@Nitin-Varma-Vegesna said in GPS for Starling2:
I got the compass sensor missing error for my Starling2, and I think it's an issue with the GPS. I want to buy a new GPS for the Starling2 ASAP, and I didn't see it on the products on the website. Is there a way for me to do that?
1 Reply Last reply a day ago Reply
@Nitin-Varma-Vegesna https://store.3dr.com/mini-gps-ublox-max-m10s/ <-- this is the gps that comes default with the starlings.
@svempati said in No detections when running custom YOLOv8 model on voxl-tflite-server:
I just ran voxl-tflite-server directly from the command line instead of in the background via systemd - aka run voxl-tflite-server directly on the command line. I would recommend NOT quantizing your model as the directions in the train yolov8 do not recommend that.
Zach
These are all the potential data types that voxl-tflite-server is expecting.
@svempati said in No detections when running custom YOLOv8 model on voxl-tflite-server:
"labels": "/usr/bin/dnn/yolov8_labels.txt",
So running your model we get the following errors via voxl-tflite-server:
Error in TensorData<float>: should not reach here
Error in TensorData<float>: should not reach here
Error in TensorData<float>: should not reach here
Error in TensorData<float>: should not reach here
Error in TensorData<float>: should not reach here
Error in TensorData<float>: should not reach here
Error in TensorData<float>: should not reach here
Error in TensorData<float>: should not reach here
Which means there is an issue in your model itself and most likely means you ran into an issue during the build process. Specifically this means that is a model issue, not a labels file issue. Your .tflite model has an output tensor with a different data type than what voxl-tflite-server expects
The code itself shows the error when you hit this case statement:
// Gets the uint8_t tensor data pointer
template <>
inline uint8_t *TensorData(TfLiteTensor *tensor, int batch_index)
{
int nelems = 1;
for (int i = 1; i < tensor->dims->size; i++)
{
nelems *= tensor->dims->data[i];
}
switch (tensor->type)
{
case kTfLiteUInt8:
return tensor->data.uint8 + nelems * batch_index;
default:
fprintf(stderr, "Error in %s: should not reach here\n",
__FUNCTION__);
}
return nullptr;
}
Which means the output tensor doesnt match the expected output in this header file. Please look into your model.
zach
@jonathankampia said in M0201 gimbal passthrough pinout:
M0201
https://forum.modalai.com/topic/4735/m0201-m0153-j2-pinout/3
Please refer to this post for the pniout guide on the m0201
Hello @svempati can you paste your yolov8_labels and tflite file and I can test it out on my end?
To confirm - you followed the instructions in this gitlab repository: https://gitlab.com/voxl-public/support/voxl-train-yolov8
Zach
Confirmed - can run the dds with humble running in the docker container:
voxl2 (M0054):~$ apt-get install voxl-microdds-agent
Reading package lists... Done
Building dependency tree
Reading state information... Done
The following NEW packages will be installed:
voxl-microdds-agent
0 upgraded, 1 newly installed, 0 to remove and 40 not upgraded.
Need to get 0 B/4874 kB of archives.
After this operation, 0 B of additional disk space will be used.
Get:1 file:/data/voxl-suite-offline-packages ./ voxl-microdds-agent 3.0.0-0 [4874 kB]
debconf: delaying package configuration, since apt-utils is not installed
Selecting previously unselected package voxl-microdds-agent.
(Reading database ... 104493 files and directories currently installed.)
Preparing to unpack .../voxl-microdds-agent_3.0.0-0_arm64.deb ...
Unpacking voxl-microdds-agent (3.0.0-0) ...
Setting up voxl-microdds-agent (3.0.0-0) ...
