Open Geonhee-LEE opened 2 years ago
https://github.com/AtsushiSakai/PythonRobotics (matplotlib(시각화), Python 3.9.x, NumPy, SciPy, pandas, cvxpy)
https://github.com/atb033/multi_agent_path_planning (matplotlib(시각화), numpy.lp(VO), scipy.optimize(NMPC))
Python implementation of a bunch of multi-robot path-planning algorithms.
Centralized Solutions : it is the responsibility of the central planner to provide a plan to the robots.
Prioritized Safe-Interval Path Planning (SIPP)
: SIPP is a local planner, using which, a collision-free plan can be generated, after considering the static and dynamic obstacles in the environment. In the case of multi-agent path planning, the other agents in the environment are considered as dynamic obstacles.Conflict Based Search(CBS)
: Conclict-Based Search (CBS), is a multi-agent global path planner.Decentralized solutions : it is the responsibility of each robot to find a feasible path. Each robot sees other robots as dynamic obstacles, and tries to compute a control velocity which would avoid collisions with these dynamic obstacles.
Velocity obstacles
: reciprocal velocity obstacle for collision-free and oscillation-free navigation of multiple mobile robots or virtual agentsNonlinear Model-Predictive Control
: A model-based controller is employed to achieve simultaneously reference trajectory tracking and collision avoidance. REFs
Prioritized Safe-Interval Path Planning (SIPP)
: https://www.cs.cmu.edu/~maxim/files/sipp_icra11.pdfConflict Based Search(CBS)
: https://www.sciencedirect.com/science/article/pii/S0004370214001386Velocity obstacles
: https://gamma.cs.unc.edu/HRVO/HRVO-T-RO.pdfNonlinear Model-Predictive Control
: https://arxiv.org/abs/1703.011642. https://github.com/vita-epfl/CrowdNav (Pytorch(학습), RVO2(ORCA), matplotlib(시각화), gym.env(학습))