/ESE650Project5

Feasible Path Planning for Cars and Pedestrians using Imitation Learning

Primary LanguageMATLABMIT LicenseMIT

Feasible Path Planning for Cars and Pedestrians using Imitation Learning

Problem Statement

Learn Cost Maps for feasible paths for cars and pedestrians using imitation of an oracle.

Usage Guide:

  1. Run WrapperCar.m for running Test Script for Car Planner.
  2. Run WrapperPedestrian.m for running Test Script for Pedestrian Planner.
  3. The training Codes for Car and Pedestrian are named TrainCar.m and TrainPredestrian.m respectively.
  4. The .mat file with CostMap for Car and Pedestrain are called CarModel.mat and PedestrainModel.mat.

Report:

You can find the report here.

Sample Outputs:

Pedestrian Paths:

Car Paths:

References:

  1. Ratliff, Nathan D., David Silver, and J. Andrew Bagnell. "Learning to search: Functional gradient techniques for imitation learning." Autonomous Robots 27.1 (2009): 25-53.