voxl2 (M0054):~$ systemctl start voxl-microdds-agent
voxl2 (M0054):~$ systemctl status voxl-microdds-agent
● voxl-microdds-agent.service - voxl-microdds-agent
Loaded: loaded (/usr/bin/MicroXRCEAgent; disabled; vendor preset: enabled)
Active: active (running) since Tue 2025-11-25 15:13:37 UTC; 14s ago
Main PID: 3370 (MicroXRCEAgent)
Tasks: 28 (limit: 4915)
CGroup: /system.slice/voxl-microdds-agent.service
└─3370 /usr/bin/MicroXRCEAgent udp4 -p 8888
Nov 25 15:13:38 m0054 MicroXRCEAgent[3370]: [1764083618.308177] info | ProxyClient.cpp | create_datawriter | datawriter created | client_key: 0x00000001, datawriter_id: 0x0DF(5), publisher_id: 0x0DF(3)
Nov 25 15:13:38 m0054 MicroXRCEAgent[3370]: [1764083618.308829] info | ProxyClient.cpp | create_topic | topic created | client_key: 0x00000001, topic_id: 0x0E6(2), participant_id: 0x001(1)
Nov 25 15:13:38 m0054 MicroXRCEAgent[3370]: [1764083618.308994] info | ProxyClient.cpp | create_publisher | publisher created | client_key: 0x00000001, publisher_id: 0x0E6(3), participant_id: 0x001(1)
Nov 25 15:13:38 m0054 MicroXRCEAgent[3370]: [1764083618.309525] info | ProxyClient.cpp | create_datawriter | datawriter created | client_key: 0x00000001, datawriter_id: 0x0E6(5), publisher_id: 0x0E6(3)
Nov 25 15:13:38 m0054 MicroXRCEAgent[3370]: [1764083618.310013] info | ProxyClient.cpp | create_topic | topic created | client_key: 0x00000001, topic_id: 0x0EB(2), participant_id: 0x001(1)
Nov 25 15:13:38 m0054 MicroXRCEAgent[3370]: [1764083618.310133] info | ProxyClient.cpp | create_publisher | publisher created | client_key: 0x00000001, publisher_id: 0x0EB(3), participant_id: 0x001(1)
Nov 25 15:13:38 m0054 MicroXRCEAgent[3370]: [1764083618.310468] info | ProxyClient.cpp | create_datawriter | datawriter created | client_key: 0x00000001, datawriter_id: 0x0EB(5), publisher_id: 0x0EB(3)
Nov 25 15:13:38 m0054 MicroXRCEAgent[3370]: [1764083618.310981] info | ProxyClient.cpp | create_topic | topic created | client_key: 0x00000001, topic_id: 0x0F0(2), participant_id: 0x001(1)
Nov 25 15:13:38 m0054 MicroXRCEAgent[3370]: [1764083618.311145] info | ProxyClient.cpp | create_publisher | publisher created | client_key: 0x00000001, publisher_id: 0x0F0(3), participant_id: 0x001(1)
Nov 25 15:13:38 m0054 MicroXRCEAgent[3370]: [1764083618.311488] info | ProxyClient.cpp | create_datawriter | datawriter created | client_key: 0x00000001, datawriter_id: 0x0F0(5), publisher_id: 0x0F0(3)
voxl2 (M0054):~$ docker images
REPOSITORY TAG IMAGE ID CREATED SIZE
ros2-image ed11b766 1040efe3dc33 2 weeks ago 2.33GB
voxl2 (M0054):~$ docker run -it --rm --net=host --ipc=host ros2-image /bin/bash
root@m0054:/# cd
root@m0054:~# ls
root@m0054:~# source /opt/ros/humble/setup.bash
root@m0054:~# ros2 topic list
/fmu/in/obstacle_distance
/fmu/in/offboard_control_mode
/fmu/in/onboard_computer_status
/fmu/in/sensor_optical_flow
/fmu/in/telemetry_status
/fmu/in/trajectory_setpoint
/fmu/in/vehicle_attitude_setpoint
/fmu/in/vehicle_command
/fmu/in/vehicle_mocap_odometry
/fmu/in/vehicle_rates_setpoint
/fmu/in/vehicle_trajectory_bezier
/fmu/in/vehicle_trajectory_waypoint
/fmu/in/vehicle_visual_odometry
/fmu/out/battery_status
/fmu/out/failsafe_flags
/fmu/out/position_setpoint_triplet
/fmu/out/sensor_combined
/fmu/out/timesync_status
/fmu/out/vehicle_attitude
/fmu/out/vehicle_control_mode
/fmu/out/vehicle_local_position
/fmu/out/vehicle_odometry
/fmu/out/vehicle_status
/parameter_events
/rosout
@jmltt said in Ros2 Humble on Voxl2:
Are there instructions on installing docker on target? The modalai guide (https://docs.modalai.com/docker-on-voxl/) references to just use the docker instructions to install via apt, but the docker install instructions linked to require an ubuntu o.s. newer than 20.04 so I wasn't sure if it would work.
@jmltt please find answers for your questions below:
Are there instructions on installing docker on target? The modalai guide (https://docs.modalai.com/docker-on-voxl/) references to just use the docker instructions to install via apt, but the docker install instructions linked to require an ubuntu o.s. newer than 20.04 so I wasn't sure if it would work. --> I always just use this file to install docker on target on the voxl2 (works for any ubuntu device as well btw): https://github.com/docker/docker-install/blob/master/install.sh
In switching to ros2 humble onboard the voxl2 do I need to update the dds client module and rebuild voxl-px4 and rebuild the voxl-microdds-agent as well? I'm assuming that if they're built to work with ros2 foxy they're going to be dependent on older versions of fast-dds than what humble would be using and might not be compatible -> No you do not need to reinstall the fast dds with a different instance. Keep in mind the DDS is ros2 agnostic and runs as the middleware BUT I will test this out this morning.
