Open UtkarshMishra04 opened 3 years ago
I have created the files mentioned above and have started testing the environment file.
However, I get the rosmaster error:
[ERROR] [1615899275.259326]: Unable to immediately register with master node [http://localhost:11311]: master may not be running yet. Will keep trying.
which is not the case for any different brain.
This is my configuration file. PS: I have disabled the algorithm parameters (aka robot['Parameters']) in utils/configuration.py
temporarily.
Behaviors: Robot: Sensors: Cameras: Camera_0: Name: 'camera_0' Topic: '/F1ROS/cameraL/image_raw' Pose3D: Pose3D_0: Name: 'pose3d_0' Topic: '/F1ROS/odom' Actuators: Motors: Motors_0: Name: 'motors_0' Topic: '/F1ROS/cmd_vel' MaxV: 3 MaxW: 0.3 BrainPath: 'brains/f1rl/f1_follow_line_camera_continuous.py' Type: 'f1rl' Simulation: World: /opt/jderobot/share/jderobot/gazebo/launch/f1_1_simplecircuit.launch Dataset: In: '/tmp/my_bag.bag' Out: '' Stats: Out: './' PerfectLap: 'lap-simple-circuit.bag' Layout: Frame_0: Name: frame_0 Geometry: [1, 1, 2, 2] Data: rgbimage Frame_1: Name: frame_1 Geometry: [0, 1, 1, 1] Data: rgbimage
If you're able to run any other brain under f1rl
folder, I guess that the problem must come from your brain file f1_follow_line_camera_continuous.py
The simulation world starts? Have you followed the same structure as the other brains in the folder? I will need more details to help you 😄
Hi I forgot to mention that all f1rl brain is giving the same error. The simulation world is not starting but Behavior studio window opens up. Yes, my structure is perfectly the same as that of other brains, in particular with the DQN brain.
Current Setup: DQN and Q-learning are already done with Discrete Control Actions
To be introduced: Policy Gradient Algorithm with Continuous Control Actions
Major Changes: