Questions tagged with AWS DeepRacer

> The problem is related to registering a **AWS DeepLens v1.1 Camera** I am failing to register a AWS Deeplens camera using machines running Ubuntu 20.4 (focal) and Mint 19.3 (tessa) or ubuntu bionic, with the error: **Device not detected**. This is when trying to follow the *Register an AWS DeepLens v1.1 device * steps on the AWS web console. Trying to go via other forums, I am made to believe that there is a need to have the **awscam** package installed on the linux machines. I ama failing to install the package as well, with the error below. Is the a awscam package for debian distributions, and more precisely for Ubuntu 20.4? **sudo apt-get install awscam** ``` sudo apt-get install awscam Reading package lists... Done Building dependency tree Reading state information... Done E: Unable to locate package awscam ``` **lsb_release -a** ``` lsb_release -a No LSB modules are available. Distributor ID: Ubuntu Description: Ubuntu 20.04.4 LTS Release: 20.04 Codename: focal ```

Hello, I have submitted an entry to Deep Racer April Open league from a temporary AWS account which has been deleted/removed. How I get the entry (or the model) moved/ported to my new/permanent AWS account. I cannot access the temporary AWS account anymore nor I have saved my model to submit again from new/permanent account. Please help. Regards, Raghavendra

LED stays in yellow(red) state. If I connect monitor/mouse/keyboard directly to Deepracer, the boot sequence has two Fails. To activate swap file and to start load/save Random Seed, and it never enter GUI login screen. In an earlier stage when connected directly with a monitor the Ubuntu GUI came up and I could login to Deepracer with deepracer password, but when trying to set up a new complicated password many times it kept responding "Sorry, that didn't work. Please try again"

I can't find the notebook for it anywhere so if anyone can give me something for the API of this thing so I can code stuff with libraries and my own models that would be great

How can I verify that the LIDAR is working correctly? Can I see it LIDAR data from a terminal window, Does the rplidarNode print to a log file? Just wanted to verify before a month return window closes! Thanks!

Does the dotted centerline of the track have to be yellow or can the centerline be any color, and still be recognized as centerline by NN.

I want to use matlab to learn deepracer. If you proceed with the ros2 topic list in the deepracer, /camera_pkg/display_mjpeg /camera_pkg/video_mjpeg /ctrl_pkg/raw_pwm /ctrl_pkg/servo_msg /deepracer_navigation_pkg/auto_drive /deepracer_systems_pkg/network_connection_status /deepracer_systems_pkg/software_update_pct /inference_pkg/rl_results /parameter_events /rosout /rplidar_ros/scan /sensor_fusion_pkg/overlay_msg /sensor_fusion_pkg/sensor_msg /usb_monitor_pkg/usb_file_system_notification /webserver_pkg/calibration_drive /webserver_pkg/manual_drive The above is output, but in practice, it cannot be used except for display_mjpeg, overlay_msg, /rplidar_ros/scan. When I looked up the reason, ros2 topic echo /camera_pkg/video_mjpeg Traceback (most recent call last): File "/opt/ros/foxy/bin/ros2", line 11, in <module> load_entry_point('ros2cli==0.9.8', 'console_scripts', 'ros2')() File "/opt/ros/foxy/lib/python3.8/site-packages/ros2cli/cli.py", line 67, in main rc = extension.main(parser=parser, args=args) File "/opt/ros/foxy/lib/python3.8/site-packages/ros2topic/command/topic.py", line 41, in main return extension.main(args=args) File "/opt/ros/foxy/lib/python3.8/site-packages/ros2topic/verb/echo.py", line 81, in main return main(args) File "/opt/ros/foxy/lib/python3.8/site-packages/ros2topic/verb/echo.py", line 95, in main message_type = get_msg_class(node, args.topic_name, include_hidden_topics=True) File "/opt/ros/foxy/lib/python3.8/site-packages/ros2topic/api/__init__.py", line 88, in get_msg_class msg_class = _get_msg_class(node, topic, include_hidden_topics) File "/opt/ros/foxy/lib/python3.8/site-packages/ros2topic/api/__init__.py", line 133, in _get_msg_class return get_message(message_type) File "/opt/ros/foxy/lib/python3.8/site-packages/rosidl_runtime_py/utilities.py", line 28, in get_message interface = import_message_from_namespaced_type(get_message_namespaced_type(identifier)) File "/opt/ros/foxy/lib/python3.8/site-packages/rosidl_runtime_py/import_message.py", line 30, in import_message_from_namespaced_type module = importlib.import_module( File "/usr/lib/python3.8/importlib/__init__.py", line 127, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "<frozen importlib._bootstrap>", line 1014, in _gcd_import File "<frozen importlib._bootstrap>", line 991, in _find_and_load File "<frozen importlib._bootstrap>", line 961, in _find_and_load_unlocked File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed File "<frozen importlib._bootstrap>", line 1014, in _gcd_import File "<frozen importlib._bootstrap>", line 991, in _find_and_load File "<frozen importlib._bootstrap>", line 973, in _find_and_load_unlocked ModuleNotFoundError: No module named 'deepracer_interfaces_pkg' As above, it is said that the depth_interfaces_pkg cannot be found. However, I completed the build after installation as shown below. (https://github.com/aws-deepracer/aws-deepracer-interfaces-pkg) I wait for an answer to what I should do to use the deepacer-interfaces-pkg in the deepracer. Please tell me how to solve this problem.