For examples the best I can do is show you what I do when running something like ros2 docker containers:
E.G:
-v /usr/include/modal_pipe_common.h:/usr/include/modal_pipe_common.h \
-v /usr/include/modal_pipe_client.h:/usr/include/modal_pipe_client.h \
-v /usr/include/c_library_v2:/usr/include/c_library_v2 \
-v /run/mpa:/run/mpa \
-v /usr/bin/voxl-list-pipes:/usr/bin/voxl-list-pipes \
-v /usr/include/voxl_cutils.h:/usr/include/voxl_cutils.h \
-v /usr/include/cJSON.h:/usr/include/cJSON.h \
-v /usr/include/modal_pipe_deprecated.h:/usr/include/modal_pipe_deprecated.h \
-v /usr/include/modal_pipe_interfaces.h:/usr/include/modal_pipe_interfaces.h \
-v /usr/include/modal_pipe_common.h:/usr/include/modal_pipe_common.h \
-v /usr/include/modal_pipe_client.h:/usr/include/modal_pipe_client.h \
-v /usr/include/modal_start_stop.h:/usr/include/modal_start_stop.h \
-v /usr/lib64/libvoxl_cutils.so:/usr/lib/libvoxl_cutils.so \
-v /usr/lib64/libmodal_json.so:/usr/lib/libmodal_json.so \
-v /usr/lib64/libmodal_pipe.so:/usr/lib/libmodal_pipe.so \
-v /usr/lib/libgbm.so:/usr/lib/aarch64-linux-gnu/libgbm.so \
-v /tmp:/tmp \
-v /etc/modalai:/etc/modalai \
-v /dev:/host/dev"
docker run --rm -it \
--privileged \
--net=host \
--ipc=host \
${VOLUMES} \
-e ROS_DOMAIN_ID=$ROS_DOMAIN_ID \
--entrypoint "/bin/bash" \
DOCKER_IMAGE_NAME_AND_TAG -c /bin/bash
https://gitlab.com/voxl-public/support/voxl-train-yolov8
I am assuming you followed this instruction set for training your model?
@jeremyrbrown5 if you paste your model and upload it here i can download it and help troubleshoot the issue you are running into
@Jakub-Tvrz said in Starling 2 Max for indoor:
We haven't bought anything yet, but we are deciding what will be the best for our warehouse inventory application. Of course, we considered the ToF option. But you still say: "however, it is not... great" - does that mean that Starling 2 is better for our application? Or does Dual vs Triple camera for Visual Inertial Odometry also have an impact?
Reply
Depends fully on your use case. I will say that PX4's instance of obstacle avoidance is not fantastic, but it is better than nothing. In my opinion I would go w/ the model that has all the bells and whistles in case you need the hardware and decide to develop your own collision avoidance or somethign of that nature.
@jeremyrbrown5 said in Issues with custom Yolov8:
@Zachary-Lowell-0 we are using the yolo predict function inside the voxl-docker. I didn't know about voxl-inspect-detections, so I'll try that.
Reply
If you are running your model directly on voxl-tflite-server then you can leverage the voxl sdk to detect any outputs from the model. That SDK is what is showing the image on voxl-portal. My guess is since this images arent showing on voxl-portal then you are having an issue during startup.
Can you run voxl-tflite-server directly on the command line and paste the output in here?
@jeremyrbrown5 I will plan on testing this out tomorrow - how are you validatign that it is detecting the rpis? Are you running voxl-inspect-detections tflite_data -a?
You will need the SKU supporting the TOF to accurately run current versions of voxl-mapper and VOA.
Zach
The system has an HDMI out so you can plug it into an external monitor yes:
@Ido-Goldstein to run yolov8 run voxl-configure-tflite-server and then when it prompts you to select your model, you can select yolov8. YOLOV11 is also currently supported however is still CPU bound so I would recommend using yolov8 for GPU processing
@Jakub-Tvrz said in Starling 2 Max for indoor:
● Next Generation PMD ToF image sensor for obstacle avoidance and 3D mapping
@Jakub-Tvrz if you purchased the starling 2 Max version that comes with the PMD TOF then you will be capable of running PX4's instance of visual obstacle avoidance - however, it is not... great.
● Next Generation PMD ToF image sensor for obstacle avoidance and 3D mapping
https://www.modalai.com/collections/all/products/starling-2-max?variant=49129974169904 <-- this the version you will had to buy for the TOF sensor
@taiwohazeez unsure if I am following this "hover mode" are you attempting to put the drone into HOLD mode? If so HOLD mode on base PX4 isnt supported without a GPS hold, so if you are flying indoors, there is a high likely hood that the GPS is relaying poor data causing the drone to drift a bit. I would recommend in QGC to turn off the GPS via the parameters and instead of going into hold mode, just staying in position mode while letting go of the sticks and see if it holds then
Zach
@all - you can just change the SYS_ID of each drone and this should solve the port confliction.
@tomverstappen I am unable to recreate the issue with a starling running 1.5.0 - the output from voxl-vision-hub shows the relative coordinate frame from the tag relative to the camera and was able to get the drone to offset correctly.
Are there any logs you can paste in here or video?