Predictively Coordinated Vehicle Acceleration and Lane Selection Using Mixed Integer Programming

2018 ◽  
Author(s):  
R. Austin Dollar ◽  
Ardalan Vahidi
Keyword(s):  
Autonomous Vehicle ◽  
Mixed Integer ◽  
Quadratic Program ◽  
Vehicle To Vehicle ◽  
Trip Time ◽  
Induced Travel ◽  
Vehicle Acceleration ◽  
Vehicle Technology ◽  
Rule Based Approach ◽  
Integer Quadratic Program

Autonomous vehicle technology provides the means to optimize motion planning beyond human capacity. In particular, the problem of navigating multi-lane traffic optimally for trip time, energy efficiency, and collision avoidance presents challenges beyond those of single-lane roadways. For example, the host vehicle must simultaneously track multiple obstacles, the drivable region is non-convex, and automated vehicles must obey social expectations. Furthermore, reactive decision-making may result in becoming stuck in an undesirable traffic position. This paper presents a fundamental approach to these problems using model predictive control with a mixed integer quadratic program at its core. Lateral and longitudinal movements are coordinated to avoid collisions, track a velocity and lane, and minimize acceleration. Vehicle-to-vehicle connectivity provides a preview of surrounding vehicles’ motion. Simulation results show a 79% reduction in congestion-induced travel time and an 80% decrease in congestion-induced fuel consumption compared to a rule-based approach.

FPGA Based Vehicle to Vehicle Communication in Spartan 3E

2020 ◽  
Vol 8 ◽  
pp. 14-21
Author(s):  
Surya Man Koju ◽  
Nikil Thapa
Keyword(s):  
Signal Processing ◽  
Autonomous Vehicle ◽  
Processing Unit ◽  
Warning Signals ◽  
Vehicle Communication ◽  
Digital Vlsi ◽  
Vehicle To Vehicle ◽  
Vehicle Operation ◽  
Vehicle Technology ◽  
The Voice

This paper presents economic and reconfigurable RF based wireless communication at 2.4 GHz between two vehicles. It implements digital VLSI using two Spartan 3E FPGAs, where one vehicle receives the information of another vehicle and shares its own information to another vehicle. The information includes vehicle’s speed, location, heading and its operation, such as braking status and turning status. It implements autonomous vehicle technology. In this work, FPGA is used as central signal processing unit which is interfaced with two microcontrollers (ATmega328P). Microcontroller-1 is interfaced with compass module, GPS module, DF Player mini and nRF24L01 module. This microcontroller determines the relative position and the relative heading as seen from one vehicle to another. Microcontroller-2 is used to measure the speed of vehicle digitally. The resulting data from these microcontrollers are transmitted separately and serially through UART interface to FPGA. At FPGA, different signal processing such as speed comparison, turn comparison, distance range measurement and vehicle operation processing, are carried out to generate the voice announcement command, warning signals, event signals, and such outputs are utilized to warn drivers about potential accidents and prevent crashes before event happens.

scholarly journals Application of mixed integer quadratic program to shortest vector problems

JSIAM Letters ◽  
2017 ◽  
Vol 9 (0) ◽  
pp. 65-68
Author(s):  
Keiji Kimura ◽  
Hayato Waki ◽  
Masaya Yasuda
Keyword(s):  
Mixed Integer ◽  
Quadratic Program ◽  
Integer Quadratic Program

Domiciling Truck Drivers More Strategically in a Transportation Network

2018 ◽  
pp. 846-865
Author(s):  
Kerry Melton ◽  
Sandeep Parepally
Keyword(s):  
Numerical Experiment ◽  
Transportation Network ◽  
Truck Drivers ◽  
Mixed Integer ◽  
Quadratic Program ◽  
Routing Problem ◽  
New Approach ◽  
Driving Time ◽  
Highway Transportation ◽  
Integer Quadratic Program

The authors propose a method to better domicile truck drivers in a relay-point highway transportation network to obtain better solutions for the truck driver domiciling and sourcing problem. The authors exploit characteristics of the truckload driver routing problem over a transportation network and introduce a new approach to domicile, source, and route truck drivers while more inclusively considering performance and cost measures related to the driver, transportation carrier, and customer. Driver domicile and relay-point locations are exploited to balance driver pay and recruiting costs and driving time. A mixed integer quadratic program will determine where driver domiciles are located to base drivers, source drivers, route drivers, etc. while considering key costs related to transporting truckload freight over long distances. A method to improve driver domicile locations is introduced to enhance driving jobs and driver sourcing, but not at the expense of the transportation carrier and customer. A numerical experiment will be conducted.

scholarly journals Agent Based Resilient Transportation Infrastructure With Surrogate Adaptive Networks

