Modeling driver behavior during complex maneuvers

Lin, Theresa; Tseng, Eric; Borrelli, Francesco

doi:10.1109/acc.2013.6580850

Cited by 13 publications

(3 citation statements)

References 15 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This key feature first enables rapid development and testing of fullstack autonomous driving control solutions, in which the designer can focus on driverless technology. It also seamlessly allow for the implementation of learning-based approaches in which the human or autonomous driver can execute arbitrarily complex maneuvers [9]. Moreover, compared to small scale vehicles, the hardware and software developed for this application are readily amenable to technology transfer to urban vehicles, for high speed or emergency maneuvering.…”

Section: Introductionmentioning

confidence: 99%

Towards the Design of Robotic Drivers for Full-Scale Self-Driving Racing Cars

Caporale

Settimi

Massa

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Autonomous vehicles are undergoing a rapid development thanks to advances in perception, planning and control methods and technologies achieved in the last two decades. Moreover, the lowering costs of sensors and computing platforms are attracting industrial entities, empowering the integration and development of innovative solutions for civilian use. Still, the development of autonomous racing cars has been confined mainly to laboratory studies and small to middle scale vehicles. This paper tackles the development of a planning and control framework for an electric full scale autonomous racing car, which is an absolute novelty in the literature, upon which we report our preliminary experiments and perspectives on future work. Our system leverages real time Nonlinear Model Predictive Control to track a pre-planned racing line. We describe the whole control system architecture including the mapping and localization methods employed.

show abstract

Section: Introductionmentioning

confidence: 99%

Towards the Design of Robotic Drivers for Full-Scale Self-Driving Racing Cars

Caporale

Settimi

Massa

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

show abstract

“…In their model, human driving behavior is classified into different modes, and each mode corresponds to a continuous ARX model. By combining this kind of hybrid model with an MPC (model predictive control) controller, the driving behavior can be converted to the control commands for the vehicle [11].…”

Section: Introductionmentioning

confidence: 99%

A Personalized Behavior Learning System for Human-Like Longitudinal Speed Control of Autonomous Vehicles

Lü

Gong

et al. 2019

Sensors

View full text Add to dashboard Cite

As the main component of an autonomous driving system, the motion planner plays an essential role for safe and efficient driving. However, traditional motion planners cannot make full use of the on-board sensing information and lack the ability to efficiently adapt to different driving scenes and behaviors of different drivers. To overcome this limitation, a personalized behavior learning system (PBLS) is proposed in this paper to improve the performance of the traditional motion planner. This system is based on the neural reinforcement learning (NRL) technique, which can learn from human drivers online based on the on-board sensing information and realize human-like longitudinal speed control (LSC) through the learning from demonstration (LFD) paradigm. Under the LFD framework, the desired speed of human drivers can be learned by PBLS and converted to the low-level control commands by a proportion integration differentiation (PID) controller. Experiments using driving simulator and real driving data show that PBLS can adapt to different drivers by reproducing their driving behaviors for LSC in different scenes. Moreover, through a comparative experiment with the traditional adaptive cruise control (ACC) system, the proposed PBLS demonstrates a superior performance in maintaining driving comfort and smoothness.

show abstract

“…A simple resolution to this issue is to turn around a thruster that has been running in reverse over a given period of time, or leave it to the operator to issue a reversal request. A more complex algorithm would make a statistical model of the environmental forces and even the operator, similar to applications in the automotive industry such as [18].…”

Section: Thrust Allocation Logicmentioning

confidence: 99%

Cartesian thrust allocation algorithm with variable direction thrusters, turn rate limits and singularity avoidance

Veksler¹,

Johansen²,

Borrelli

et al. 2014

2014 IEEE Conference on Control Applications (CCA)

Self Cite

View full text Add to dashboard Cite

Abstract-The literature on thrust allocation algorithms that is currently available usually focuses on solving only a few of the many facets of the thrust allocation problem at a time. This paper presents a unified thrust allocation algorithm that solves most of the challenges that are faced by the practitioners in one algorithm. This includes controlling thrusters that can change the direction of the generated thrust slowly and/or reverse the direction of the generated thrust, minimizing the power consumption and wear-and-tear in the thrusters, and handling thruster saturations. When rotable thrusters are present, a functionality to avoid driving the thruster system into singular configurations should normally be included. This functionality requires significant numerical calculations for each iteration of the thrust allocation algorithm. In the presented work those calculations were written in explicit form using a symbolic processor, translated to ANSI C and compiled. This technique was demonstrated to provide acceptable real-time performance. [12]. These developments allow DP operations with better safety, economy, positioning precision and reliability, making it possible for the DP-equipped vessels to perform more complex tasks in deeper waters [13] and on arctic latitudes [14], [15]. DP algorithms are usually divided into several parts, one of which is the thrust allocation (TA) algorithm. The task of the TA algorithm is to receive a command telling it how much force and moment of force (jointly called "generalized force" in this context) the thruster system should produce, and generate commands down to the individual thrusters to I. INTRODUCTION

show abstract

Modeling driver behavior during complex maneuvers

Cited by 13 publications

References 15 publications

Towards the Design of Robotic Drivers for Full-Scale Self-Driving Racing Cars

Towards the Design of Robotic Drivers for Full-Scale Self-Driving Racing Cars

A Personalized Behavior Learning System for Human-Like Longitudinal Speed Control of Autonomous Vehicles

Cartesian thrust allocation algorithm with variable direction thrusters, turn rate limits and singularity avoidance

Contact Info

Product

Resources

About