Development of Deep Learning Based Human-Centered Threat Assessment for Application to Automated Driving Vehicle
Open Access
- 28 December 2019
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 10 (1) , 253
Abstract
This paper describes the development of deep learning based human-centered threat assessment for application to automated driving vehicle. To achieve naturalistic driver model that would feel natural while safe to a human driver, manual driving characteristics are investigated through real-world driving test data. A probabilistic threat assessment with predicted collision time and collision probability is conducted to evaluate driving situations. On the basis of collision risk analysis, two kinds of deep learning have been implemented to reflect human driving characteristics for automated driving. A deep neural network (DNN) and recurrent neural network (RNN) are designed by neural architecture search (NAS), and by learning from the sequential data, respectively. The NAS is used to automatically design the individual driver’s neural network for efficient and effortless design process while ensuring training performance. Sequential trends in the host vehicle’s state can be incorporated through hand-made RNN. It has been shown from human-centered risk assessment simulations that two successfully designed deep learning driver models can provide conservative and progressive driving behavior similar to a manual human driver in both acceleration and deceleration situations by preventing collision.Keywords
Funding Information
- Sookmyung Women's University (1-1903-2022)
This publication has 20 references indexed in Scilit:
- Modulation Format Recognition and OSNR Estimation Using CNN-Based Deep LearningIEEE Photonics Technology Letters, 2017
- A Learning-Based Framework for Velocity Control in Autonomous DrivingIEEE Transactions on Automation Science and Engineering, 2015
- An IMM/EKF Approach for Enhanced Multitarget State Estimation for Application to Integrated Risk Management SystemIEEE Transactions on Vehicular Technology, 2014
- Comparison of Markov Chain Abstraction and Monte Carlo Simulation for the Safety Assessment of Autonomous CarsIEEE Transactions on Intelligent Transportation Systems, 2011
- Using Stochastic Petri Nets for Level-Crossing Collision Risk AssessmentIEEE Transactions on Intelligent Transportation Systems, 2009
- Human driving data-based design of a vehicle adaptive cruise control algorithmVehicle System Dynamics, 2008
- Sensor Fusion for Predicting Vehicles' Path for Collision Avoidance SystemsIEEE Transactions on Intelligent Transportation Systems, 2007
- Experimental Assessment of the RESCUE Collision-Mitigation SystemIEEE Transactions on Vehicular Technology, 2007
- Constructive algorithms for structure learning in feedforward neural networks for regression problemsIEEE Transactions on Neural Networks, 1997
- Structure learning of Bayesian networks by genetic algorithms: a performance analysis of control parametersIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996