TUM - Institute of Automotive Technology's starred repositories
global_racetrajectory_optimization
This repository contains multiple approaches for generating global racetrajectories.
GraphBasedLocalTrajectoryPlanner
Local trajectory planner based on a multilayer graph framework for autonomous race vehicles.
mod_vehicle_dynamics_control
TUM Roborace Team Software Stack - Path tracking control, velocity control, curvature control and state estimation.
racetrack-database
This repository contains center lines (x- and y-coordinates), track widths and race lines for over 20 race tracks (F1 and DTM) all over the world
trajectory_planning_helpers
Useful functions used for path and trajectory planning at TUM/FTM
sim_vehicle_dynamics
TUM Roborace Team Software Stack - Vehicle Simulation
laptime-simulation
This repository contains a quasi-steady-state lap time simulation implemented in Python. It can be used to evaluate the effect of various vehicle parameters on lap time and energy consumption.
Lecture_AI_in_Automotive_Technology
This is the github Repository that belongs to the lecture "Artificial Intelligence in Automotive Technology" from the Institute of Automotive Technology of the Technical University of Munich
race-simulation
This repository contains a race simulation to determine a race strategy for motorsport circuit races. Race strategy in this context means the determination of pit stops.
veh_passenger
TUM Roborace Team Software Stack - Example Vehicle
f110_rrt_star
RRT Star path planning for dynamic obstacle avoidance for the F110 Autonomous Car
velocity_optimization
Optimizes (Maximizes) the velocity profile for a vehicle with respect to physical constraints (e.g., power, force, combined acceleration, ...). Takes into account a variable friction potential between road and tires. Max. power input can be variable (for e.g., energy strategy purpose).
f1-timing-database
SQLite database containing Formula 1 lap and race timing information for the seasons 2014 - 2019
semantic-depth
Fusing Semantic Segmentation and Monocular Depth Estimation for Enabling Autonomous Driving in Roads without Lane Lines
ScenarioArchitect
The Scenario Architect provides a lightweight graphical user interface that allows a straightforward realization and manipulation of concrete driving testing scenarios. Exemplary usecases are the validation of an online verification framework or training of an prediction algorithm.
conditionalstateful
A simple and lightweight event driven state machine library