Index Data based on orientation Testing q-learning Crash 150 eps Data based on orientation The laser always takes its measurements from an absolute orientation, so we cannot rely on the ...

Index LearningAgent Class ParkingAgent Class LearningAgent Class The LearningAgent class implements a Q-learning agent optimized for parking tasks using LiDAR and fixed angular velocity. T...

Index Building scenario Getting started with Q-Learning Building scenario By modifying the scenario I have not been able to figure out how to add static agents. The only ways I have manage...

Index Searching Chassis Using RLidar Searching Chassis SMARTS uses in all its examples a chassis called BoxChassis, which I didn’t think much of at first. Investigating the guts I found th...

Index Testing RLidar Configuring RLidar Testing RLidar After further testing, it has been determined that the sensor is detecting the ground, then an image of the lidar beams will be displ...

Index Using RLIDAR Setting scenario Using RLIDAR Several tests have been carried out within the same scenario to check the lidar measurements. Among them, a test has been done with our ag...

Index Using RLIDAR Configuring enviroment Using RLIDAR Some of the RLIDAR tests will be shown as the output of the array hits: hits: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,...

Index Using RLIDAR Sensor measurements Using RLIDAR To use the lidar we have to write this line in the main: def main(scenarios, headless, num_episodes, max_episode_steps=None): agent_...

Index Starting to go backwards Sensor measurements Starting to go backwards The main problem with this phase is that the simulator is designed to drive exclusively forwards, in fact, the r...

Index Basic Teleop Velocities Teleop Basic Teleop In this example the predefined actions of SMARTS are used, so the control of the car is not absolute and it is very difficult to leave the...