Open zhjying opened 4 months ago
Hello, sorry for not making it clear. The RLVS.py file refers to any of the python scripts in the scripts/ folder. More specifically, you can run the ddpg training for static contour following or for the moving target following (ddpg_stco.py or ddpg_follow_velx.py). You can also run the inference of these trained models with infer_ddpg_stco.py and infer_ddpg_follow_velx.py
Thanks for the clarification. I'll use the provided scripts for training and inference. Appreciate the help!
I'm sorry to bother you again, but after following the steps in run.md, the drone and vehicle aren't moving. Should I configure something myself, or is there a step I might be missing? I’m basing this on the fact that the view doesn’t change after running _rosrun image_view imageview image:=/Detection. To ensure I'm not missing any details, I've included some outputs from each command below. Thanks again for your help. By the way, I’m running this on Ubuntu 20.04.
roslaunch stalker summit.launch
[ INFO] [1723097878.108185994, 0.001000000]: Loading gazebo_ros_control plugin
[ INFO] [1723097878.109076173, 0.001000000]: Starting gazebo_ros_control plugin in namespace: /robot/
[ INFO] [1723097878.110532569, 0.001000000]: gazebo_ros_control plugin is waiting for model URDF in parameter [/robot/robot_description] on the ROS param server.
[ERROR] [1723097878.232867849, 0.001000000]: No p gain specified for pid. Namespace: /robot/gazebo_ros_control/pid_gains/robot_front_right_wheel_joint
[ERROR] [1723097878.234343712, 0.001000000]: No p gain specified for pid. Namespace: /robot/gazebo_ros_control/pid_gains/robot_front_left_wheel_joint
[ERROR] [1723097878.235539293, 0.001000000]: No p gain specified for pid. Namespace: /robot/gazebo_ros_control/pid_gains/robot_back_left_wheel_joint
[ERROR] [1723097878.236639344, 0.001000000]: No p gain specified for pid. Namespace: /robot/gazebo_ros_control/pid_gains/robot_back_right_wheel_joint
[ERROR] [1723097878.237711889, 0.001000000]: No p gain specified for pid. Namespace: /robot/gazebo_ros_control/pid_gains/robot_front_ptz_camera_pan_joint
[ERROR] [1723097878.238818750, 0.001000000]: No p gain specified for pid. Namespace: /robot/gazebo_ros_control/pid_gains/robot_front_ptz_camera_tilt_joint
[ INFO] [1723097878.242355020, 0.001000000]: Loaded gazebo_ros_control.
[ WARN] [1723097878.272534119, 0.001000000]: PlanarMovePlugin (ns = /robot/) missing
sim_vehicle.py --mavproxy-args="--streamrate=30" -v ArduCopter -f gazebo-iris --console --map
BUILD SUMMARY Build directory: /home/lxy/zjy/ardupilot/build/sitl Target Text (B) Data (B) BSS (B) Total Flash Used (B) Free Flash (B) bin/arducopter 3976540 173501 210632 4150041 Not Applicable
Build commands will be stored in build/sitl/compile_commands.json 'build' finished successfully (2.052s) SIM_VEHICLE: Using defaults from (../Tools/autotest/default_params/copter.parm,../Tools/autotest/default_params/gazebo-iris.parm) SIM_VEHICLE: Run ArduCopter SIM_VEHICLE: "/home/lxy/zjy/ardupilot/Tools/autotest/run_in_terminal_window.sh" "ArduCopter" "/home/lxy/zjy/ardupilot/build/sitl/bin/arducopter" "-S" "--model" "gazebo-iris" "--speedup" "1" "--slave" "0" "--defaults" "../Tools/autotest/default_params/copter.parm,../Tools/autotest/default_params/gazebo-iris.parm" "--sim-address=127.0.0.1" "-I0" RiTW: Starting ArduCopter : /home/lxy/zjy/ardupilot/build/sitl/bin/arducopter -S --model gazebo-iris --speedup 1 --slave 0 --defaults ../Tools/autotest/default_params/copter.parm,../Tools/autotest/default_params/gazebo-iris.parm --sim-address=127.0.0.1 -I0 SIM_VEHICLE: Run MavProxy SIM_VEHICLE: "mavproxy.py" "--out" "127.0.0.1:14550" "--out" "127.0.0.1:14551" "--master" "tcp:127.0.0.1:5760" "--sitl" "127.0.0.1:5501" "--streamrate" "30" "--map" "--console" WARNING: You should uninstall ModemManager as it conflicts with APM and Pixhawk Connect tcp:127.0.0.1:5760 source_system=255 [Errno 111] Connection refused sleeping Loaded module console Loaded module map Log Directory: Telemetry log: mav.tlog Waiting for heartbeat from tcp:127.0.0.1:5760 MAV> Detected vehicle 1:1 on link 0 STABILIZE> Received 1373 parameters (ftp) Saved 1373 parameters to mav.parm
