merge_yield_controller_bagfile_analysys.zip contains 2 files: 2023_11_17_21_34_48_2T3MWRFVXLW056972trustaimerge.bag, the field experiment data of "Interpretable Finite State Machine Controller: A Case Study on Lane Merge Yield Mode", submitted to The 27th IEEE International Conference on Intelligent Transportation Systems (IEEE ITSC 2024). TrustAI_analysis.ipynb, the corresponding analysis code as an example.

Our repeatability evaluation package includes data, python notebooks for recreating our quantitative figures, and a docker image to playback the recorded ROS bag file simulating the ROS message passing network. If you have never used these before, install the proper resources on your machine here:Docker Install: https://docs.docker.com/engine/install/Jupyter Install: https://jupyter.org/installA. File ResourcesYou can find the relevant files at this Zenodo DOI: https://zenodo.org/records/10611821B. Docker ImageThe Docker image provides a ROS integration to automatically perform a realtime repl

merge_yield_controller_bagfile_analysys.zip contains 2 files: 1. 2023_11_17_21_34_48_2T3MWRFVXLW056972trustaimerge.bag, the field experiment data of "Interpretable Finite State Machine Controller: A Case Study on Lane Merge Yield Mode", submitted to The 27th IEEE International Conference on Intelligent Transportation Systems (IEEE ITSC 2024). 2. TrustAI_analysis.ipynb, the corresponding analysis code as an example.

this is a test upload with a de-identified data sample

Setup This project requires the emp-toolkit. Please install the Semihonest two party computation tool. https://github.com/emp-toolkit/emp-sh2pc   Generating results To generate the time results run the following on a terminal from the root directory: $ python compute_times.py   The output should be 3 csv files called y10_u2_results.csv, y50_u10_results.csv, y250_u50_results.csv.

A temp file for testing.

AHG LIDAR Data Visualization for IRL   Dependencies: - numpy - matplotlib   Recreating information: - ut-walrus-output.pickle contains the rosbag information in pickle format and includes obstacle and trajectory data. - The pickle data can be parsed using pickle_parse.py - The point cloud data in binary is present in full_map_binary.npy and can be visualized using plot_grid.py  

Solves the network-wide contraflow lane reversal problem using three different methodologies . The problem is analougus to many Network Design Problems (NDP). The network and demand data is provided as in TNTP data format. To run use: python3 -m experiments.{name of the file without extension} Requirements: gurobipy, networkx, scipy, numpy, pwlf