search

ROBOTIS-GIT / turtlebot3_machine_learning

Apache License 2.0
121 stars 82 forks source link

Issue Time is out of dual 32-bit range #11

Closed dovanhuong closed 6 years ago

dovanhuong commented 6 years ago

Dear Turtlebot3 team, I'm having an issue while running dqn machine learning for turtlebot3. after it run for a second it came to had an issue with " time is out of dual 32-bit range" as I copied description in below. Could you please have a look on it and give me your advice how to fix this issue!? Thank you in advance. /// Issue description. Command from DQN training: kist-cmr@kistcmr-940X3G-930X3G:~$ roslaunch turtlebot3_dqn turtlebot3_dqn_stage_3.launch ... logging to /home/kist-cmr/.ros/log/6daabb0e-db21-11e8-a010-052aeba48057/roslaunch-kistcmr-940X3G-930X3G-2351.log Checking log directory for disk usage. This may take awhile. Press Ctrl-C to interrupt Done checking log file disk usage. Usage is <1GB.

started roslaunch server http://kistcmr-940X3G-930X3G:35507/

SUMMARY

PARAMETERS

NODES / moving_obstacle (turtlebot3_dqn/moving_obstacle) turtlebot3_dqn_stage_3 (turtlebot3_dqn/turtlebot3_dqn_stage_3)

ROS_MASTER_URI=http://localhost:11311

process[turtlebot3_dqn_stage_3-1]: started with pid [2368] process[moving_obstacle-2]: started with pid [2369] Using TensorFlow backend.

Layer (type) Output Shape Param #

dense_1 (Dense) (None, 64) 1856

dense_2 (Dense) (None, 64) 4160

dropout_1 (Dropout) (None, 64) 0

dense_3 (Dense) (None, 5) 325

activation_1 (Activation) (None, 5) 0

Total params: 6,341 Trainable params: 6,341 Non-trainable params: 0

Layer (type) Output Shape Param #

dense_4 (Dense) (None, 64) 1856

dense_5 (Dense) (None, 64) 4160

dropout_2 (Dropout) (None, 64) 0

dense_6 (Dense) (None, 5) 325

activation_2 (Activation) (None, 5) 0

Total params: 6,341 Trainable params: 6,341 Non-trainable params: 0

[INFO] [1540779779.192717, 0.559000]: Goal position : 0.6, 0.0

[INFO] [1540779804.492929, 15.190000]: Ep: 1 score: -256.66 memory: 65 epsilon: 1.00 time: 0:00:26

Traceback (most recent call last): File "/home/kist-cmr/catkin_ws/src/turtlebot3_machine_learning/turtlebot3_dqn/nodes/turtlebot3_dqn_stage_3", line 168, in next_state, reward, done = env.step(action) File "/home/kist-cmr/catkin_ws/src/turtlebot3_machine_learning/turtlebot3_dqn/src/turtlebot3_dqn/environment_stage_3.py", line 139, in step reward = self.setReward(state, done, action) File "/home/kist-cmr/catkin_ws/src/turtlebot3_machine_learning/turtlebot3_dqn/src/turtlebot3_dqn/environment_stage_3.py", line 116, in setReward self.goal_x, self.goal_y = self.respawn_goal.getPosition(True, delete=True) File "/home/kist-cmr/catkin_ws/src/turtlebot3_machine_learning/turtlebot3_dqn/src/turtlebot3_dqn/respawnGoal.py", line 83, in getPosition self.deleteModel() File "/home/kist-cmr/catkin_ws/src/turtlebot3_machine_learning/turtlebot3_dqn/src/turtlebot3_dqn/respawnGoal.py", line 76, in deleteModel del_model_prox(self.modelName) File "/opt/ros/kinetic/lib/python2.7/dist-packages/rospy/impl/tcpros_service.py", line 435, in call return self.call(*args, *kwds) File "/opt/ros/kinetic/lib/python2.7/dist-packages/rospy/impl/tcpros_service.py", line 515, in call responses = transport.receive_once() File "/opt/ros/kinetic/lib/python2.7/dist-packages/rospy/impl/tcpros_base.py", line 727, in receive_once p.read_messages(b, msg_queue, sock) File "/opt/ros/kinetic/lib/python2.7/dist-packages/rospy/impl/tcpros_service.py", line 353, in read_messages self._read_ok_byte(b, sock) File "/opt/ros/kinetic/lib/python2.7/dist-packages/rospy/impl/tcpros_service.py", line 336, in _read_ok_byte raise ServiceException("service [%s] responded with an error: %s"%(self.resolved_name, str)) rospy.service.ServiceException: service [/gazebo/delete_model] responded with an error: Time is out of dual 32-bit range [turtlebot3_dqn_stage_3-1] process has died [pid 2368, exit code 1, cmd /home/kist-cmr/catkin_ws/src/turtlebot3_machine_learning/turtlebot3_dqn/nodes/turtlebot3_dqn_stage_3 __name:=turtlebot3_dqn_stage_3 __log:=/home/kist-cmr/.ros/log/6daabb0e-db21-11e8-a010-052aeba48057/turtlebot3_dqn_stage_3-1.log]. log file: /home/kist-cmr/.ros/log/6daabb0e-db21-11e8-a010-052aeba48057/turtlebot3_dqn_stage_3-1.log

Command for gazebo: kist-cmr@kistcmr-940X3G-930X3G:~$ roslaunch turtlebot3_gazebo turtlebot3_stage_3.launch ... logging to /home/kist-cmr/.ros/log/6daabb0e-db21-11e8-a010-052aeba48057/roslaunch-kistcmr-940X3G-930X3G-1897.log Checking log directory for disk usage. This may take awhile. Press Ctrl-C to interrupt Done checking log file disk usage. Usage is <1GB.