roslaunch stalker apm.launch
[ WARN] [1723081379.479818387, 38.985000000]: CMD: Unexpected command 410, result 4
[ INFO] [1723081380.349558397, 39.852000000]: GF: Using MISSION_ITEM_INT
[ INFO] [1723081380.349653126, 39.852000000]: RP: Using MISSION_ITEM_INT
[ INFO] [1723081380.349711784, 39.852000000]: WP: Using MISSION_ITEM_INT
[ INFO] [1723081380.349779664, 39.852000000]: VER: 1.1: Capabilities 0x000000000000fbef
[ INFO] [1723081380.349822819, 39.852000000]: VER: 1.1: Flight software: 040404ff (865cffa5)
[ INFO] [1723081380.349868467, 39.852000000]: VER: 1.1: Middleware software: 00000000 ( )
[ INFO] [1723081380.349932698, 39.852000000]: VER: 1.1: OS software: 00000000 ( )
[ INFO] [1723081380.350002285, 39.852000000]: VER: 1.1: Board hardware: 00000000
[ INFO] [1723081380.350047018, 39.852000000]: VER: 1.1: VID/PID: 0000:0000
[ INFO] [1723081380.350102731, 39.853000000]: VER: 1.1: UID: 0000000000000000
[ INFO] [1723081381.989795052, 41.494000000]: FCU: EKF3 IMU1 origin set
[ INFO] [1723081382.080120107, 41.585000000]: FCU: Field Elevation Set: 584m
[ INFO] [1723081382.183240634, 41.687000000]: FCU: EKF3 IMU0 origin set
[ WARN] [1723081386.508394451, 46.012000000]: TM : RTT too high for timesync: 11.00 ms.
[ INFO] [1723081389.352779079, 48.856000000]: FCU: ArduCopter V4.4.4 (865cffa5)
[ INFO] [1723081389.353306191, 48.857000000]: FCU: c3b528eeb4774b5ba94bd65c03e964f7
[ INFO] [1723081389.353828623, 48.858000000]: FCU: Frame: QUAD/X
[ INFO] [1723081394.346495112, 53.849000000]: GF: mission received
[ INFO] [1723081394.347171219, 53.850000000]: RP: mission received
[ INFO] [1723081394.349004972, 53.853000000]: WP: mission received
[ INFO] [1723081404.807272045, 64.310000000]: FCU: EKF3 IMU0 is using GPS
[ INFO] [1723081404.808389743, 64.312000000]: FCU: EKF3 IMU1 is using GPS
[ WARN] [1723081416.666875475, 76.167000000]: PR: Param STAT_RUNTIME (65535/1373):
rosrun stalker ddpg_follow_velx.py 2024-08-08 14:18:30.761623: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2024-08-08 14:18:33.087592: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 3748 MB memory: -> device: 0, name: Tesla T4, pci bus id: 0000:65:00.0, compute capability: 7.5 2024-08-08 14:18:33.090566: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /job:localhost/replica:0/task:0/device:GPU:1 with 10067 MB memory: -> device: 1, name: Tesla T4, pci bus id: 0000:ca:00.0, compute capability: 7.5 Exceeded Bounds --> Return to initial position
rosrun color_detector detect_line.py starting node
rosrun color_detector box_to_line.py out of bounds out of bounds out of bounds
roslaunch darknet_ros darknet_ros.launch waiting for an image
Hello, sorry for the late reply. Can you manually make the drone takeoff? in this prompt: sim_vehicle.py --mavproxy-args="--streamrate=30" -v ArduCopter -f gazebo-iris --console --map after STABILIZE> write: mode GUIDED arm throttle takeoff 3 (make sure to run these commands a minute after the script is initialized otherwise you will get a gps error) if the drone does not move in the gazebo then it has something to do with the integration of ardupilot with gazebo. There are these instructions that might be helpful and I have used them in the past https://github.com/Intelligent-Quads/iq_tutorials/tree/master/docs
Hello, I am trying to run the stalker repository but noticed that the RLVS.py file mentioned in the scripts is missing. Could you please provide information on how to obtain this file or suggest an alternative solution? Thank you for your assistance.