https://repost.aws/questions/QU9PJl7BvYTE6fEvKsa-GouQ#ANJDSwe-nfT5e--OEfw6tIQw The link above is my previous question. I finally solved this problem. Those who experienced the same problem as me would have tried to initialize by following the link below. https://docs.aws.amazon.com/deepracer/latest/developerguide/deepracer-ubuntu-update-preparation.html For those who have experienced similar problems, aws told me that the "shell script" file will run automatically if I run the link above. When booted into the usb iso file, the "shell script" actually worked, but it did not initialize. * To solve this problem, only the contents of the factory reset file must be included in the Flask usb drive. The link below contains what I explained. https://www.youtube.com/watch?v=f_GD7RcMsR0 * In aws, in order to avoid this problem, it would be better to correct that part in the link below and add related photos. https://docs.aws.amazon.com/deepracer/latest/developerguide/deepracer-ubuntu-update-preparation.html

https://docs.aws.amazon.com/deepracer/latest/developerguide/deepracer-vehicle-factory-reset-preparation.html I upgraded the aws deepracer to 20.04.01 using the document provided by aws. However, when I booted to usb iso file and installed ubuntu20.04, I received the message "ubuntu has been blocked by the current security policy", so I can no longer proceed. The answers written by aws representatives in the link below are neither correct nor relevant to the document. How should we solve this problem? Please give me accurate information that I can solve this problem. I need a quick answer. https://repost.aws/questions/QUvRolXJh2SVanVuL8aDiUUA/aws-deep-racer-reinstallation-error-and-the-ubuntu-has-been-blocked-by-the-current-security-policy https://repost.aws/questions/QUhzOK7OazR5O692KZ9nZxpA/ubuntu-has-been-blocked-by-the-current-security-policy-error-after-updating-aws-deep-racer-device-to-the-ubuntu-20-04

Is it possible to create my own neural network instead of using the built in ppo or sac

During the reinstallation of ubuntu in Deepracer, 'https://docs.aws.amazon.com/deepracer/latest/developerguide/deepracer-vehicle-factory-reset-preparation.html' I ran as described here, but it is not proceeding with a warning saying ubuntu has been blocked by the current security policy.

I was following this guide (https://docs.aws.amazon.com/deepracer/latest/developerguide/deepracer-ubuntu-update-instructions.html) to flash Deepracer device. But after step 4, the boot USB loaded a temporary ubuntu UI with an icon on desktop to install ubuntu 20.04. This isn't what the documentation describes in step 5 onward. After installing the new OS and restarted, I got an error "ubuntu has been blocked by the current security policy". Quick google search pointed out that I have to disable "secure boot", but this option isn't found anywhere in BIOS. I went back to the boot device to retry installing many times to no avail. What do to now?

Hi Can I get the additional body shell? I can not find on Amazon.com

Hey there, I keep getting a network error every time I try to sign up to the DeepRacer Student. I tried using my school email, then my was email. I tried logging in with my school email too, and my AWS Educate credentials and so on. I then even set up multi-user access for deep racers but it still didn't work. I keep getting a network error response every time I try to sign up or login in. I don't know what to do and I would be really grateful for some support. Thank you. edit: just saw that it's the same for AWS BugBust, when I try to sign up or login it gives a network error too.