2020 ◽  
Author(s):  
Andre A. Apostol ◽  
Cameron J. Turner
Keyword(s):  
Decision Making ◽  
Traffic Flow ◽  
Intelligent Agents ◽  
Autonomous Vehicle ◽  
Transportation Infrastructure ◽  
Adaptive Networks ◽  
Agent Based ◽  
Vehicle To Vehicle ◽  
Vehicle To Infrastructure ◽  
Vehicle Technology

Abstract Connected autonomous intelligent agents (AIA) can improve intersection performance and resilience for the transportation infrastructure. An agent is an autonomous decision maker whose decision making is determined internally but may be altered by interactions with the environment or with other agents. Implementing agent-based modeling techniques to advance communication for more appropriate decision making can benefit autonomous vehicle technology. This research examines vehicle to vehicle (V2V), vehicle to infrastructure (V2I), and infrastructure to infrastructure (I2I) communication strategies that use gathered data to ensure these agents make appropriate decisions under operational circumstances. These vehicles and signals are modeled to adapt to the common traffic flow of the intersection to ultimately find an traffic flow that will minimizes average vehicle transit time to improve intersection efficiency. By considering each light and vehicle as an agent and providing for communication between agents, additional decision-making data can be transmitted. Improving agent based I2I communication and decision making will provide performance benefits to traffic flow capacities.

Mixed-Integer Quadratic Program for Predictive Control of a Grid-Connected Power Converter

2019 ◽  
Author(s):  
Rodrigo Morfin-Magana ◽  
Jesus Rico-Melgoza ◽  
Fernando Ornelas-Tellez ◽  
Francesco Vasca ◽  
David Cortes-Vega
Keyword(s):  
Predictive Control ◽  
Power Converter ◽  
Mixed Integer ◽  
Quadratic Program ◽  
Integer Quadratic Program

Domiciling Truck Drivers More Strategically in a Transportation Network

2014 ◽  
Vol 2 (1) ◽  
pp. 41-56
Author(s):  
Kerry Melton ◽  
Sandeep Parepally
Keyword(s):  
Numerical Experiment ◽  
Transportation Network ◽  
Truck Drivers ◽  
Mixed Integer ◽  
Quadratic Program ◽  
Routing Problem ◽  
New Approach ◽  
Driving Time ◽  
Highway Transportation ◽  
Integer Quadratic Program

The authors propose a method to better domicile truck drivers in a relay-point highway transportation network to obtain better solutions for the truck driver domiciling and sourcing problem. The authors exploit characteristics of the truckload driver routing problem over a transportation network and introduce a new approach to domicile, source, and route truck drivers while more inclusively considering performance and cost measures related to the driver, transportation carrier, and customer. Driver domicile and relay-point locations are exploited to balance driver pay and recruiting costs and driving time. A mixed integer quadratic program will determine where driver domiciles are located to base drivers, source drivers, route drivers, etc. while considering key costs related to transporting truckload freight over long distances. A method to improve driver domicile locations is introduced to enhance driving jobs and driver sourcing, but not at the expense of the transportation carrier and customer. A numerical experiment will be conducted.

scholarly journals Integer Programming for Learning Directed Acyclic Graphs from Continuous Data

2020 ◽  
pp. ijoo.2019.0040
Author(s):  
Hasan Manzour ◽  
Simge Küçükyavuz ◽  
Hao-Hsiang Wu ◽  
Ali Shojaie
Keyword(s):  
Programming Model ◽  
Score Function ◽  
Directed Acyclic Graphs ◽  
Mixed Integer ◽  
Computational Time ◽  
Quadratic Program ◽  
Acyclic Graphs ◽  
Continuous Relaxation ◽  
Integer Quadratic Program ◽  
Better Than

Learning directed acyclic graphs (DAGs) from data is a challenging task both in theory and in practice, because the number of possible DAGs scales superexponentially with the number of nodes. In this paper, we study the problem of learning an optimal DAG from continuous observational data. We cast this problem in the form of a mathematical programming model that can naturally incorporate a superstructure to reduce the set of possible candidate DAGs. We use a negative log-likelihood score function with both l0 and l1 penalties and propose a new mixed-integer quadratic program, referred to as a layered network (LN) formulation. The LN formulation is a compact model that enjoys as tight an optimal continuous relaxation value as the stronger but larger formulations under a mild condition. Computational results indicate that the proposed formulation outperforms existing mathematical formulations and scales better than available algorithms that can solve the same problem with only l1 regularization. In particular, the LN formulation clearly outperforms existing methods in terms of computational time needed to find an optimal DAG in the presence of a sparse superstructure.

Sign in / Sign up

Export Citation Format

Share Document