Skip to content

Reactive modelling of the environment behavior for robotic systems with falsification and SVM

Notifications You must be signed in to change notification settings

chenyx09/Reactive-modelling

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Code for the paper "Counter-example Guided Learning of Bounds on Environment Behavior"

Platform: Matlab
Prerequisite: Cplex, S-Taliro, Gurobi, qpOASES

To reproduce the result for the two robot problem, run 'robot_falsification'
To reproduce the result for the lane change problem, run 'LC_falsification'

Index of important functions:

params.m:                                     Declaring parameters
SVM_reactive_bound.m:                         Main SVM function that generates the classifier
extract_reactive_bound_2region_soft_bdry.m:   Generate reactive bound function from the classifier
BlackBoxMPCLaneChange.m:                      Lane change simulator
two_robot_sim.m:                              Simulation of the two robot example to generate positive data
two_robot_staliro_shortest_time_reactive.m:   S-Taliro file to generate negative data for the two robot example
lane_change_staliro.m:                        S-Taliro file to generate negative data for the lane change example

About

Reactive modelling of the environment behavior for robotic systems with falsification and SVM

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published