I am experiencing an issue while attempting calibration on my car. I have updated my software to the latest available (2.0.173.0). I booted up the compute module and then turned on the servo switch. I got the two short and the long beep. However, I cannot get the wheels to turn in the forward direction. The reverse direction switch does nothing. How do I fix this? Further info: it seems like all the servo responses are the reverse of what I would expect. When aligning the front wheels, it's the front right wheel that wants to line up with the back, rather than the front left, as the diagram would suggest. Also the left/right turn response during calibration seems opposite as well. The connectors between the compute module and the rest of the car look right. This seems to be an issue with the calibrations and there's a minus sign missing somewhere!

Just received my DeepRacer Evo and the compute battery (Asus power bank) is dead on arrival. When you attempt to charge it, the LEDs flash quickly which the manual indicates is an error condition. I left it on the charger for a few hours but no change. The power bank won't turn on at all. How do I go about getting a replacement power bank? A quick search of the forums shows that this seems to be a common issue. For reference, my Amazon order is #113-4655438-6809828. Thanks.

When I have tried to connect to the car's web interface, on a desktop, only the login page displays, but the /home page remains blank. I have tried Edge and IE on a Windows computer and Chrome on an Ubuntu computer. When I tried Edge on my Android phone, there was no problem. I had a similar problem when I tried to set up the WiFi over USB; I ended up using the *.txt file method for setting the password. Could there be some settings issue that prohibits the /home page from loading on a desktop browser, but not on a mobile?

Is there a parts list for the DeepRacer that includes Amazon links to the parts used or where replacements can be obtained? I need a replacement for the car battery and have not been able to find one that will actually attach to the car - the plug types are different. Where can I buy a replacement for either battery? I need the small one, but might as well get spares for everything. Edited by: Gregory G. Pierce on Oct 12, 2019 3:06 PM

I just noticed there are two quite different Shanghai Sudu track layouts. One is offered when creating a new model (AWS DeepRacer > Reinforcement learning > Create model) and labeled as **Shanghai Sudu Training**. The other is offered on virtual circuit page (AWS DeepRacer > DeepRacer Virtual Circuit > Shanghai Sudu) and labeled just as **Shanghai Sudu**. Does it mean that the models are trained on a one track and then compete against each other on a different one?

Hi I updated reward_function to speed up using params\['steps'] but not working as expected. The reward_function is this ===================================== def reward_function(params): ''' Example of rewarding the agent to follow center line ''' reward=1e-3 # Read input parameters track_width = params\['track_width'] distance_from_center = params\['distance_from_center'] steering = params\['steering_angle'] speed = params\['speed'] all_wheels_on_track = params\['all_wheels_on_track'] steps = params\['steps'] progress = params\['progress'] # Total num of steps we want the car to finish the lap, it will vary depends on the track length TOTAL_NUM_STEPS = 300 if distance_from_center >=0.0 and distance_from_center <= 0.03: reward = 1.0 if not all_wheels_on_track: reward = reward -1 else: reward = reward + progress # add speed penalty if speed < 1.0: reward *=0.80 else: reward += speed **# Give additional reward if the car pass every 100 steps faster than expected** **if (steps % 50) == 0 and progress > (steps / TOTAL_NUM_STEPS) :** **reward += 10.0** return float(reward) ================================================== There was no lines with bold in previous model. I trained for 5 hours but the result is slower than before. with Previous model, I could get 21~24 seconds to run the Empire City track but with the new model after training for 5 hour, I am getting 24~27 seconds. Other Action space and hyperparameters are same. Anybody knows why the result is slower than before?

I've created a model for Kumo Torakku track and got 26 seconds lap time. Actually the model was cloned from others. (Straight Track -> Oval Track -> London Loop). Repetition of training does not reduce lap time. I used hyperparameter as default and changed the Maximum speed to 5 in Action Space. (Others are as default. Steering 30, Steering angle granularity 5, Speed granularity 2) Since I'm familiar with coding, I tried multiple things with reward_function. i.e. distance from center, all wheels on track, steering threshold, speed penalty etc. As I said, there is no improvement at all with this configuration for Kumo Torakku. So I will create new Model. Anybody recommend any Action Space configuration for Kumo Torakku to get better results please? Maximum steering angle : Steering angle granualrity : Maximum speed : Speed granuality : I have read documents for Hyperparameters but no idea what those are. ;( Anybody can recommend good Hyperparameters configuration for Kumo Torakku please?

