Vehicle Velocity Prediction Using Artificial Neural Networks and Effect of Real-World Signals on Prediction Window by, Tushar D. Gaikwad Committee – Dr. Zachary Asher, Chair Dr. Richard Meyer Dr. Alvis Fong Western Michigan University 1
Agenda Introduction Methodology Results Conclusion and Future Work ➢ Introduction/Background: ➢ Results: o Intelligent Transportation System (ITS) o Assessment methods o Autonomous vehicles o Effect of different signals o Challenges and strategies o Effect of different neural networks o Artificial Intelligence(AI) o Effect on different prediction window o Research gap o Forward prediction for every 10 sec o Literature review ➢ Conclusion and future work o Novel contribution o Summary ➢ Methodology: o Conclusion o Future Work o Approach for velocity prediction o Drive cycle development o Analogy for neural networks Energy Efficient & Autonomous Vehicles Laboratory W ESTERN M ICHIGAN U NIVERSITY 2
Acknowledgement Introduction Methodology Results Conclusion and Future Work ➢ University Faculty: ➢ Graduate Students: o Dr. Zachary Asher o Farhang Motallebiaraghi o Dr. Richard Meyer o Nick Goberville o Dr. Alvis Fong o Nicholas Brown o Dr. Thomas Bradley o Arron Rabinowitz o Dr. Jennifer Hudson o Amol Patil o Dr. Ilya Kolmanovsky o Johan Fanas o Yogesh Jagdale o Parth Kadav o Marsad Zoardar Energy Efficient & Autonomous Vehicles Laboratory W ESTERN M ICHIGAN U NIVERSITY 3
Introduction Introduction Methodology Results Conclusion and Future Work • The shift that we are witnessing toward Intelligent Transportation Systems(ITS) , will be the most disruptive since the Initial days of 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. Energy Efficient & Autonomous Vehicles Laboratory W ESTERN M ICHIGAN U NIVERSITY 4
Autonomous Vehicles Introduction Methodology Results Conclusion and Future Work • 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 Energy Efficient & Autonomous Vehicles Laboratory W ESTERN M ICHIGAN U NIVERSITY 5
Motivation 1: Fuel Economy Introduction Methodology Results Conclusion and Future Work Fuel economy: • Climate change is projected to significantly affect the world • Severe consequences of global warming sooner than expected. • Governments around the world have imposed various Fuel economy (FE) requirements. Strategy: • Optimal Energy Management • 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.] Energy Efficient & Autonomous Vehicles Laboratory W ESTERN M ICHIGAN U NIVERSITY 6
Motivation 1: Safety Introduction Methodology Results Conclusion and Future Work Safety: • Over 37,000 people killed and injured in the US fatal collisions in 2017 • These accidents often originate from driver inattention or impairment • Driver error is responsible for 90+% of crashes in the U.S. 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)] Energy Efficient & Autonomous Vehicles Laboratory W ESTERN M ICHIGAN U NIVERSITY 7
Challenges and Strategies Introduction Methodology Results Conclusion and Future Work How to predict vehicle velocity? Energy Efficient & Autonomous Vehicles Laboratory W ESTERN M ICHIGAN U NIVERSITY 8
Artificial Intelligence(AI) Introduction Methodology Results Conclusion and Future Work • AI has ability to model and extract unseen features and relationships. • Powerful tool to predict the future output of any complex system • Machine learning (ML) is about extracting knowledge from data. • ML is intersection of statistics, AI, and computer science and is also known as predictive analytics or statistical learning. • Deep Learning is the subset of ML which has multilayered neurons Energy Efficient & Autonomous Vehicles Laboratory W ESTERN M ICHIGAN U NIVERSITY 9
Artificial Intelligence Introduction Methodology Results Conclusion and Future Work • Deep learning models are algorithms inspired by the structure and function of the brain called artificial neural networks. • Deep learning consists of hidden layers and multiple neurons. • As we construct larger neural networks and train them with more and more data, their performance continues to increase. Energy Efficient & Autonomous Vehicles Laboratory W ESTERN M ICHIGAN U NIVERSITY 10
Research Gap Introduction Methodology Results Conclusion and Future Work • Projects should address research gap • Are there certain types of perception algorithms that work better than others? • Are there certain sensor inputs that enable high quality predictions? • Which is a better model with sensor/signal inputs for different prediction windows as an output Energy Efficient & Autonomous Vehicles Laboratory W ESTERN M ICHIGAN U NIVERSITY 11
Literature Introduction Methodology Results Conclusion and Future Work Year Researchers/Group Remarks University of Florida 2008- Their study used V2I and GPS signals as inputs into a perception model using traffic model . Later they used NN which was found better University of Wisconsin- 2009 than traffic models . Milwaukee 2014 University of Minnesota They used the historical data of speed, and spacing relative to the leading vehicle and V2I as inputs to traffic model 2014 Lefèvre et al. Prediction using ego vehicle velocity over 1-10 sec was compared with respect to parametric and non-parametric models 2015 Lemieux et al. Deep learning networks is also used to predict ego vehicle velocity and route. 2015 Sun et al Radial Basis Function neural networks performed good vehicle speed performance on four standard driving cycles 2015 Amir Rezaei et.al. Studied prediction for 1, 6, 10 seconds with GPS/GIS used in ANN 2015 Hellström and Jankovic Proposed a model for human driver operating an accelerator pedal and used it for prediction 2017 Colorado State University This study used current and previous vehicle velocity and GPS data input to a shallow NN perception model. 2017 Olabiyi et al. Deep Neural Networks (DNNs) is used for prediction Utilized V2V and V2I communications for future vehicle velocity prediction . They also developed an energy management strategy based 2017 Zhang et al. on vehicle velocity prediction. 2017 David Baker et.al. Studied different prediction window for error distribution with NARX model. They used Vehicle speed and GPS from CAN in Narx model. Beijing Institute of 2018 Demonstrated velocity forecast with aid of historical data in Gaussian function Neural Network Technology, China Liu Kuan et.al. University of Explored a variety of perception models including auto-regressive moving average, shallow NN, long short term memory (LSTM) deep NN, 2019 Michigan markov chain, and conditional linear gaussian models. It was determined that the LSTM deep NN provided the best prediction fidelity Energy Efficient & Autonomous Vehicles Laboratory W ESTERN M ICHIGAN U NIVERSITY 12
Novel Contribution Introduction Methodology Results Conclusion and Future Work • Use of different real-world signals in groups to estimate effect on prediction. • Use of different models consisting DNN and machine learning models to estimate better prediction model. • Understanding effects of different inputs and models on different prediction window. • Use of two assessment methods to understand results. Energy Efficient & Autonomous Vehicles Laboratory W ESTERN M ICHIGAN U NIVERSITY 13
Methodology Introduction Methodology Results Conclusion and Future Work • Vehicle Velocity Prediction Strategy • Drive Input • Deep Learning and Machine Learning Models • Prediction Window • Assessment Energy Efficient & Autonomous Vehicles Laboratory W ESTERN M ICHIGAN U NIVERSITY 14
Methodology Introduction Methodology Results Conclusion and Future Work • Vehicle Velocity Prediction Strategy Energy Efficient & Autonomous Vehicles Laboratory W ESTERN M ICHIGAN U NIVERSITY 15
Drive Cycle Development and Signal Recording Introduction Methodology Results Conclusion and Future Work • 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 Energy Efficient & Autonomous Vehicles Laboratory W ESTERN M ICHIGAN U NIVERSITY 16
Recommend
More recommend
