AZore's starred repositories
unsignalized-junction-control
FCFS and Planning Based strategy using sumo and TraCI interface
Multi-Agent-Path-Finding
Goal of project is to write programs that will allow multiple agents to find optimal paths from their start location to their goal location such that all agents are able to move simultaneously. Various algorithms will be explored such as Prioritized Planning, Conflict-Based Search (CBS), A* Search. Additionally, a paper that describes Safe Interval Path Planning (SIPP) provided the inspiration for writing of SIPP versions of Prioritized Planning and CBS.
covid19-mobility
Projection of Future Mobility and Fuel Demand using Machine Learning
ME5406_exampleSAPP
Single-Agent Path Planning (SIPP) DRL example
multi_agent_path_planning
Python implementation of a bunch of multi-robot path-planning algorithms.
Reinforcement_Learning_for_Traffic_Light_Control
Apply deep reinforcement learning methods including DQN, DDPG for traffic light control in simulation (discrete environment), to prove the 'Green Wave' phenomenon in intelligent traffic system.
AA-SIPP-m
Algorithm for prioritized multi-agent path finding (MAPF) in grid-worlds. Moves into arbitrary directions are allowed (each agent is allowed to follow any-angle path on the grid). Timeline is continuous, i.e. action durations are not explicitly discretized into timesteps. Different agents' size and moving speed are supported. Planning is carried out in (x, y, \theta) configuration space, i.e. agents' orientation are taken into account.
libMultiRobotPlanning
Library with search algorithms for task and path planning for multi robot/agent systems
SuboptimalSIPP
Implementation of different versions of Safe Interval Path Planning algorithm that can find bounded-suboptimal solutions.
Path-Planning-in-a-Dynamic-Environment
A cool project in which we do path planning in an environment with moving obstacles and large scale fixed obstacles. We use two different representations of the world to handle the fixed and moving obstacles.
Continuous-CBS
Continuous CBS - a modification of conflict based search algorithm, that allows to perform actions (move, wait) of arbitrary duration. Timeline is not discretized, i.e. is continuous.
latex-cookbook
LaTeX论文写作教程 (清华大学出版社)
mapf-visualizer
simple multi-agent pathfinding (MAPF) visualizer for research usage
Traffic-Assignment-Frank-Wolfe-2021
This simple script computes the traffic assignment using the Frank-Wolfe algorithm (FW) or the Method of successive averages (MSA). It can compute the User Equilibrium (UE) assignment or the System Optimal (SO) assignment. The travel time cost function that models the effect of congestion on travel time is pluggable and definable by the users.
Traffic-CONTROL-System---MATLAB
A traffic control system which counts the number of vehicles and detects passage of any emergency vehicle. This will help in dynamic traffic signal system which will lead to an efficient passage of traffic.
Dtalite_NeXTA_package
DTALite-NEXTA Software Release
ga_traffic_light_optimizer_sumo
Evolutionary Algorithm to optimize waiting time in traffic lights.