Neural network vehicle models for high-performance automated driving

@article{Spielberg2019NeuralNV,
  title={Neural network vehicle models for high-performance automated driving},
  author={Nathan A. Spielberg and Matthew Brown and Nitin R. Kapania and John C. Kegelman and J. Christian Gerdes},
  journal={Science Robotics},
  year={2019},
  volume={4}
}
A neural network improved performance over a simple model when implemented in feedforward-feedback control on an experimental vehicle. Automated vehicles navigate through their environment by first planning and subsequently following a safe trajectory. To prove safer than human beings, they must ultimately perform these tasks as well or better than human drivers across a broad range of conditions and in critical situations. We show that a feedforward-feedback control structure incorporating a… 
End-to-End Neural Network for Vehicle Dynamics Modeling
TLDR
A neural network architecture is presented that is able to replace a single-track model for vehicle dynamics modeling and has advantages over a physics-based model in terms of accuracy.
Deep Neural Networks with Koopman Operators for Modeling and Control of Autonomous Vehicles
TLDR
A data-driven vehicle modeling approach based on deep neural networks with an interpretable Koopman operator that exhibits a high modeling precision at a wide operating range and outperforms previously developed methods in terms of modeling performance.
Sampling-Based Nonlinear MPC of Neural Network Dynamics with Application to Autonomous Vehicle Motion Planning
TLDR
A sampling-based non- linear model predictive control approach for control of neural network dynamics that can potentially make effective searches in the control action space for optimal control and also facilitate computation toward overcoming the challenges caused by Neural network dynamics is presented.
A high-performance neural network vehicle dynamics model for trajectory tracking control
Traditional models of vehicle dynamics engineered from physical principles are usually simplified and assumed, resulting in the model cannot accurately reflect the actual dynamic characteristics of
Neural-MPC: Deep Learning Model Predictive Control for Quadrotors and Agile Robotic Platforms
TLDR
Neural-MPC is presented, a framework to efficiently integrate large, complex neural network architectures as dynamics models within a model-predictive control pipeline, demonstrating up to 83% reduction in positional tracking error when compared to state-of-the-art MPC approaches without neural network dynamics.
TOAST: Trajectory Optimization and Simultaneous Tracking using Shared Neural Network Dynamics
TLDR
A novel control scheme that can design an optimal tracking controller using the neural network dynamics of the MPC, making it possible to be applied as a plug-and-play extension for any existing model-based feedforward controller.
Comparing driving behavior of humans and autonomous driving in a professional racing simulator.
TLDR
A study that used a professional racing simulator to compare the behavior of human and autonomous drivers under an aggressive driving scenario and investigated how the features used to predict driving performance in humans can be used in autonomous driving.
A deep learning framework based on Koopman operator for data-driven modeling of vehicle dynamics
TLDR
A deep learning framework relying on an interpretable Koopman operator to build a data-driven predictor of the vehicle dynamics and results in a global model that integrates the dynamics in both longitudinal and lateral directions.
DDK: A Deep Koopman Approach for Dynamics Modeling and Trajectory Tracking of Autonomous Vehicles
TLDR
Simulation results illustrate that the model of the nonlinear vehicle dynamics can be identified effectively via the proposed method and that excellent tracking performance can be obtained with the identified model under DDK-MPC.
Extended model predictive control scheme for smooth path following of autonomous vehicles
This paper presents an extended model predictive control (MPC) scheme for implementing optimal path following of autonomous vehicles, which has multiple constraints and an integrated model of vehicle
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 42 REFERENCES
Neural networks representation of a vehicle model: 'Neuro–Vehicle (NV)'
Recent developments in the area of the artificial neural networks (NN) provide an alternative approach to the modelling of vehicular dynamics, particularly near their operational limits where the
Autonomous Vehicle Control at the Limits of Handling
Racecar drivers have the ability to operate a vehicle at its friction limit without losing control. If autonomous vehicles or driver assistance systems had similar capabilities, many fatal accidents
Predictive Control of Autonomous Ground Vehicles With Obstacle Avoidance on Slippery Roads
Two frameworks based on Model Predictive Control (MPC) for obstacle avoidance with autonomous vehicles are presented. A given trajectory represents the driver intent. An MPC has to safely avoid
Predictive Active Steering Control for Autonomous Vehicle Systems
TLDR
The effectiveness of the proposed MPC formulation is demonstrated by simulation and experimental tests up to 21 m/s on icy roads, and two approaches with different computational complexities are presented.
Knowledge-Based Training of Artificial Neural Networks for Autonomous Robot Driving
TLDR
This chapter presents the neural network architecture and training techniques that allow ALVINN to drive in a variety of circumstances including single-lane paved and unpaved roads, multilane lined and unlined roads, and obstacle-ridden on-and off-road environments, at speeds of up to 55 miles per hour.
Generating locally optimal trajectories for an automatically driven car
The test-drive of an automobile along a given test-course can be modeled by formulating a suitable optimal control problem. However, if the length of the course is very long or if it has a very
Optimization‐based autonomous racing of 1:43 scale RC cars
TLDR
The control performance is investigated experimentally using 1:43 scale RC race cars, driven at speeds of more than 3 m/s and in operating regions with saturated rear tire forces (drifting).
Path Planning for Autonomous Vehicles in Unknown Semi-structured Environments
TLDR
A practical path-planning algorithm for an autonomous vehicle operating in an unknown semi-structured (or unstructured) environment, where obstacles are detected online by the robot’s sensors is described, leading to faster search and final trajectories better suited to the structure of the environment.
Learning quadrotor dynamics using neural network for flight control
TLDR
This paper investigates whether a neural network based dynamics model can be employed to synthesize control for trajectories different than those used for training, and learns a quadrotor dynamics model using only translational and only rotational training trajectories.
Autonomous Automobile Trajectory Tracking for Off-Road Driving: Controller Design, Experimental Validation and Racing
TLDR
This work treats automobile trajectory tracking in a new manner, by considering the orientation of the front wheels - not the vehicle's body - with respect to the desired trajectory, enabling collocated control of the system.
...
1
2
3
4
5
...