I think AWS doesn't allow to modify Action Space when Clone a model. There is no Edit feature while reward_function, Hyperparameters and Stop Condition section have the Edit function. Anybody knows how to update Action Space when Clone a model?

Hello, I'm running into problems with resetting my resources. I've noticed this once before after creating a user in IAM to access deepracer - I could reset resources but then it fails to recreate them and complains about existing deep racer roles. After I remove the roles and user it still fails to create, but provides no information. Has anyone had any experience around this? Thanks, Tomasz Ptak

Hi all, Can we use our own computing servers to train and test our models? Or is it necessary to use Amazon servers (and therefore pay) to train and test our models? I am asking because I am thinking to participate in this challenge with some undergraduate students but it would be quite expensive to pay for all students... Thank you in advance for your answer. Best regards, Pierre

Hi all, I am interested in DeepRacer but I am a little bit confused about the information about this information that is provided on https://aws.amazon.com/deepracer/. I can read on the website: **1.** _Virtual Circuit: Join the AWS DeepRacer League from anywhere in the world via the AWS DeepRacer console and put your skills to the test on virtual tracks inspired by famous raceways to be revealed monthly._ **2.** _You can access the simulator from the US East (N. Virginia) region in the AWS console._ Indeed, when I log in AWS, I don't have access to DeepRacer console from Belgium. So I am wondering how people can still participate in the virtual circuit and sometimes summit circuit from anywhere in the world. Can anyone help me to clarify this? Thank you in advance for your answer. Best regards, Pierre

I want to identify events such as the car changing direction or crossing a threshold and calculate how frequently those events happen. This will require a history of values and some knowledge of time. Is there any way to get this data within the reward function? From the examples it seems like we only have the ability to know the cars instantaneous state.

Getting error: “Couldn't retrieve reinforcement learning models” And I’m unable to see any of my models, and the service seems to have lost it’s ‘connection’ with the VPC it built. I have tried to start again, but getting many errors when trying to create the Account resources. Is DeepRacer down?

Getting a strange error when trying to submit my model to the Virtual League. Alias doesn't adhere to our community guidelines. Couldn't set user's alias You have exceeded the number leaderboard submission requests allowed on your account. Failed to create leaderboard submission I tried submitting variations but resulted in the same message. Sad to know my name does not adhere to community guidelines...hahah --Scott Edited by: Scott-Pletcher on Apr 19, 2019 10:24 AM