xacro: Traditional processing is deprecated. Switch to --inorder processing! To check for compatibility of your document, use option --check-order. For more infos, see http://wiki.ros.org/xacro#Processing_Order xacro.py is deprecated; please use xacro instead started roslaunch server http://kistcmr-940X3G-930X3G:39243/

SUMMARY

PARAMETERS

NODES / gazebo (gazebo_ros/gzserver) gazebo_gui (gazebo_ros/gzclient) spawn_urdf (gazebo_ros/spawn_model)

auto-starting new master process[master]: started with pid [1911] ROS_MASTER_URI=http://localhost:11311

setting /run_id to 6daabb0e-db21-11e8-a010-052aeba48057 process[rosout-1]: started with pid [1924] started core service [/rosout] process[gazebo-2]: started with pid [1927] process[gazebo_gui-3]: started with pid [1932] process[spawn_urdf-4]: started with pid [1937] [ INFO] [1540779727.024198143]: Finished loading Gazebo ROS API Plugin. [ INFO] [1540779727.024966235]: waitForService: Service [/gazebo/set_physics_properties] has not been advertised, waiting... Couldn't find a preferred IP via the getifaddrs() call; I'm assuming that your IP address is 127.0.0.1. This should work for local processes, but will almost certainly not work if you have remote processes.Report to the disc-zmq development team to seek a fix. Couldn't find a preferred IP via the getifaddrs() call; I'm assuming that your IP address is 127.0.0.1. This should work for local processes, but will almost certainly not work if you have remote processes.Report to the disc-zmq development team to seek a fix. Couldn't find a preferred IP via the getifaddrs() call; I'm assuming that your IP address is 127.0.0.1. This should work for local processes, but will almost certainly not work if you have remote processes.Report to the disc-zmq development team to seek a fix. Couldn't find a preferred IP via the getifaddrs() call; I'm assuming that your IP address is 127.0.0.1. This should work for local processes, but will almost certainly not work if you have remote processes.Report to the disc-zmq development team to seek a fix. [ INFO] [1540779727.445171329, 0.023000000]: waitForService: Service [/gazebo/set_physics_properties] is now available. [ INFO] [1540779727.489099999, 0.066000000]: Physics dynamic reconfigure ready. [ INFO] [1540779727.645949424, 0.141000000]: Laser Plugin: Using the 'robotNamespace' param: '/' [ INFO] [1540779727.646047582, 0.141000000]: Starting Laser Plugin (ns = /) [ INFO] [1540779727.648495262, 0.141000000]: Laser Plugin (ns = /) , set to "" [spawn_urdf-4] process has finished cleanly log file: /home/kist-cmr/.ros/log/6daabb0e-db21-11e8-a010-052aeba48057/spawn_urdf-4*.log [ INFO] [1540779727.736957369, 0.141000000]: Starting plugin DiffDrive(ns = //) [ INFO] [1540779727.737100552, 0.141000000]: DiffDrive(ns = //): = na [ INFO] [1540779727.738137890, 0.141000000]: DiffDrive(ns = //): = [ WARN] [1540779727.738257190, 0.141000000]: DiffDrive(ns = //): must be either true or false [ WARN] [1540779727.738284271, 0.141000000]: DiffDrive(ns = //): must be either true or false [ WARN] [1540779727.738308214, 0.141000000]: DiffDrive(ns = //): must be either true or false [ INFO] [1540779727.739348552, 0.141000000]: DiffDrive(ns = //): Try to subscribe to cmd_vel [ INFO] [1540779727.742647201, 0.141000000]: DiffDrive(ns = //): Subscribe to cmd_vel [ INFO] [1540779727.744078090, 0.141000000]: DiffDrive(ns = //): Advertise odom on odom Couldn't find a preferred IP via the getifaddrs() call; I'm assuming that your IP address is 127.0.0.1. This should work for local processes, but will almost certainly not work if you have remote processes.Report to the disc-zmq development team to seek a fix. Couldn't find a preferred IP via the getifaddrs() call; I'm assuming that your IP address is 127.0.0.1. This should work for local processes, but will almost certainly not work if you have remote processes.Report to the disc-zmq development team to seek a fix. Couldn't find a preferred IP via the getifaddrs() call; I'm assuming that your IP address is 127.0.0.1. This should work for local processes, but will almost certainly not work if you have remote processes.Report to the disc-zmq development team to seek a fix. Couldn't find a preferred IP via the getifaddrs() call; I'm assuming that your IP address is 127.0.0.1. This should work for local processes, but will almost certainly not work if you have remote processes.Report to the disc-zmq development team to seek a fix. [ERROR] [1540779811.093034347, 3.621000000]: Exception thrown while processing service call: Time is out of dual 32-bit range

kijongGil commented 6 years ago

Hi, @dovanhuong :) Could you tell me what is gazebo and tensorflow version?

dovanhuong commented 6 years ago

hello, @kijongGil I'm using Gazebo9 and tensorflow version 1.12.0-rc0. and ROS Kinetic. Could you please help to check this!?

kijongGil commented 6 years ago

Did you use ubuntu 18.04? Because I use Gazebo7, ubuntu 16.04 and ROS Kinetic. We are not support ubuntu 18.04 yet. I think your problem is Gazebo 9. But, I can not use Gazebo 9 in ubuntu 16.04. Could you change your environment?

dovanhuong commented 6 years ago

I think the problem is come from Gazebo 9. I tested again with Gazebo 7 and it worked fine. I'll consider to think about change to my own environment. Thank you so much! ;)

kijongGil commented 6 years ago

This issue is closing. Please reopen it when you have another issue. Thanks.