shields until Prospect 4. East on Prospect until College 5. North on College until Mulberry 6. West on Mulberry until Parking Lot 7. Parking Lot

slide-11
SLIDE 11

Conclusions Results Methods Introduction

2020-01-0729 11

Data Collection

  • Autonomous

driver assistance system (ADAS) data for the vehicle forward cone from smart radar.

  • Vehicle to infrastructure (V2I) data in the form
  • f traffic signal information and segment

travel times.

  • EGO Vehicle Parameters using Freematics

logger.

  • Sr. No.

Parameters 1 Time 2 Latitude 3 Longitude 4 Distance 5 Brake Pedal Position 6 Transmission Gear 7 Engine Speed 8 Max Torque 9 Min Torque 10 Engine Torque 11 Turn Signal 12 Vehicle Speed 13 Acceleration Longitude 14 Acceleration Latitude 15 Yaw Rate 16 Altitude 17 SPaT 18 Segment Speed 19 ADAS

slide-12
SLIDE 12

Conclusions Results Methods Introduction

2020-01-0729 12

Recorded Signals Velocity on the Longitude vs Latitude vs time Radar Object Detections immediately in front.

slide-13
SLIDE 13

Conclusions Results Methods Introduction

2020-01-0729 13

Recorded Signals Velocity vs Time for one drive instance. Velocity on the map Terrain

slide-14
SLIDE 14

Conclusions Results Methods Introduction

2020-01-0729 14

LSTM(Long Short-term memory)

  • Special type of Recurrent Neural Network

(RNN)

  • A typical LSTM unit is composed of a cell, an

input gate, an output gate, and a forget gate

  • The cell remembers values and the three

gates regulate the flow of information into and out of the cell.

  • Forget Gate: Decides what information to

discard from the cell.

  • Input Gate: Decides which values from the

input to update the memory state.

  • Output Gate: Decides what to output based
  • n input and the memory of the cell
slide-15
SLIDE 15

Conclusions Results Methods Introduction

2019-01-1212 15

Assessment methods

slide-16
SLIDE 16

Conclusions Results Methods Introduction

2019-01-1212 16

Assessment methods

  • MAE = 1.6763 m/s
  • Time Shift = 0 Seconds

Increase in MAE

  • MAE = 1.6763 m/s
  • Time Shift = 10 Seconds

Increase in MAE and Time shift

slide-17
SLIDE 17

Conclusions Results Methods Introduction

2019-01-1212 17

Assessment methods

  • MAE = 4.3901 m/s
  • Time Shift = 10 Seconds
slide-18
SLIDE 18

Conclusions Results Methods Introduction

2019-01-1212 18

Effect of Different Signals on Prediction

Data Group A Current Velocity GPS Data Group B Current Velocity GPS Previous 5 Seconds EGO and Engine Parameters Data Group C Current Velocity GPS Previous 5 Seconds EGO and Engine Parameters Radar Data Data Group D Current Velocity GPS Previous 5 Seconds EGO and Engine Parameters SPat Data Group E Current Velocity GPS Previous 5 Seconds EGO and Engine Parameters SPat Segment Speed

Group A Group B Group B Group D

Data Group F Current Velocity GPS Previous 5 Seconds EGO and Engine Parameters SPat Segment Speed Radar Data Group G Current Velocity GPS Previous 5 Seconds EGO and Engine Parameters Segment Speed

Group E Group B

slide-19
SLIDE 19

Conclusions Results Methods Introduction

2019-01-1212 19

Effect of Different Signals on Prediction

slide-20
SLIDE 20

Conclusions Results Methods Introduction

2019-01-1212 20

Effect of Different Signals on Prediction

slide-21
SLIDE 21

Conclusions Results Methods Introduction

2019-01-1212 21

Effect of Different Signals on Prediction

Prediction with Group D Prediction with Group E

slide-22
SLIDE 22

Conclusions Results Methods Introduction

2019-01-1212 22

Effect of Different Signals on Prediction Window

slide-23
SLIDE 23

Conclusions Results Methods Introduction

2019-01-1212 23

Forward Prediction Window Prediction for every second shown for Every 10 second interval

slide-24
SLIDE 24

Conclusions Results Methods Introduction

2019-01-1212 24

Forward Prediction Window Prediction for every second shown for Every 10 second interval

slide-25
SLIDE 25

Conclusions Results Methods Introduction

2019-01-1212 25

Group D LSTM 10 second prediction MAE and Time Shift MAE = 1.78 m/s Time Shift =2.35 LSTM

Model

Summary

  • Autonomous vehicles is the key to move towards ITS
  • It uses AI to power different strategies to enable safer and smarter transportation.
  • Velocity prediction is very important to develop those strategies.
slide-26
SLIDE 26

Conclusions Results Methods Introduction

  • For Evaluating Results its better to use MAE along with time shift.
  • Dataset with SPaT data performs better in terms of getting accurate results
  • LSTM performs the best in terms of MAE, which is 1.78m/s, at prediction window of 10

seconds.

  • Increase in Prediction Window Increases MAE and Time shift in case of ANN.

2019-01-1212 26

Conclusion

  • Study with More drive cycle on different types of roads
  • Inclusion of V2V data and Camera data
  • More V2I data.
  • Implementation of trained model on NVIDIA drive PX2 to test prediction accuracy on the road.

Future Work

slide-27
SLIDE 27

2019-01-1212 27

Thank you

Name Tushar D. Gaikwad , Zachary D. Asher, Aaron Rabinowitz, Farhang Motallebiaraghi, Thomas Bradley, Alvis Fong, Rick Meyer University/Work Western Michigan University, Colorado State University Address 4601 Campus Dr, Kalamazoo, MI 49008 Email tushar.d.gaikwad@wmich.edu / zach.asher@wmich.edu