Hi, Trying to train a deep racer using the vanilla github setup (including redis setup in training_worker.py). Redis sets up fine every time but I get a redis connection error when the simulation complete the first episode of 20 runs. Sagemaker start and Robomaker errors logs below. I have searched high and low to find out what is going wrong and no luck - any assistance appreciated! Excerpt of Sagemaker cloudwatch logs on start up related to redis: --- 22:14:50 Invoking script with the following command: 22:14:50 /usr/bin/python training_worker.py --RLCOACH_PRESET deepracer --aws_region us-east-1 --s3_bucket sagemaker-us-east-1-158249709041 --s3_prefix rl-deepracer-sagemaker-190413-220444 22:14:51 211:C 13 Apr 2019 22:14:51.317 # oO0OoO0OoO0Oo Redis is starting oO0OoO0OoO0Oo 22:14:51 211:C 13 Apr 2019 22:14:51.317 # Redis version=5.0.3, bits=64, commit=00000000, modified=0, pid=211, just started 22:14:51 211:C 13 Apr 2019 22:14:51.317 # Configuration loaded 22:14:51 211:M 13 Apr 2019 22:14:51.319 * Running mode=standalone, port=6379. 22:14:51 211:M 13 Apr 2019 22:14:51.319 # WARNING: The TCP backlog setting of 511 cannot be enforced because /proc/sys/net/core/somaxconn is set to the lower value of 128. 22:14:51 211:M 13 Apr 2019 22:14:51.319 # Server initialized 22:14:51 211:M 13 Apr 2019 22:14:51.319 # WARNING overcommit_memory is set to 0! Background save may fail under low memory condition. To fix this issue add 'vm.overcommit_memory = 1' to /etc/sysctl.conf and then reboot or run the command 'sysctl vm.overcommit_memory=1' for this to take effect. 22:14:51 211:M 13 Apr 2019 22:14:51.319 # WARNING you have Transparent Huge Pages (THP) support enabled in your kernel. This will create latency and memory usage issues with Redis. To fix this issue run the command 'echo never > /sys/kernel/mm/transparent_hugepage/enabled' as root, and add it to your /etc/rc.local in order to retain the setting after a reboot. Redis must be restarted after THP is disabled. 22:14:51 211:M 13 Apr 2019 22:14:51.319 * Ready to accept connections 22:14:56 Redis server started successfully! 22:14:57 Uploaded IP address information to S3: 172.31.27.217 --- Excerpt from robomaker cloud watch logs where it bombs is below (note I've customized some of the messages): --- 22:17:27 Step No=7.00 Step Reward=8.1870 On track?=True Dist from centre=0.02 Frame Progress=0.0000 Total Progress=6.6870 To Finish=93.31 X, Y, Z=2.17, 0.60, 0.00 22:17:27 Action sent to Ros/Gazebo... 22:17:27 Message recieved from Ros/Gazebo... on_track=True 22:17:27 Step No=8.00 Step Reward=8.1870 On track?=True Dist from centre=0.02 Frame Progress=0.0000 Total Progress=6.6870 To Finish=93.31 X, Y, Z=2.19, 0.60, 0.00 22:21:49 Traceback (most recent call last): 22:21:49 File "/home/robomaker/workspace/bundle-store/b56d2ca1-05a5-4aa6-b6d2-84b6766f0d8b/usr/local/lib/python3.5/dist-packages/redis/connection.py", line 484, in connect 22:21:49 sock = self._connect() 22:21:49 File "/home/robomaker/workspace/bundle-store/b56d2ca1-05a5-4aa6-b6d2-84b6766f0d8b/usr/local/lib/python3.5/dist-packages/redis/connection.py", line 541, in _connect 22:21:49 raise err 22:21:49 File "/home/robomaker/workspace/bundle-store/b56d2ca1-05a5-4aa6-b6d2-84b6766f0d8b/usr/local/lib/python3.5/dist-packages/redis/connection.py", line 529, in _connect 22:21:49 sock.connect(socket_address) 22:21:49 TimeoutError: Errno 110 Connection timed out --- Further down the error log... --- 22:21:49 File "/home/robomaker/workspace/bundle-store/b56d2ca1-05a5-4aa6-b6d2-84b6766f0d8b/usr/local/lib/python3.5/dist-packages/redis/connection.py", line 489, in connect 22:21:49 raise ConnectionError(self._error_message(e)) 22:21:49 redis.exceptions.ConnectionError: Error 110 connecting to 172.31.27.217:6379. Connection timed out. 22:21:50 ================================================================================REQUIRED process agent-9 has died! 22:21:50 process has died pid 133, exit code 1, cmd /home/robomaker/workspace/bundle-store/b56d2ca1-05a5-4aa6-b6d2-84b6766f0d8b/opt/install/deepracer_simulation/lib/deepracer_simulation/run_rollout_rl_agent.sh __name:=agent __log:=/home/robomaker/.ros/log/8bfee468-5e39-11e9-a84a-0242a9fe0103/agent-9.log. 22:21:50 log file: /home/robomaker/.ros/log/8bfee468-5e39-11e9-a84a-0242a9fe0103/agent-9*.log 22:21:50 Initiating shutdown! 22:21:50 ================================================================================ 22:21:51 agent-9 killing on exit Edited by: axb2035 on Apr 15, 2019 2:53 AM Edited by: axb2035 on Apr 15, 2019 2:56 AM

Hi, today my DeepRacer arrived after a long journey. At re:Invent i removed the small rc battery but not the big one, because i did not see the battery. After unpacking the packet the big battery is still missing. What will be a suitable replacement for the battery? Thanks Marco